Prof. Eran A. Edirisinghe Profile

Prof. Eran A. Edirisinghe

at Loughborough Univ

SPIE Involvement:

Author

Publications (32)

Proceedings Article | 13 May 2015 Paper

The application of machine learning in multi sensor data fusion for activity recognition in mobile device space

Asmaa Marhoubi, Sara Saravi, Eran Edirisinghe

Proceedings Volume 9481, 94810G (2015) https://doi.org/10.1117/12.2177115

KEYWORDS: Sensors, Gyroscopes, Mobile devices, Machine learning, Data fusion, Cell phones, Denoising, Optical sensors, Environmental sensing, Analytical research

Read Abstract +

Proceedings Article | 13 May 2015 Paper

Illumination modelling of a mobile device environment for effective use in driving mobile apps

Asmaa Marhoubi, Sara Saravi, Eran Edirisinghe, Helmut Bez

Proceedings Volume 9481, 94810R (2015) https://doi.org/10.1117/12.2177087

KEYWORDS: Light sources, Mathematical modeling, Mobile devices, Modeling, Sensors, Performance modeling, Optical sensors, Environmental sensing, 3D modeling, Machine learning

Read Abstract +

Proceedings Article | 20 March 2015 Paper

Automatic diagnosis of inflammatory muscle disease for MRI using computer-extracted features of bivariate histograms

James Jack, Terence Jones, Charles Hutchinson, Helmut Bez, Eran Edirisinghe

Proceedings Volume 9414, 941402 (2015) https://doi.org/10.1117/12.2076757

KEYWORDS: Magnetic resonance imaging, Inflammation, Scanners, Tissues, Fourier transforms, Computer aided diagnosis and therapy, Computed tomography, Blood vessels, Biopsy, Blood

Read Abstract +

Proceedings Article | 13 June 2014 Paper

Military personnel recognition system using texture, colour, and SURF features

Martins Irhebhude, Eran Edirisinghe

Proceedings Volume 9090, 90900Q (2014) https://doi.org/10.1117/12.2048818

KEYWORDS: Image segmentation, Defense and security, Head, Feature selection, Pollution control, Feature extraction, Camouflage, Environmental sensing, Image retrieval, Information security

Read Abstract +

Proceedings Article | 7 March 2014 Paper

Image matching in Bayer raw domain to de-noise low-light still images, optimized for real-time implementation

I. Romanenko, E. Edirisinghe, D. Larkin

Proceedings Volume 9020, 90200Y (2014) https://doi.org/10.1117/12.2042489

KEYWORDS: Sensors, Denoising, Image processing, Optical flow, Image sensors, Data modeling, Image filtering, Image resolution, Cameras, Signal to noise ratio

Read Abstract +

Temporal accumulation of images is a well-known approach to improve signal to noise ratios of still images taken in a low light conditions. However, the complexity of known algorithms often leads to high hardware resource usage, increased memory bandwidth and computational complexity, making their practical use impossible. In our research we attempt to solve this problem with an implementation of a practical spatial-temporal de-noising algorithm, based on image accumulation. Image matching and spatial-temporal filtering was performed in Bayer RAW data space, which allowed us to benefit from predictable sensor noise characteristics, thus allowing using a range of algorithmic optimizations. The proposed algorithm accurately compensates for global and local motion and efficiently removes different kinds of noise in noisy images taken in low light conditions. In our algorithm we were able to perform global and local motion compensation in Bayer RAW data space, while preserving the resolution and effectively improving signal to noise ratios of moving objects as well as non-stationary background. The proposed algorithm is suitable for implementation in commercial grade FPGA’s and capable of processing 16MP images at capturing rate (10 frames per second). The main challenge for matching between still images is the compromise between the quality of the motion prediction and the complexity of the algorithm and required memory bandwidth. Still images taken in a burst sequence must be aligned to compensate for background motion and foreground objects movements in a scene. High resolution still images coupled with significant time between successive frames can produce large displacements between images, which creates additional difficulty for image matching algorithms. In photo applications it is very important that the noise is efficiently removed in both static, and non-static background as well as in a moving objects, maintaining the resolution of the image. In our proposed algorithm we solved the issue of matching current image with accumulated image data in Bayer RAW data space in order to efficiently perform spatio-temporal noise reduction and reduce the computational requirements. In this paper we provide subjective experimental results to demonstrate the ability of the proposed method to match noisy still images in order to perform efficient de-noising and avoid motion artefacts in resulting still images.

