PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
This study explores the impact of synthetic medical images, created through Stable Diffusion, on neural network training for lung condition classification. Using a hybrid dataset combining real and synthetic images, diverse state-of-the-art vision models were trained. Neural networks effectively learned from synthetic data, its performance is similar or superior to models trained purely on real images as long as the training is carried out under equal conditions: same architecture, same number of epochs, same training style, same resolution of the input image. We selected ConvNext-small as our test architecture. Its best performance when trained with a hybrid dataset (synthetic and real images) was 89% while when trained with purely real images it was 85%. These results were obtained when evaluated with an external validation data set curated by a radiologist. However, hybrid models seem to show a limit in their performance when exploring different training techniques. In contrast, a simpler architecture trained with only real images can take advantage of more complex training regimes to elevate its final performance. In this regard, our best hybrid-trained model (ConvNext-small) achieved an external validation accuracy of 87% while ResNet-34 attained a 93% validation accuracy trained only on real images. Both models were evaluated with the real-image-only dataset provided by the radiologist. This study concludes by comparing our top AI models and radiologists’ performance levels.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Our talk introduces a fully automated imaging-based liquid processing platform to revolutionize traditional pipetting in cell culture studies. This system minimizes operational errors by automating processes, significantly enhancing efficiency. With expedited liquid handling and cell imaging capabilities, it maps cellular information. The platform comprises key modules, including Motion, Pipetting, Imaging, and Software, providing precise XYZ axis movement, fluid transfer, cell imaging, and algorithm-driven post-processing and hardware control.
Utilizing a CNC-based Motion Module, the platform navigates well-plates precisely based on g-coding. The Imaging Module displays cells, while the Pipetting Module ensures efficient solution handling. System software, coordinating processes, capturing and processes data, guides investigations into cellular pathways and therapeutic profiling.
The platform incorporates an incubator with customizable settings, maintaining optimal conditions for cellular analyses.
This comprehensive system signifies a significant leap in laboratory technology, promising heightened precision, efficiency, and adaptability for advancing cellular research.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
The incidence of skin cancer has increased in the last decades, being one of the most common cancers, but can have a five-year survival rate of over 99% if treated early. This work describes a novel hyperspectral dermoscope for early skin cancer detection, able to capture spatial and spectral information in the Visible (VIS) and Near Infrared (NIR) ranges by using Liquid Crystal Tunable Filters (LCTFs). KURIOS-VB1 and KURIOS-XE2 filters were used for VIS and NIR ranges, respectively, providing 136 wavelengths with 5 nm of spectral resolution. A dichroic mirror combines output light paths, illuminating the skin's surface via a fiber optic ring light. Reflected light is captured by a 1.3-megapixel monochrome camera. Additionally, a custom hand-held 3D printed part integrates optics and control circuitry. The proposed characterization method used to optimize the camera exposure time for each wavelength has proven effective in obtaining a flat white reference and gathering information in the range of 450 to 1050 nm and, especially, at critical wavelengths such as the test wavelengths evaluated closer to the limit bands of the LCFTs (450 and 600 nm for VIS, and 750 and 900 nm for NIR).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Deep learning models (DLM) encounter challenges in medical image segmentation and classification tasks, primarily due to the requirement for a substantial volume of annotated images, which are both time-consuming and expensive to acquire. In our work, we utilize neural style transfer (NST) to enhance a tiny dataset of ultrasound images, significantly improving the performance of deep learning models (DLM). Additionally, we explore style interpolation to generate new target styles, specifically tailored for ultrasound images. In summary, our objective is to demonstrate the potential utility of neural style transfer in scenarios with limited datasets, particularly in the context of ultrasound images using the dataset of breast ultrasound images (Walid Al-Dhabyani, Mohammed Gomaa, Hussien Khaled, and Aly Fahmy, 2020).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Explainability and bias mitigation are crucial aspects of deep learning (DL) models for medical image analysis. Generative AI, particularly autoencoders, can enhance explainability by analyzing the latent space to identify and control variables that contribute to biases. By manipulating the latent space, biases can be mitigated in the classification layer. Furthermore, the latent space can be visualized to provide a more intuitive understanding of the model’s decision-making process. In our work, we demonstrate how the proposed approach enhances the explainability of the decision-making process, surpassing the capabilities of traditional methods like Grad-Cam. Our approach effectively identifies and mitigates biases in a straightforward manner, without necessitating model retraining or dataset modification, showing how Generative AI has the potential to play a pivotal role in addressing explainability and bias mitigation challenges, enhancing the trustworthiness and clinical utility of DL-powered medical image analysis tools.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Obtaining high-quality images for training AI models in the field of plankton identification, particularly cyanobacteria, is a challenging and time-critical task that necessitates the expertise of biologists. Data augmentation techniques, including conventional methods and GANs, can improve model performance, but GANs typically require large training datasets to produce high-quality results. To tackle this issue, we employed the StyleGAN2ADA model on a dataset of 9 cyanobacteria genera plus non-cyanobacterial microalgae. We evaluated the generated images using both qualitative and quantitative metrics. Qualitative assessments involved a psychophysical test conducted by three expert biologists to identify shape and texture deviations or chromatic aberration that might impede visual classification. Additionally, three non-reference image quality metrics based on perceptual features were used for quantitative assessment. Images meeting quality standards will be incorporated into classification models to assess the performance improvement compared to the original dataset. This comprehensive evaluation process ensured the suitability of generated images for enhancing model performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Research on interpretable CNN classifiers, involves comparing semantic segmentation masks with heat maps designed as visual explanations. A robust explanation accurately identifies or approximates the segmentation of an object. Our focus is on CNN classifiers with enhanced explainability, particularly in the middle layers. To explore this, we propose testing an encoder, trimmed to a medium layer, within a Fully Convolutional Network (FCN). Semantic segmentation is a pivotal task in computer vision preceding object recognition, and demands efficiency to optimize performance, energy consumption, and hardware costs. While various lightweight FCN proposals exist for distinct semantic segmentation tasks, their designs often introduce additional complexity compared to the more basic FCN design we advocate. Our goal is to see how well a minimal FCN works in a simple semantic segmentation task using medical images and how its accuracy changes when the training dataset is shrunk. The study involves characterizing and comparing our