Proceedings Article | 5 March 2014 Paper

A novel approach to extract closed foreground object contours in video surveillance

Giounona Tzanidou, Eran Edirisinghe

Proceedings Volume 9026, 902615 (2014) https://doi.org/10.1117/12.2041311

KEYWORDS: Image segmentation, RGB color model, Video, Video surveillance, Expectation maximization algorithms, Image filtering, Anisotropic diffusion, Edge detection, Sinc filters, MATLAB

Read Abstract +

Proceedings Article | 17 February 2014 Paper

Backwards compatible high dynamic range video compression

Vladimir Dolzhenko, Vyacheslav Chesnokov, Eran Edirisinghe

Proceedings Volume 9029, 902907 (2014) https://doi.org/10.1117/12.2042513

KEYWORDS: High dynamic range imaging, Image compression, Video compression, Computer programming, Video, Image quality, Associative arrays, Image enhancement, Scalable video coding, Image quality standards

Read Abstract +

SPIE Journal Paper | 20 September 2013

Multiexposure and multifocus image fusion with multidimensional camera shake compensation

Alexis Lluis Gomez, Sara Saravi, Eran Edirisinghe

OE, Vol. 52, Issue 10, 102007, (September 2013) https://doi.org/10.1117/12.10.1117/1.OE.52.10.102007

KEYWORDS: Image fusion, Cameras, Image registration, Transform theory, Image enhancement, High dynamic range imaging, Wavelets, Image processing, Optical engineering, Image quality

Read Abstract +

Multiexposure image fusion algorithms are used for enhancing the perceptual quality of an image captured by sensors of limited dynamic range. This is achieved by rendering a single scene based on multiple images captured at different exposure times. Similarly, multifocus image fusion is used when the limited depth of focus on a selected focus setting of a camera results in parts of an image being out of focus. The solution adopted is to fuse together a number of multifocus images to create an image that is focused throughout. A single algorithm that can perform both multifocus and multiexposure image fusion is proposed. This algorithm is a new approach in which a set of unregistered multiexposure/focus images is first registered before being fused to compensate for the possible presence of camera shake. The registration of images is done via identifying matching key-points in constituent images using scale invariant feature transforms. The random sample consensus algorithm is used to identify inliers of SIFT key-points removing outliers that can cause errors in the registration process. Finally, the coherent point drift algorithm is used to register the images, preparing them to be fused in the subsequent fusion stage. For the fusion of images, a new approach based on an improved version of a wavelet-based contourlet transform is used. The experimental results and the detailed analysis presented prove that the proposed algorithm is capable of producing high-dynamic range (HDR) or multifocus images by registering and fusing a set of multiexposure or multifocus images taken in the presence of camera shake. Further, comparison of the performance of the proposed algorithm with a number of state-of-the art algorithms and commercial software packages is provided. In particular, our literature review has revealed that this is one of the first attempts where the compensation of camera shake, a very likely practical problem that can result in HDR image capture using handheld devices, has been addressed as a part of a multifocus and multiexposure image enhancement system.

SPIE Journal Paper | 29 August 2013

Human object annotation for surveillance video forensics

Muhammad Fraz, Iffat Zafar, Giounona Tzanidou, Eran Edirisinghe, Muhammad Saquib Sarfraz

JEI, Vol. 22, Issue 04, 041115, (August 2013) https://doi.org/10.1117/12.10.1117/1.JEI.22.4.041115

KEYWORDS: Video, Video surveillance, Surveillance, Forensic science, Image segmentation, RGB color model, Binary data, Cameras, Video processing, Image processing

Read Abstract +

Proceedings Article | 19 March 2013 Paper

Human object articulation for CCTV video forensics

I. Zafar, M. Fraz, Eran Edirisinghe

Proceedings Volume 8663, 86630Z (2013) https://doi.org/10.1117/12.2004956

KEYWORDS: Video, Video surveillance, RGB color model, Feature extraction, Surveillance, Data modeling, Forensic science, Cameras, Head, Image segmentation

Read Abstract +

In this paper we present a system which is focused on developing algorithms for automatic annotation/articulation of humans passing through a surveillance camera in a way useful for describing a person/criminal by a crime scene witness. Each human is articulated/annotated based on two appearance features: 1. primary colors of clothes in the head, body and legs region. 2. presence of text/logo on the clothes. The annotation occurs after a robust foreground extraction based on a modified approach to Gaussian Mixture model and detection of human from segmented foreground images. The proposed pipeline consists of a preprocessing stage where we improve color quality of images using a basic color constancy algorithm and further improve the results using a proposed post-processing method. The results show a significant improvement to the illumination of the video frames. In order to annotate color information for human clothes, we apply 3D Histogram analysis (with respect to Hue, Saturation and Value) on HSV converted image regions of human body parts along with extrema detection and thresholding to decide the dominant color of the region. In order to detect text/logo on the clothes as another feature to articulate humans, we begin with the extraction of connected components of enhanced horizontal, vertical and diagonal edges in the frames. These candidate regions are classified as text or non-text on the bases of their Local Energy based Shape Histogram (LESH) features combined with KL divergence as classification criteria. To detect humans, a novel technique has been proposed that uses a combination of Histogram of Oriented Gradients (HOG) and Contourlet transform based Local Binary Patterns (LBP) with Adaboost as classifier. Initial screening of foreground objects is performed by using HOG features. To further eliminate the false positives due to noise form background and improve results, we apply Contourlet-LBP feature extraction on the images. In the proposed method, we extract the LBP feature descriptor for Contourlet transformed high pass sub-images from vertical and diagonal directional bands. In the final stage, extracted Contourlet-LBP descriptors are applied to Adaboost for classification. The proposed frame work showed fairly fine performance when tested on a CCTV test dataset.

Proceedings Article | 19 February 2013 Paper

Spatial-temporal noise reduction method optimized for real-time implementation

I. Romanenko, E. Edirisinghe, D. Larkin

Proceedings Volume 8655, 86550L (2013) https://doi.org/10.1117/12.2001661

KEYWORDS: Sensors, Denoising, Video, Image filtering, Image processing, RGB color model, Image sensors, Data modeling, Video surveillance, Nonlinear filtering

Read Abstract +

Proceedings Article | 4 May 2012 Paper

High dynamic range video transmission and display using standard dynamic range technologies

A. Léonce, Tao-i Hsu, D. Wickramanayake, E. Edirisinghe

Proceedings Volume 8436, 84361D (2012) https://doi.org/10.1117/12.922851

KEYWORDS: High dynamic range imaging, Image enhancement, Video, Image compression, Image processing, Image filtering, Light sources and illumination, Standards development, Image quality, Sensors

Read Abstract +

Proceedings Article | 4 May 2012 Paper

Perceptual colour spaces for high dynamic range image compression

Vladimir Dolzhenko, Vyacheslav Chesnokov, Eran Edirisinghe

Proceedings Volume 8436, 843608 (2012) https://doi.org/10.1117/12.922848

KEYWORDS: High dynamic range imaging, Image compression, Computer programming, Associative arrays, JPEG2000, Image quality standards, Quantization, Image quality, Visualization, Image storage

Read Abstract +

Proceedings Article | 4 May 2012 Paper

Evaluating the effectiveness of treatment of corneal ulcers via computer-based automatic image analysis

Nesreen Otoum, Eran Edirisinghe, Harminder Dua, Lana Faraj

Proceedings Volume 8436, 84360D (2012) https://doi.org/10.1117/12.922620

KEYWORDS: Image segmentation, Cornea, Image analysis, Image processing, RGB color model, Reflection, Image quality, Image filtering, Reflectivity, Inspection