minimal FCN against other lightweight deep segmentation models and analyzing accuracy curves concerning the quantity of training data. Utilizing chest CT imaging, we focus on segmenting the lungs. We highlight the importance of data consumption and model size as decisive factors in selecting an architecture, especially when differences in predictive accuracy are marginal. Characterizing deep architectures based on their data requirements, allows for a thorough comparison fostering a deeper understanding of their suitability for specific applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Freeform optics bring new degrees of freedom to optical systems and require the abilities both to describe any surface (continuous or not) and to optimize their shape together with the geometry of the entire system. This increases the number of variables, and therefore the complexity of the fitness function to be minimized in order to obtain highest optical performance. Most proprietary algorithms from commercial solutions cannot handle more than tens of variables and/or noisy function landscape limiting the implementation of such free-form in optical systems. Here, CMA-ES algorithm is coupled to parallel computation of ray tracing simulations able to cover the high computational demand. The benefits of such state-of-the-art evolutionary optimization algorithms is a one-step convergence by exploring the entire landscape of solutions without the need of any starting optical architecture.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Extending the depth of field (DOF) of imaging optics is a longstanding challenge in machine vision, microscopy, photography and cinematography. This paper presents a method to extend DOF of camera lenses up to 5 times by using foto-foXXus - multi-focus quasi afocal optics. The foto-foXXus devices are implemented as achromatic aplanatic optical systems installed in front of camera lenses in such a way that the combined optical system has simultaneously several focuses separated along the optical axis. When applied for imaging a scene, such a combined optical system forms along the optical axis several images of each object of the extended DOF. The inevitable decrease in contrast of the common image, resulting from defocusing of some images from the plane of camera sensor (or film), can be enhanced using specific algorithms in the stage of image processing, which is nowadays an obligatory part of image capture in machine vision or microscopy. This method is very effective in capturing black-and-white objects, such as QR-codes, or in computer vision-based robotic arms for detecting the shape and size of objects. Direct measurements of the modulation transfer function (MTF) and through-focus MTF curves for a system consisting of a foto-foXXus and a state-of-the-art machine vision objective confirm the increase in depth of focus of the combined optical system and, consequently, depth of field in the Object space. The paper presents description of the foto-foXXus devices, measurements data of MTF and through-focus MTF-curves using the MTF test bench, as well as examples of imaging real objects demonstrating effective extending depth of field.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
A novel multichannel optical imaging system capable of high-resolution imaging across a wide field of view (FOV) of 7x7 mm2 with a 4x magnification. Comprised by microlens arrays (MLAs) and micro-aperture arrays, our design circumvents the traditional trade-off between resolution and field size. Each channel of the system is optically isolated by microaperture arrays acting as field stops, ensuring high-quality imaging without crosstalk. A 5x5 step micro-scanning technique extends the imaging capability to the entire FOV. Experimental validation of the prototype, which employs commercially available MLAs and fabricated micro-aperture arrays, demonstrates agreement with theoretical predictions, achieving clear imaging without the need for a large sensor. This approach promises significant advancements in applications requiring detailed imaging over large areas.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Compact wide-angle lenses with adjustable focus have a broad range of applications in emerging technologies. The standard approach to designing lenses with variable focal length is to move a group of lenses along the optical axis. These systems are often bulky due to the need for displacements of a few millimeters or centimeters. To create a compact wide angle lens with a variable focal length, we propose a system including Alvarez and aspherical lenses. The complete system is 18mm long, has a cutoff frequency over 223 lp/mm considering three wavelengths in the visible range: 486, 588, 656 nm, low vignetting, 87.5° FOV, object distance range from 25 cm to infinity.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Adaptive and active optics grant the ability to correct for aberrations, focus and zoom factors changes, and compensate for environmental conditions. Hugely important in physical optics such as high resolution imaging and ground-based astronomy. Presented here is an adaptable lens and mirror technology capable of a full range of focal lengths and shapes. Using transparent oxides and the joule heating effect, local temperature changes can be induced to cause material expansion in a predefined shape based on the thermal distribution. By creating a constriction in the conductive layer adding resistance to the material and creating a localised heating element on the order of millimetres and below in scale. Actively changing the optical systems can be realised on the millisecond timescale additionally allowing an almost arbitrary lens shape as well as variable focal length. Similar effects can be exploited to create a deformable mirror where the active layer is a metallic reflector, such as aluminium or silver, and this layer is used to deliver heat using the same effects. Using this localised heating, focal lengths from infinity to a few centimetres can be achieved through highly expansive substrates and minimal heating and energy usage.
A multitude of such elements can be constructed in such a way to provide a micro-lens array of different focal lengths allowing a field of view with simultaneous focusing on several objects at once for imaging applications. These elements can also be combined over a larger area to create astronomy grade deformable mirrors. The heated areas can be freely designed to any desired shape such as space filling hexagons and create an unconventional adaptive optics systems with advantages over conventional systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Spherical waves emanating from a point are usually modeled in wavefront recording planes perpendicular to their direction of propagation, leading to a symmetric wavefield, typically referred to as a point spread function (PSF). But when the wavefront recording plane is tilted with respect to the hologram plane, this wavefield becomes asymmetric and is typically obtained by the rotation of the frequency domain. This work aims to derive the asymmetric PSF (aPSF) analytically directly in the spatial domain, allowing for the accurate and efficient use of tilted wavefront recording planes in computer-generated holography.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Accurately estimating 3D optical flow in computer-generated holography poses a challenge due to the scrambling of 3D scene information during hologram acquisition. Therefore, to estimate the scene motion between consecutive frames, the scene geometry should be recovered first. Recent studies have demonstrated that a 3D RGB-D representation can be extracted from an input hologram with relatively low error under well-chosen numerical reconstruction parameters. However, limited attention has been given to how the produced error can impact the flow estimation algorithms. Therefore, in this study, we evaluate different learning/non-learning methodologies for recovering 3D scene geometry. Next, we analyze the types of distortions produced by these methods and attempt to minimize estimation error using spatial and temporal constraints. Finally, we compare the performance of several state-of-the-art methods to estimate the 3D optical flow vectors on the recovered sequence of RGB-D images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Color holographic displays typically independently manipulate and combine light for three different wavelengths. Recent advances have made it possible to jointly encode a single extended-phase spatial light modulator (SLM) pattern modulating all colors simultaneously to display holograms at higher framerates and qualities. However, this inevitably leads to “color replicas”, where the objects at one wavelength are replicated at different depths for different colors, leading to disturbances in the viewing experience, thereby limiting its usefulness for 3D displays. We propose a novel coded illumination scheme to decorrelate the different color signals, eliminating the color replicas. We present the novel joint-color coding CGH algorithm, as well as an additional calibration algorithm, showing significant improvements in visual quality with a minor modification to the optical display setup.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