Read Abstract +

Corneal Ulcers are a common eye disease that requires prompt treatment. Recently a number of treatment approaches have been introduced that have been proven to be very effective. Unfortunately, the monitoring process of the treatment procedure remains manual and hence time consuming and prone to human errors. In this research we propose an automatic image analysis based approach to measure the size of an ulcer and its subsequent further investigation to determine the effectiveness of any treatment process followed. In Ophthalmology an ulcer area is detected for further inspection via luminous excitation of a dye. Usually in the imaging systems utilised for this purpose (i.e. a slit lamp with an appropriate dye) the ulcer area is excited to be luminous green in colour as compared to rest of the cornea which appears blue/brown. In the proposed approach we analyse the image in the HVS colour space. Initially a pre-processing stage that carries out a local histogram equalisation is used to bring back detail in any over or under exposed areas. Secondly we deal with the removal of potential reflections from the affected areas by making use of image registration of two candidate corneal images based on the detected corneal areas. Thirdly the exact corneal boundary is detected by initially registering an ellipse to the candidate corneal boundary detected via edge detection and subsequently allowing the user to modify the boundary to overlap with the boundary of the ulcer being observed. Although this step makes the approach semi automatic, it removes the impact of breakages of the corneal boundary due to occlusion, noise, image quality degradations. The ratio between the ulcer area confined within the corneal area to the corneal area is used as a measure of comparison. We demonstrate the use of the proposed tool in the analysis of the effectiveness of a treatment procedure adopted for corneal ulcers in patients by comparing the variation of corneal size over time.

Proceedings Article | 2 May 2012 Paper

Block matching noise reduction method for photographic images applied in Bayer RAW domain and optimized for real-time implementation

I. Romanenko, E. Edirisinghe, D. Larkin

Proceedings Volume 8437, 84370F (2012) https://doi.org/10.1117/12.922791

KEYWORDS: Image processing, Denoising, Sensors, Image filtering, Video, RGB color model, Signal processing, Video processing, Cameras, Optical filters

Read Abstract +

Image de-noising has been a well studied problem in the field of digital image processing. However there are a number of problems, preventing state-of-the-art algorithms finding their way to practical implementations. In our research we have solved these issues with an implementation of a practical de-noising algorithm. In order of importance: firstly we have designed a robust algorithm, tackling different kinds of nose in a very wide range of signal to noise ratios, secondly in our algorithm we tried to achieve natural looking processed images and to avoid unnatural looking artifacts, thirdly we have designed the algorithm to be suitable for implementation in commercial grade FPGA's capable of processing full HD (1920×1080) video data in real time (60 frame per second). The main challenge for the use of noise reduction algorithms in photo and video applications is the compromise between the efficiency of the algorithm (amount of PSNR improvement), loss of details, appearance of artifacts and the complexity of the algorithm (and consequentially the cost of integration). In photo and video applications it is very important that the residual noise and artifacts produced by the noise reduction algorithm should look natural and do not distract aesthetically. Our proposed algorithm does not produce artificially looking defects found in existing state-of-theart algorithms. In our research, we propose a robust and fast non-local de-noising algorithm. The algorithm is based on a Laplacian pyramid. The advantage of this approach is the ability to build noise reduction algorithms with a very large effective kernel. In our experiments effective kernel sizes as big as 127×127 pixels were used in some cases, which only required 4 scales. This size of a kernel was required to perform noise reduction for the images taken with a DSLR camera. Taking into account the achievable improvement in PSNR (on the level of the best known noise reduction techniques) and low algorithmic complexity, enabling its practical use in commercial photo, video applications, the results of our research can be very valuable.