During the quantization of the hologram values part of the information is lost, which introduces quantization noise in the reconstruction. To enhance the hologram quality, we developed in a previous work a view-dependent error diffusion algorithm which rejects the quantization noise in specific views. However, this algorithm is slow which prevents its use in real-time applications. In this paper, we present a GPU implementation of this technique which uses the inherent parallelism of the error diffusion algorithm. Moreover, we introduce a technique to select diffusion weights, which allows a trade-off between computation time and reconstruction quality. Experimental results demonstrate the ability of our approach to quickly generate high-quality holograms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Linear Canonical Transformations are phase space deformations that can be used to describe linear optical systems. In geometric optics they correspond to the transformations of the light rays during propagation in arbitrary media, while in wave optics they describe the evolution of the space-frequency components. Although their meaning is non-ambiguous in the former case, in the latter it depends on the specific space-frequency decomposition of the wavefield. In this paper we gather several results from theoretical time-frequency analysis with Gabor Frames and provide a preliminary analysis on the implementation of phase space deformation for linear optical systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Despite many years of development in computer-generated holography, perfect phase-only holograms for most target images are still yet possible to compute. All computational phase retrieval algorithms end up with some error between the target image and the reconstruction of the computer-generated hologram (CGH), except for specific targets. This research focuses on the fundamental limits of phase-only CGH quantized to limited bit-depth levels, from the information theory point of view, revealing the information capacity of CGH and its effect on reconstruction quality, with an attempt to quantify how hard a target image is for phase-only hologram computation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
In this paper, we investigate the application of Gabor Frames (GFs) as an effective Time-Frequency (TF) analysis tool for compressing digital holograms. Our choice of GFs stems from their notable flexibility and accuracy in TF decomposition. Unlike some other techniques, GFs offer the advantage of accommodating both overcomplete and orthonormal signal representations. Furthermore, GFs have a robust mathematical foundation, opening doors to a broad spectrum of potential applications beyond compression. First, we provide an overview of essential concepts in GFs theory like dual GFs, analysis and synthesis operators. Second, we illustrate how GFs can be employed for digital holograms representation in the phase space domain. For compression purpose, we substitute the Short-Time Fourier Transform (STFT) used in the JPEG-PLENO Holography codec by tight GFs, and compare their encoding performance. We present and thoroughly discuss the rate-distortion graphs, shedding light on the efficacy of GFs in digital hologram lossy compression.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Multiphoton microscopy (MPM) is an advanced imaging technique used in biological and biomedical research to visualize and study living tissues and cells with high resolution. It is particularly well-suited for deep tissue imaging, as it minimizes photodamage and provides improved penetration compared to traditional microscopy techniques like confocal microscopy. The Point Spread Function (PSF) plays a crucial role in multiphoton microscopy and describes how a point source of light is imaged as a spatial distribution in the microscope. Understanding the 3D PSF is essential for deconvolution and other post-processing techniques used to reconstruct 3D images from a stack of 2D images. The imaging of fluorescent beads used as point sources is a solution to evaluate the PSF. Usually, this strategy involves a bead of dimensions smaller than resolutions, typically with diameter of about less than 200 nm. However, in this setting, it is often complex to detect correctly the beads and thus to estimate accurately the PSF. We develop a computational solution for the PSF estimation based on the imaging of micro objects bigger than the resolution limit. We use fluorescent microspheres with a diameter of 1 μm and estimate the PSF from the deformations observed in the image of these microspheres. A deconvolution strategy illustrates the performance of our method, where we successfully restore an unsliced whole striated skeletal muscle utilizing the PSF estimated with 1 μm diameter beads.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Confocal microscopy offers enhanced image contrast and signal-to-noise ratio compared to wide-field illumination microscopy, achieved by effectively eliminating out-of-focus background noise. In our study, we initially showcase the functionality of a line-scanning confocal microscope aligned through the utilization of a Digital Light Projector (DLP) and a rolling shutter CMOS camera. In this technique, a sequence of illumination lines is projected onto a sample using a DLP and focusing objective (50X, NA=0.55). The reflected light is imaged with the camera. Line-scanning confocal imaging is accomplished by synchronizing the illumination lines with the rolling shutter of the sensor, leading to a substantial enhancement of approximately 50% in image contrast. Subsequently, this setup is employed to create a dataset comprising 500 pairs of images of paper tissue. This dataset is employed for training a Generative Adversarial Network (cGAN). Roughly 45% contrast improvement was measured in the test images for the trained network, in comparison to the ground-truth images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
This study proposes a novel approach in response to the persistent challenge of achieving precise autofocus in Digital Lensless Holographic Microscopy (DLHM). It involves employing an enhanced Bluestein algorithm to simulate DLHM holograms under a variety of conditions, spanning amplitude-only, phase-only, and amplitude-phase objects. These simulated holograms are used to assess the performance of autofocus metrics, including the Dubois and Spectral Dubois metrics, gradient and variance-based approaches, and lastly a learning-based model. By considering the variety of sample types and geometrical configurations, this study delves into the robustness and limitations of these metrics across diverse scenarios. This research reveals different performances depending on sample characteristics, offering valuable insights into selecting the most suitable autofocus metric, which is a demanding step in practical DLHM applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Classical and linear measurements are bound by the shot noise limit. In optics, the sensitivity increases i) with the square root of the number of photons detected, or ii) with the photons-sample interactions. Case (i) is limited by how safe or efficient is the power level, while (ii) is limited by how to achieve and resolve any number of interactions. We report a versatile interference contrast imaging technique, which extracts more information per photon resource than any linear phase imager to date. It is based on a non-resonant multipass design that allows to efficiently implement case (ii) and extract holographic information by using a single photon camera. It has been designed as a wide-field imaging (i.e., without requiring pixel-scanning) technique, able to image highly transparent/reflective samples, with noise reduction beyond 0.22 in less than 7 rounds.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Controlling and understanding light propagation through a multimode fiber (MMF) requires knowledge of an optical Transmission Matrix (TM). Holography is essential for extracting phase information from intensity measurements, enabling the TM measurement. Usually, complex optical fields are retrieved through its interferences with a plane wavefront. Here we demonstrate and study TM measurements of an MMF using a self-reference approach, emphasizing its strengths and limitations. We focus on compensating for phase fluctuations to enhance image quality. The efficiency of this approach in precise TM measurements is experimentally confirmed by demonstrating high-quality light focusing, as well as complex patterns transmission through an MMF. This work enhances the understanding of self-reference holography in complex scattering media and its practical applications, particularly in studying and controlling light within MMFs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
A novel ImageJ plugin is designed to extend the depth-of-field (DoF) by seamlessly fusing a series of multi-focus images, allowing for in-depth analysis. Moreover, it has been tested on multi-exposure image stacks, demonstrating its adeptness in preserving intricate details within both poorly and brightly illuminated regions of 3-D specimens. The significance of this capability becomes particularly apparent when dealing with images that exhibit a limited DoF and varying exposure settings under low signal-to-noise ratio conditions. The plugin’s effectiveness has been thoroughly validated through the processing and analysis of numerous image stacks featuring diverse diatom and cyanobacteria species. The proposed methodology incorporates a two-scale decomposition (TSD) scheme, complemented by the refinement of weight maps using edge-preserving filtering (EPF). This dual approach ensures the preservation of fine details in the fused image while simultaneously minimizing noise. Such innovations make this plugin a valuable tool for researchers and analysts working with complex image datasets.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Near-eye displays (NED) are devices that are intended to project three dimensional images with wide-angle view. However, at present most of the 3D displays are based on stereoscopic principle, which does not satisfy the required parameters of human vision. This limitation can be overcome by implementing digital holograms within the NED. This is because a digital hologram contains the whole wavefront information of the scene. Thus, a holographic NED (HNED) is capable to reconstruct any three-dimensional scene while matching all the physiological cues of human vision. Nevertheless, truly immersion experience in HNED requires wide angle view and full colour reconstruction as well. In this work, we study HNED for pupil and non-pupil configuration that reconstructs large 3D colour scenes. The colour reconstruction is made by using RGB illumination and time multiplexing. Numerical analysis is carried out to test the FOV and the quality of reconstructions. Moreover, experimental colour reconstructions are made by employing laser for the pupil configuration and LED for non-pupil configuration. This is done to compare reconstruction quality and FOV of the displayed 3D scene.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
By using a method of expanding the depth of field, the VAC problem can be alleviated, and when applied to an AR optical system, clear virtual image can be delivered even under conditions that deviate from the depth of the virtual screen. In achieving these conditions, an optical system was developed that demonstrates the possibility of a simpler EDOF optical system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Photonic Integrated Circuits (PICs) are chips with optical inputs and outputs that are linked by waveguides. They allow for a better control over the light propagation and an improved mechanical stability with respect to free space optical systems. In this article, a three-dimensional photonic integrated circuit (3D PIC) for hyperspectral imaging is proposed. We will also present our latest numerical and experimental results toward the fabrication of a hyperspectral imaging system using 3D PICs fabricated using an ultrafast femtosecond laser in a glass chip.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
We propose digital correction methods for recovering aberrated spectra in a portable low-cost miniaturized grating-based spectrometer, which is modelled in optical and numerical simulations. To realize the digital spectrum recovery, different Point Spread Function (PSF) modelling approaches for wavelength-dependent PSFs are proposed and implemented into four digital correction algorithms, namely inverse Fourier Transform (IFT) deconvolution, Wiener deconvolution, Lucy-Richardson (LR) and Landweber iterative algorithm. Results show that both LR and Landweber algorithms can improve the spectral resolution by about a factor of two. The enhanced spectral resolution is comparable to that of commercial table-top spectrometers, while our spectrometer has a much smaller packaging volume of about one cubic inch.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
This paper presents a novel comparative study between two prominent compressed sensing algorithms – Orthogonal Matching Pursuit (OMP) and Iterative Hard Thresholding (IHT) – within the context of digital holography, specifically focusing on their efficacy in handling phase discontinuities. Previous research has predominantly centered on Gibbs ringing artifacts in image reconstruction and their mitigation. However, the aspect of phase discontinuities, which are critical in holographic imaging, has not been extensively explored. Our study implement both OMP and IHT algorithms in a simulated digital holographic environment, where phase discontinuities are inherent due to the nature of holographic imaging. We analyze how these algorithms perform in the presence of phase discontinuities. We quantitatively analyze the performance of each algorithm in handling phase discontinuities. Additionally, our study delves into the computational efficiency of both algorithms, considering their practical applicability in real-time holographic imaging systems. The results of our comparative analysis provide insights into the advantages and limitations of OMP and IHT in the context of phase discontinuities. Our findings have significant implications for advancing digital holography, particularly in applications requiring precise phase information, such as medical imaging, microscopy, and non-destructive testing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