Proceedings Article | 1 May 2012 Paper

Subjectively optimised multi-exposure and multi-focus image fusion with compensation for camera shake

A. Lluis-Gomez, S. Saravi, E. Edirisinghe

Proceedings Volume 8436, 84360Q (2012) https://doi.org/10.1117/12.922712

KEYWORDS: Image fusion, Image registration, Cameras, Wavelets, Transform theory, Image enhancement, Image quality, High dynamic range imaging, Image processing, Fusion energy

Read Abstract +

Proceedings Article | 5 May 2010 Paper

Real-time speaker identification for video conferencing

S. Saravi, I. Zafar, E. Edirisinghe, R. Kalawsky

Proceedings Volume 7724, 77240D (2010) https://doi.org/10.1117/12.854846

KEYWORDS: Laser induced plasma spectroscopy, Video, Facial recognition systems, Detection and tracking algorithms, Edge detection, Sensors, Image processing algorithms and systems, Image registration, Information visualization, Mouth

Read Abstract +

Proceedings Article | 5 May 2010 Paper

Real-time multi-barcode reader for industrial applications

Iffat Zafar, Usman Zakir, Eran Edirisinghe

Proceedings Volume 7724, 772404 (2010) https://doi.org/10.1117/12.854645

KEYWORDS: Bandpass filters, Cameras, Optical filters, LED backlight, Image filtering, Light sources and illumination, Image processing, Image segmentation, Linear filtering, Light sources

Read Abstract +

Proceedings Article | 27 March 2009 Paper

A comparative study in ultrasound breast imaging classification

Moi Hoon Yap, Eran Edirisinghe, Helmut Bez

Proceedings Volume 7259, 72591S (2009) https://doi.org/10.1117/12.811208

KEYWORDS: Tumors, Principal component analysis, Image classification, Ultrasonography, Breast imaging, Feature extraction, Shape analysis, Breast, Fractal analysis, Telecommunications

Read Abstract +

Proceedings Article | 3 February 2009 Paper

Localized contourlet features in vehicle make and model recognition

I. Zafar, E. Edirisinghe, B. Acar

Proceedings Volume 7251, 725105 (2009) https://doi.org/10.1117/12.805878

KEYWORDS: Transform theory, Detection and tracking algorithms, Feature extraction, Systems modeling, Image filtering, Feature selection, Analytical research, Performance modeling, Computing systems, Wavelets

Read Abstract +

Proceedings Article | 8 March 2007 Paper

Fully automatic lesion boundary detection in ultrasound breast images

M. Yap, E. Edirisinghe, H. Bez

Proceedings Volume 6512, 65123I (2007) https://doi.org/10.1117/12.708625

KEYWORDS: Image segmentation, Ultrasonography, Breast, Image filtering, Breast cancer, Computer aided diagnosis and therapy, Nonlinear filtering, Tumors, Diagnostics, CAD systems

Read Abstract +

Proceedings Article | 26 February 2007 Paper

A neighborhood analysis based technique for real-time error concealment in H.264 intra pictures

Steven Beesley, Christos Grecos, Eran Edirisinghe

Proceedings Volume 6507, 650706 (2007) https://doi.org/10.1117/12.704866

KEYWORDS: Error analysis, Convolution, Video, Statistical analysis, Visualization, Binary data, Mobile devices, Video coding, Computer programming, Edge detection

Read Abstract +

Proceedings Article | 20 February 2007 Paper

Two-dimensional statistical linear discriminant analysis for real-time robust vehicle-type recognition

I. Zafar, E. Edirisinghe, S. Acar, H. Bez

Proceedings Volume 6496, 649602 (2007) https://doi.org/10.1117/12.704592

KEYWORDS: Principal component analysis, Light sources and illumination, Systems modeling, Statistical analysis, Detection and tracking algorithms, Databases, Image classification, Performance modeling, Visual process modeling, Facial recognition systems

Read Abstract +

Proceedings Article | 19 January 2006 Paper

Shape adaptive integer transform for coding arbitrarily shaped objects in H.264/AVC

Xiongwen Li, Eran Edirisinghe, Helmut Bez

Proceedings Volume 6077, 60770C (2006) https://doi.org/10.1117/12.642320

KEYWORDS: Information technology, Image compression, Quantization, Image quality, Computer programming, Video coding, Visualization, Discrete wavelet transforms, Standards development, Visual compression

Read Abstract +

SPIE Journal Paper | 1 July 2005

Zerotree-based stereoscopic video CODEC

S. Thanapirom, W.A.C. Fernando, Eran Edirisinghe

OE, Vol. 44, Issue 07, 077004, (July 2005) https://doi.org/10.1117/12.10.1117/1.1951768

KEYWORDS: Video, Video coding, Image compression, Wavelets, Computer programming, Discrete wavelet transforms, Image quality, Quantization, Motion estimation, Optical engineering

Read Abstract +

Proceedings Article | 22 March 2005 Paper

An extended H.264 CODEC for stereoscopic video coding

Balamuralii Balasubramaniyam, Eran Edirisinghe, Helmut Bez

Proceedings Volume 5664, (2005) https://doi.org/10.1117/12.587583

KEYWORDS: Video, Video coding, Computer programming, Standards development, Video surveillance, Motion estimation, Video compression, Cameras, Image compression, Telecommunications

Read Abstract +

Proceedings Article | 18 January 2004 Paper

Fast wavelet transform domain texture synthesis

Dhammike Wickramanayake, Eran Edirisinghe, Helmut Bez

Proceedings Volume 5308, (2004) https://doi.org/10.1117/12.526801

KEYWORDS: Image processing, Discrete wavelet transforms, Stochastic processes, Image resolution, Error analysis, Fast wavelet transforms, Volume rendering, Visualization, Real time imaging, Wavelets

Read Abstract +

Proceedings Article | 30 May 2003 Paper

Pioneering block-based stereo image CODEC in wavelet domain

Eran Edirisinghe, M. Nayan, Helmut Bez

Proceedings Volume 5006, (2003) https://doi.org/10.1117/12.474092

KEYWORDS: Image compression, Wavelets, Discrete wavelet transforms, Image quality, Computer programming, Image transmission, Reconstruction algorithms, Transform theory, Video coding, Standards development

Read Abstract +

Proceedings Article | 7 May 2003 Paper

Rate-controlled region-of-interest-based image coding with JPEG-LS

Eran Edirisinghe, Satish Bedi

Proceedings Volume 5022, (2003) https://doi.org/10.1117/12.476372

KEYWORDS: Image compression, Image quality, Visualization, Image quality standards, Optical inspection, Digital photography, Medical imaging, Process modeling, Satellite imaging, Digital imaging

Read Abstract +

Proceedings Article | 4 January 2002 Paper

Improvements to JPEG-LS via diagonal edge-based prediction

Eran Edirisinghe, Satish Bedi, Christos Grecos

Proceedings Volume 4671, (2002) https://doi.org/10.1117/12.453103

KEYWORDS: Edge detection, Image compression, Image quality standards, Error analysis, Statistical analysis, Quantization, Photography, Computer science, Electronics engineering, Standards development

Read Abstract +

Proceedings Article | 28 December 2000 Paper

Stereo image compression approach via pixel value variation trend adaptive subspace projection

Eran Edirisinghe, Jianmin Jiang

Proceedings Volume 4207, (2000) https://doi.org/10.1117/12.411761

KEYWORDS: Image compression, Image quality, Rubidium, Mining, Computer programming, Error analysis, Image quality standards, Lamps, Video coding, Algorithms

Read Abstract +

Proceedings Article | 18 October 1999 Paper

Object-driven block-based algorithm for the compression of stereo image pairs

Eran Edirisinghe, Jianmin Jiang, Helmut Bez

Proceedings Volume 3808, (1999) https://doi.org/10.1117/12.365840

KEYWORDS: Image compression, Computer programming, Reconstruction algorithms, Image quality, Algorithm development, Visualization, Data compression, Cameras, Analytical research, Image segmentation

Read Abstract +

Showing 5 of 32 publications

Conference Committee Involvement (2)

Real-Time Image and Video Processing

7 April 2016 | Brussels, Belgium

Real-Time Image and Video Processing

17 April 2014 | Brussels, Belgium

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years