In this work, we present a histogram post-processing method for Single Photon Avalanche Diode (SPAD)-based direct Time of Flight (d-ToF) depth measurement systems that compensates for the nonlinear behavior of the SPAD. The proposed compensation method approximates a linear behavior of the SPAD detector over time, resulting in a linearized histogram of timestamps even under strong background illumination conditions. The process can compensate for the distortion problem known as pile-up, which causes the corruption of the histogram of timestamps due to the variability of the intensity of the background and reflected laser light. The proposed approach has been first demonstrated with simulations, based on a physical model for the computation of the optical power budget and a numerical engine for the generation of the simulated train of timestamps. In particular, we consider a set of realistic parameters for typical SPAD-based d-ToF sensors, allowing us to validate the compensation method over a wider range of values. Finally, the method is validated with data from a real d-ToF sensor to demonstrate the effectiveness in mitigating the pile-up distortion phenomenon in the computation of the ToF.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Non-invasive, automated, and continuous 3D plant imaging is important for studying plant development, performing digital phenotyping, and detection of plant diseases. In this study, we reconstructed 3D plant structural and fluorescence plant images using an automated monocular vision-based structure from motion technique requiring only 2 RGB images. By using different exposure durations and RGB spectral filters we are able to acquire both white light structural information and fluorescence functional information in a single acquisition. The combined structural and function information enables us to observe and locate the plant disease of autofluorescing downy mildew lettuce plants in 3D. We demonstrate the effect of important parameters such as exposure duration and sampling frequency on the 3D reconstruction quality. We believe that our work will enable plant biologists and plant breeders to aid in understanding plant-pathogen interactions, plant development, and to utilize this for breeding more disease resistant crops.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
The olive oil industry plays a significant role in the global agricultural economy, with the quality of olive oil greatly dependent on the quality and ripeness of the olives used in its production. Accurate and efficient sorting and classification of olive fruit are crucial steps in optimizing olive oil yield and quality. In this scientific project, we propose a novel approach to automate the classification of olive fruit based on their ripeness and quality using computer vision techniques. The visual system is composed of a segmentation and classification deep network, based on YOLO architecture. In practice despite the processing unexpected foreign objects may be present as well (e.g. leaves, twigs etc), which may lead to erroneous classification to one of the existing classes. A classification problem is therefore defined. The experimental results validate the utility of the approach with high classification accuracy based on expert annotation and demonstrate high detection rates for outlier objects. The speed of the system ensures a high production throughput.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Mie lidar has been profoundly applied in the retrieval of aerosol optical coefficients in vertical distribution. However, few studies further explore the strategies for the retrieval of aerosol mass profiles quantitively from lidar observation. To meet the rising demand of aerosol mass concentration in spatial and temporal distribution, an iteration algorithm for profiling aerosol mass composition as well as extinction coefficient based on spaceborne dual-wavelength lidar data is proposed. By constructing the relationship between mixed aerosol mass profiles and optical properties at different wavelengths, new constraints are induced to improve the accuracy of lidar ratio. Meanwhile, aerosol composition profiles can also be deduced based on the a prior estimation of aerosol compositions and intrinsic optical features of the aerosols. This method has been verified by simulated lidar signals and CALIOP data, suggesting potential applicability in satellite data processing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Malaria, a significant global health concern, necessitates precise diagnostic tools for effective management. This study introduces an innovative approach to malaria detection using advanced machine-learning techniques. By harnessing convolutional neural networks (CNNs) and deep learning, the research presents a robust framework for automated malaria detection through microscopic images of red blood cells. The study evaluates three key algorithms—CNN, VGG-16, and Support Vector Machine (SVM)—using a meticulously curated dataset of 27,560 images. Results highlight the VGG-16 model’s exceptional accuracy, achieving 98.5%. Transfer learning is pivotal in its success, demonstrating the power of pre-trained models for medical image analysis. This research advances automated disease diagnosis, particularly in resource-limited settings. Future work involves fine-tuning algorithms, exploring ensemble techniques, and enhancing interpretability for broader healthcare applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Conventionally, LCoS, μ-LEDs, and LBS are the principal micro-displays used in Near-Eye displays. We propose an alternative display concept, which offers increased flexibility for its integration with the optical combiner, resulting in a more efficient energy yield. The concept is based on photonic integrated circuits (PIC) in the visible range, active light extraction components using liquid crystals, and pixelated holograms. The combination of these elements enables the generation of an emissive point, whose properties: position, emission angle, and divergence are adjustable. We describe our concept and compare the expected performances with conventional solutions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Object tracking with subpixel accuracy is crucial in experiments where the object’s apparent movement on the camera sensor is very small. This situation can occur when the movement is inherently minimal or when it takes place at a significant distance from the camera. Achieving accuracies beyond 0.01 pixels requires careful planning and noise cancellation to obtain precise and consistent results. Therefore, it is imperative to meticulously design experiments in the laboratory to determine the true performance under the best possible conditions.
To achieve high subpixel accuracy, it is necessary to find a balance among the camera's features, the object to camera distance, and the object’s speed. These parameters collectively define the final pixel-to-millimeter ratio, which ultimately determines the method’s accuracy.
Additionally, selecting the appropriate algorithm is fundamental for accurately determining the target’s position. In our case, we employ normalized cross-correlation between images with analytic interpolation of the correlation peak.
A drawback of subpixel tracking approach is that tracking targets with subpixel accuracy makes the system highly sensitive to thermal errors. Heating of the electronics can lead to the expansion of the camera casing and sensor, resulting in drifts and distortions in the final image.
In our presentation, we will show different combinations that ensure precise subpixel accuracy while accounting for observed thermal distortions. Following our results with Basler cameras, our recommendation is to use the lowest target speed with a temporal resolution to achieve an apparent interframe shift of less than 0.004 pixels and at least 2 hours of stabilization time.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
The design and adjustment of image-based detection and tracking systems require the use of calibrated sliders on which to place the targets. Scientific-grade sliders often provide high precision and repeatability (1 micron), although they are frequently expensive and can only move small-size and lightweight targets, limiting their applications.
In our research work, we need to conduct motion detection tests with subpixel precision by tracking natural textures on stone materials. The test samples used in the laboratory can weight more than 1 kg to have a statistically representative amount of texture details. This weight makes them too heavy for scientific sliders.
In this work, we propose the use of photographic sliders as precision displacement systems. Since these systems are designed for artistic purposes, precise calibration is necessary for their use in accurate displacements. The calibration procedure involves the precise tracking of a circular target’s centroid location with subpixel accuracy. To achieve this, the slider’s speed and the camera’s acquisition time are adjusted, ensuring that interframe is around 0,1 pixels. The same trajectory is assessed at various displacement speed to determine both the repeatability and linearity in velocity and positioning.
The tests were conducted using a Thorlabs DDS100/M linear slider and an Edelkrone One photographic slider. The results demonstrate that the photographic slider delivers a similar level of precision at just one-fifth of the cost when compared to the Thorlabs slider.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Achieving subpixel accuracy in object tracking presents significant advantages for motion and deformation analysis. While accuracies exceeding 0.01 pixels are attainable under optimal conditions, sustaining these conditions is often limited to short durations. The heating of devices can induce sensor and housing expansion, resulting in image distortions. In this study, we investigate thermal effects by capturing static sequences of a binary target comprising a matrix of circles. Images were captured every two minutes over a 15-hour period. Subpixel tracking of image drifts and deformations was achieved by locating the centroid of each circle. We evaluated the performance of a Basler Ace2 camera both in its standard configuration and with a heat sink accessory, demonstrating the effectiveness of the heat sink in reducing stabilization time and minimizing drift and distortions. Our findings indicate that while incorporating a heat sink offers advantages, potential drawbacks must also be considered.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Semantic segmentation is a suitable deep learning method to determine the area of an object without marking the object in a rectangular box and assigning it to a class. With semantic segmentation, each pixel of an image can be optimally assigned to a class. This is particularly advantageous when determining the degree of coverage of different habitats in the Wadden Sea, such as mussel beds. In this paper, two well-known segmentation methods, U-Net and Mask R-CNN, are compared. Experimental results of the deep learning evaluation are presented. Evaluation metrics such as intersect over union (IOU) and mean average precision (mAP) are compared. IOU is a particularly interesting metric in this use case, as it specifically concerns the degree of coverage, i.e. the correct recognition of an area. In addition, the specific selection criteria of the networks used and a justification for the final network used are given. Furthermore, the requirements analysis lists the specifications that distinguish this project from others. Images taken by a drone are used as training and test data. More information about the drone, the camera and the flight altitude can be found in the paper. The aim is to validate satellite data, which in the past has always been done by hand or on foot. In particular, the strengths and weaknesses of U-Net and Mask R-CNN are explored and described in this work. The dataset used, the parameters set and the computational and time effort are explained in more detail. In particular, our deep learning evaluation shows a significant milestone with an outstanding IOU of over 85%, confirming the ability of semantic segmentation to accurately define object areas within the diverse habitats of the Wadden Sea.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Advanced information technologies, such as the fifth-generation mobile networks (5G), unmanned aerial vehicles (UAV), and artificial intelligence (AI), build the foundation for integrated autonomous systems in smart agriculture that contribute to the sustainable transformation and optimization of agricultural processes, such as weed control. Weed control is a particular challenge for specialty crops, as it is labor-intensive, and the widely used chemical weed control is increasingly subject to legal restrictions. A new Regulation on the Sustainable Use of Plant Protection Products was adopted by the European Commission in 2022 that targets to reduce the use of chemical pesticides by 50% by 2030. This paper proposes a sustainable weed control approach based on tree crown detection using remote sensing data and evaluates the state-of-the-art deep learning architectures YOLOv4-tiny, YOLOv4-tiny-3l, and YOLOv7-tiny using a five-fold cross-validation with image inputs sizes of 832 x 832 and 1152 x 1152 pixels. The deep learning architectures are trained and evaluated with a custom dataset of 63 individual UAV-based images with 1,380 transplanted three-year-old Christmas trees under normal production conditions. The selected deep learning models achieve an average precision (AP) at an intersection over union (IOU) threshold of 0.5 above 97%, showing that all selected architectures are suited for this specific application. Neither a significant interaction effect nor significant main effects of the deep learning architecture or the image input size could be observed on the AP.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
To realize three-dimensional (3D) displays observable from all directions, we propose utilizing a hyperboloidal mirror to reflect light in all directions. The hyperboloidal mirror has two focal points in imaging relation. Thus, an image displayed near one focal point is reconstructed as a virtual image near the other focal point after the hyperboloidal mirror reflection. Owing to the geometrical property of the hyperboloidal mirror, the diverging angle of the reflected light can be much larger than that of conventional planar displays. However, there is a problem that the imaging magnification ratio depends on the propagation direction. This is one reason for distortion in hyperboloidal mirror imaging, and must be solved appropriately. This paper proposes a technical method to overcome the above distortion depending on the propagation direction by multi-view-based integral imaging. In integral imaging, the propagation direction of each elemental image is optically limited; therefore, the magnification ratio can be regarded as approximately constant within each propagation. Thus, the combination of integral imaging and hyperboloidal mirror reflection enables display of arbitrary multiple images with a very wide viewing zone without specially caring about the distortion. By displaying multiple images with proper parallax corresponding to the propagation directions, a full-parallax multi-view-based 3D display can be realized. In this study, a large hyperboloidal mirror with a diameter of 15 cm was used, and a 3D display with the horizontal and vertical viewing zones of 135° and 60°, respectively, has been successfully demonstrated.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Pressure ulcers are a significant concern in intensive and long-term care settings, posing a substantial financial burden with costs reaching approximately $167,000 for a four-stage ulcer. These ulcers progress from stage 1 to stage 4, with stages 3 and 4 marking a transition to irreversible inflammation, underscoring the importance of early diagnosis and treatment. The incidence and prevalence of pressure ulcers vary internationally, with reports indicating an average of 22-44% in intensive care units across US hospitals. Given their substantial prevalence and the financial and human costs involved, early treatment and prevention are paramount healthcare objectives. In response, we introduce an algorithm for a pressure ulcer treatment device, leveraging biophotonics sensor technology for impedance measurement and light irradiation, as developed in prior research. This algorithm generates a wound map from impedance data, facilitating tailored light output adjustments for each impedance pin based on the map. Validation through 10-Fold Cross Validation yielded an accuracy rate of 91% for the algorithm. Furthermore, we posit that ongoing advancements in mobile healthcare and data analytics will significantly enhance the efficacy of pressure ulcer treatment devices, streamlining management processes.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Deep neural networks automatically extract features; however, in many cases, the features extracted by the classifier are biased by the classes during the training of the model. Analyzing 3D medical images can be challenging due to the high number of channels in the images, which require long training times when using complex deep models. To address this issue, we propose a two-step approach: (i) We train an autoencoder to reconstruct the input images using some channels in the volume. As a result, we obtain a hidden representation of the images. (ii) Shallow models are then trained with the hidden representation to classify the images using an ensemble of features. To validate the proposed method, we use 3D datasets from the MedMNIST archive. Our results show that the proposed model achieves similar or even better performance than ResNet models, despite having significantly fewer parameters (approximately 14,000 parameters).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
This paper presents the evaluation of object detectors and trackers within a parallel software architecture to enable long distance UAV detection and tracking in real-time using a telescope-based optical system. The architecture combines computationally expensive deep learning-based object detectors with traditional object trackers to achieve a detection and tracking rate of 100 fps. Four object detectors, FRCNN, SSD, Retinanet and FCOS, are fine-tuned on a custom UAV dataset and integrated together with three trackers, Medianow, KCF and MOSSE, into a parallel software architecture. The evaluation is conducted on a separate set of test images and videos. The combination of FRCNN and Medianow shows the best performance in terms of intersection over union and center location offset on the video test set, enabling detection and tracking of UAVs at 100 fps.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Most bacteria classifiers created by neural networks and/or image processing methods are unable to generalize when used with different data bases of images acquired with the same type of acquisition systems, even if the sample preparation is similar. In this work, we introduce an ensemble of deep neural networks designed for the classification of bacteria in a broad context. We use a dataset comprising Actinomyces, Escherichia, Staphylococcus, Lactobacillus, and Micrococcus bacteria with Gram staining, which was acquired through brightfield microscopy from various sources. To normalize diversity of image characteristics, we applied domain generalization and adaptation techniques. Subsequently, we used phenotypic characteristics, such as the color reaction to Gram staining and morphology, to classify the bacteria.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
In Machine Learning projects effective preparation of training datasets is essential. When dealing with image datasets, especially limited ones, data augmentation techniques play a crucial role in increasing the dataset size and diversity. These techniques, spanning from basic to deformable to deep learning augmentations, offer varying effects from simple noise addition to generating entirely new synthetic images.
In this study, we propose an alternative approach to augmenting a dataset utilizing a technique found in video processing called Video Frame Interpolation (VFI). Unlike traditional methods, with VFI we aim to produce images that are neither mere variations of the original images nor entirely synthetic ones, instead providing a middle ground where the images generated are synthetic temporal variations of the original ones. We propose to use pre-trained VFI networks in conjunction with Transfer Learning to develop specialized models capable of interpolating medical images with enough precision so that a medical specialist would deem them clinically plausible.
For this study, we worked with a model developed by Niklaus et al., on cardiac ultrasound videos and images alongside a seasoned cardiologist to provide an expert evaluation on the viability of this technique. Our findings indicate that the results produced by our fine-tuned model can indeed be considered realistic, and depending on the use case, the results of the pre-trained model can also be useful.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
In recent years, many novel phase space distributions have been proposed and one of the more independently interesting is the Bai distribution function (BDF). The BDF has been shown to interpolate between the instantaneous auto-correlation function and the Wigner distribution function, and to link the geometrical and wave optical descriptions in the Fresnel domain. Currently, the BDF is only defined for continuous signals. However, for both simulation and experimental purposes, the signals must be discrete. This necessitates the development of a BDF analysis workflow for discrete signals. In this paper, we will analyse the sampling requirements imposed by the BDF, and demonstrate their correctness by comparing the continuous BDFs of continuous test signals with their numerically approximated counterparts. Our results will permit more accurate simulations using BDFs, which will be useful in applying them to problems in, e.g., partial coherence.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
A small field of view is one of the main limitations of holographic displays that prevent holographic displays from being successful commercial products. Although several methods have been proposed and shown some abilities to extend the replay field, they either introduce high-cost components or have complex experimental setups. In this paper, we propose a new method to extend the field of view of holographic display systems. The proposed method is based on an off-axis holographic display with two laser beams and one SLM. The SLM is illuminated by two laser beams from different angles and the holograms displayed are synchronized with alternating laser beams. Experimental results demonstrate that the proposed method can extend the replay field by two times with high-quality image reconstruction, less cost and simple experimental setups.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Holography has amassed increased attention over time, especially in direct recording using CCD arrays and numerical reconstruction. This surge is particularly notable in 3D imaging techniques like Digital holographic microscopy (DHM), which serves as a non-contact profilometric instrument for revealing the topography of microscopic objects. As for, multiangle digital holographic profilometry (MIDHP) combines DHM and multi-angle interferometry has a good ability to measure the profile of samples and solve the 2π ambiguity problem. Despite significant progress in MIDHP, challenges arise from computation inaccuracies or data deficiencies, especially in the presence of aberrations when acquiring sufficient information of high numerical aperture (NA) samples using the classical compensation method. To address this, we introduce spherical-wave illumination scanning digital holographic profilometry (SWS-DHP), which has proven to be effective in profiling high-NA objects. Since the classical aberration compensation proved inadequate in this case, this paper proposes a new aberration compensation method based on the propagation of object and illumination waves, automatically correcting aberrations within the entire 3D volume of the reconstruction. Our investigation employs a model-based approach, and the accuracy of this new method will be tested numerically and experimentally, particularly on high-NA and high-depth objects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
One of the parameters of eye movement recording devices is their sampling rate. It has been widely studied how the sampling rate of eye trackers affects the assessment of saccadic eye movement parameters. It has also been investigated whether the sampling rate of eye trackers affects the duration of fixations and saccade parameters during reading. In studies analyzing fixation stability, measurements are taken at different sampling rates, but how the sampling rate affects this fixation parameter has not been extensively investigated. Fixation stability is commonly quantified using bivariate contour ellipse areas (BCEA). The aim of this study was to determine whether the sampling rate of an eye tracker affects the measurement of fixation stability. Participants in the study were adults aged 20 to 30 years. Their eye movements during fixation were recorded using the Tobii Pro Fusion eye tracker. The fixation target was presented on a computer monitor, and eye movements were recorded at three sampling rates: 60 Hz, 120 Hz, and 250 Hz. The results demonstrated strong correlation between the BCEA measurements of each participant across all used sampling rates. However, when analyzing the overall data, there is no significant effect of the sampling rate on fixation stability measurement.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
The usual optimization methods in optical design like those available in CodeV and Zemax, while powerful, are very dependent of the starting system and the chosen merit function. Moreover the number of lenses is by the way defined. We present a novel global optimization approach employing saddle point construction that overcomes these limitations. This method facilitates the systematic exploration of design space by adding constructively new lens, leading to innovative, high-performance optical solutions. As study case we consider a wide-angle eyepiece with six lenses. Our findings retrieve the solutions obtained by CodeV global optimizer and a few more with less lenses. For the moment this optimization approach is limited to on-axis systems with spherical lenses.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Solving the problem of reverse engineering as a key element of the production process and its technological preparation has a key role. This work demonstrates for the first time the possibility of preparing production and collecting key indicators, which allows you to recreate a digital twin of the technological process and display the technological aspects of the design as a result of collecting key indicators. Such indicators include the width of the cut layer, the cutting zone of a conical cutter during multi-axis positioning, obtained based on the results of processing a group of images of processed products. Actual technological indicators of the technological process can be identified and numerically formalized by assessing the shape of the helical surface on a class of parts obtained as a result of multi-coordinate processing, which proves the possibility of applied application of the method in the structure of the production process in real time. As a result, the use of a new algorithm will reduce the likelihood of receiving defective products and recreate the technological process based on processing a set of product images. The work constructs an analytical model for the automated creation of processing paths based on improved B-splines, which can significantly improve smoothness compared to numerical methods for generating paths. The actual technological indicators of the machining process can be identified and numerically formalized dependencies by determining the influence of the helical surface on the precise positioning of the end mill with compensation along each axis during 5-axis machining, obtained as a result of multi-axis machining, which proves the possibility of applied application of the method in the production process in the mode real time.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
In precision engineering, helical surfaces on critical parts of equipment have become widespread. The article proposes an new method and practical recommendations for measuring geometric accuracy, linear and angular measurements, and studying the characteristics of helical surfaces and specialized equipment for monitoring the accuracy of helical surfaces. The uniqueness of the approach lies in the formation of key indicators of classification and filtering of a set of specialized measurement techniques based on scanning and digital image processing. A new method is proposed that makes it possible to adjust the measurement of the coordinates of the profile points of the helical surface in the radial section according to the shape of the focal area on the helical surface obtained by a reflected light camera. The work established new indicators of the effectiveness of tool control for high-speed multi-axis milling based on recommendations for the selection of methods and means of monitoring and control at the stage of technological preparation of production in real time. Criteria and indicators have been formed to eliminate errors at any stage in the process of digital control of images of the helical surface of a cutting tool for high-speed machining. The method consists in determining the law of preserving the shape of the profile, its further rotation and comparison with the original control profile by identifying a new relationship between the focal length and the profiling shape. The shape of the profiling curve is described depending on the angle of inclination of the helical flute, diameter, segmentation of the image in the focal zone and the magnitude of the error when measuring the profile in real time relative to the base profile. In this regard, the work justifies the practical adaptation of the search results for key measurement schemes in comparison with other existing methods for helical surfaces with an rake angle of the tangent to the profile in the axial section. The new level of production creates greater demand for product quality efficiency in a unified digital environment. As an advanced solution, the work proposes a method for compensating for errors in the shape of the focus area. This method allows you to compensate for the error in real time without stopping for readjustment. More accurate results allowed for an increase in accuracy up to 10 times compared to existing methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Caterpillars pose a significant threat to agriculture, devouring crop foliage and evading traditional pest control methods like sticky or pheromone traps. While chemical pesticides are effective, concerns arise over crop residues. This study aims to address these challenges by tracking and estimating caterpillar positions in orchards in real-time, leveraging the Intel Realsense D405 RGB-D camera. Training data comprises 2,000 images from a jujube orchard, capturing diverse conditions such as exposure, occlusion, and wind. Real-time inference yields promising results, even recognizing the smallest 2-cm caterpillar at 21x12 pixels from a distance of 35 cm. The transition from YOLOv7 to YOLO NAS and from DeepSORT to SORT enhances detection by 30%, surpassing 95% accuracy. This innovative approach not only offers improved pest detection but also holds promise for integration with various technologies. From employing robot arms for targeted caterpillar removal to implementing laser pest targeting, this breakthrough contributes significantly to sustainable agriculture. By addressing the critical need for effective and environmentally friendly pest control practices, it helps ensure the long-term viability of agricultural systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Diffraction calculations are essential in optics, including holography, optical element design, and information optics. Convolution-based diffraction calculations can be accelerated by Fourier transforms; however, they often suffer from ringing artifacts (a.k.a. Gibbs phenomena) due to the non-continuous borders of the calculation windows. Suppressing techniques for ringing artifacts have been proposed so far, but these techniques are time-consuming and use large amounts of memory. This study presents a ringing artifact reduction using the Fresnel integrals.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Brain tumors represent a critical health challenge, underscoring the urgency of accurate detection for timely intervention. Our study addresses this vital need by employing advanced machine learning techniques. We introduce a novel approach utilizing Convolutional Neural Networks (CNNs) for precise brain tumor classification. Our method involves custom data preparation, a network design and thorough training to improve precision. Additionally, we incorporate the known VGG16 structure into our strategy. Initial findings demonstrate the promise of our algorithm, the VGG16 version in outperforming techniques, for identifying brain tumors. With a remarkable 91.00% accuracy rate for VGG16 - Scenario 1 and a significantly improved 78.33% accuracy for CNN - Scenario 2, our findings highlight the superiority of our CNN-based methodology in achieving higher accuracy. As we continue to refine our approach, we anticipate making significant contributions to the medical field’s ability to accurately diagnose brain tumors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Blood cancer remains a major global health challenge, emphasizing the critical need of early diagnosis, for effective treatment and improved patient outcomes. Recently, quantitative phase imaging (QPI) based study of cancerous cell morphology, viability and proliferation, attracts the attention of the pathologist and researchers. In this research article, we have introduced customized QPI based imaging tool for investigation of malignant blood cells for the early detection of cancer. The proposed tool enables the measurement of optical path length variations which gives the provision of label-free, high-resolution imaging of blood cells, allowing for the precise quantification of cellular parameters such as volume, thickness, and dry mass. The proposed low-cost configuration referred as self-referencing QPI system, makes use of the laser beam for generation of the interferograms. Moreover, this technique has the advantage of numerical focusing, and it is not necessary to place the imaging device at the image plane of the magnifying lens. Therefore, efficient autofocusing feature is designed that ensures the efficacious detection, omitting human error and declining the time-consumption. Moreover, the precision of early cancer diagnosis is enhanced through the integration of convolutional neural network (CNN) and QPI technique, which reduces the likelihood of inaccurate imaging. The non-invasive nature of proposed imaging system minimizes patient discomfort and enables real-time monitoring of disease progression. The methodology demonstrates promising results in the early detection of blood cancer and impassive the need of stained sample preparation. This research contributes to the advancement of personalized medicine and underscores the importance of leveraging quantitative phase imaging for early intervention and improved management of blood cancer.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
The achievement of a wide-ranging and versatile response from a single optical device holds significant relevance in microscopy and bio-medical imaging techniques. These imaging methods help us find the building blocks of a targeted object. However, classic optical systems require multiple components, which results in a bulky setup, making them impossible to integrate on a single chip. Luckily, metasurfaces are scientifically engineered and can manipulate light at subwavelength degrees. Therefore, they are ideal for constructing compact optical devices that seamlessly integrate onto a single chip. Current research trends have directed good attention towards broadband multifunctional meta-devices offering different applications. These metasurfaces can change waves at nano levels and show talent for various imaging and data communications tasks. However, developing multifunctional metasurfaces that can operate across a spectrum and have a single-cell construction base remains a challenge. In this study, we introduce an innovative spin-decoupled metasurface that functions across all visible spectrums to manipulate visible light and offers applications in biomedical imaging. Our designed methodology can integrate different phase profiles onto a single metasurface with the help of Fourier transformation, which gives different responses for different circularly polarized light. We numerically simulated each designed metasurface using the visible spectrum, and the obtained results indicate an excellent performance of a multifunctional metasurface. The presented approach and compact metadevices can pave the roadway for applications such as optical data transfer, edge detection microscopy, and biomedical imaging.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
This paper presents an efficient algorithm for finding the location of legs on electronic components. The proposed method has a wide range of applications, including areas such as quality manufacturing, quality control, defect detection, and more.
The research described in this article demonstrates the significant potential for automation and optimization in the context of microchip analysis processes. Automated analysis systems can eliminate the need for manual labor, leading to increased efficiency, accuracy, and consistency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.