KEYWORDS: Neodymium, Blood, Image segmentation, RGB color model, Detection and tracking algorithms, Principal component analysis, Image filtering, Visualization, Pathology, CMYK color model
This paper presents an end-to-end framework for automatically detecting and segmenting blood cells including normal red blood cells (RBCs), connected RBCs, abnormal RBCs (i.e. tear drop, burr cell, helmet, etc.) and white blood cells (WBCs). Our proposed system contains several components to solve different problems regarding RBCs and WBCs. We first design a novel blood cell color representation which is able to emphasize the RBCs and WBCs in separate channels. Template matching technique is then employed to individually detect RBCs and WBCs in our proposed representation. In order to automatically segment the RBCs and nuclei from WBCs, we develop an adaptive level set-based segmentation method which makes use of both local and global information. The detected and segmented RBCs, however, can be a single RBC, a connected RBC or an abnormal RBC. Therefore, we first separate and reconstruct RBCs from the connected RBCs by our suggested modified template matching. Shape matching by inner distance is later used to classify the abnormal RBCs from the normal RBCs. Our proposed method has been tested and evaluated on different images from ALL-IDB,10 WebPath,24 UPMC,23 Flicker datasets, and the one used by Mohamed et al.14 The precision and recall of RBCs detection are 98.43% and 94.99% respectively, whereas those of WBCs detection are 99.12% and 99.12%. The F-measure of our proposed WBCs segmentation gets up to 95.8%.
Iris masks are essential in iris recognition. The purpose of having a good iris mask is to indicate which part of iris texture map is useful and which part is occluded or contains noisy artifacts such as eyelashes, eyelids and specular reflections. The accuracy of the iris mask is extremely important. The performance of the iris recognition system will decrease dramatically when iris mask is inaccurate, even when the best recognition algorithm is used. Traditionally, people used naive rule-based algorithms to estimate iris masks from the iris texture map. But the accuracy of the iris mask generated in this way is questionable. In this paper, we propose a probabilistic and learning-based method to automatically estimate iris mask from iris texture map. The features used in this method are very simple, yet the resulting estimated iris mask is significantly more accurate than the rule-based methods. We also demonstrate the effectiveness of the algorithm by performing iris recognition based on masks estimated by different algorithms. Experimental results show the masks estimated by the proposed algorithm help to increase the iris recognition rate on NIST Iris Challenge Evaluation (ICE) database.
Facial recognition is fast becoming one of the more popular and effective modalities of biometrics when used in
controlled environments. Controlled environments are those in which factors such as facial expression, pose, camera
position, and in particular illumination effects are controlled to some degree with respect to better performance.
Regulation or normalization of such factors has effects on all facial recognition algorithms, and the factor of illumination
effects is one of significant importance. In this paper we describe a method to address illumination effects in the
biometric modality of face recognition using Empirical Mode Decomposition (EMD) to identify illumination modes that
compose the image. Following identification of intrinsic mode functions that correspond to the dominant illumination
factors, we reconstruct the facial image minus these negative factors to synthesize a more neutral facial image. We then
perform recognition and verification experiments using different algorithms such as Principal Component Analysis
(PCA), Fisher Linear Discriminant Analysis (FLDA), and Correlation Filters (CF's) to demonstrate the fundamental
effectiveness of EMD as an illumination compensation method. Results are reported on the Carnegie Mellon University
Pose-Illumination-Expression (CMU PIE) Database and the Yale Face Database B.
In this paper we demonstrate the subspace generalization power of the kernel correlation feature analysis (KCFA)
method for extracting a low dimensional subspace that has the ability to represent new unseen datasets. Examining the
portability of this algorithm across different datasets is an important practical aspect of real-world face recognition
applications where the technology cannot be dataset-dependant. In most face recognition literature, algorithms are
demonstrated on datasets by training on one portion of the dataset and testing on the remainder. Generally, the testing
subjects' dataset partially or totally overlap the training subjects' dataset however with disjoint images captured from
different sessions. Thus, some of the expected facial variations and the people's faces are modeled in the training set. In
this paper we describe how we efficiently build a compact feature subspace using kernel correlation filter analysis on the
generic training set of the FRGC dataset and use that basis for recognition on a different dataset. The KCFA feature
subspace has a total dimension that corresponds to the number of training subjects; we chose to vary this number to
include up to all of 222 available in the FRGC generic dataset. We test the built subspace produced by KCFA by
projecting other well-known face datasets upon it. We show that this feature subspace has good representation and
discrimination to unseen datasets and produces good verification and identification rates compared to other subspace and
dimensionality reduction methods such as PCA (when trained on the same FRGC generic dataset). Its efficiency, lower
dimensionality and discriminative power make it more practical and powerful than PCA as a robust lower
dimensionality reduction method for modeling faces and facial variations.
Reliable person recognition is important for secure access and commercial applications requiring human identification.
Face recognition (FR) is an important technology being developed for human identification. Algorithms and systems for
large population face recognition (LPFR) are of significant interest in applications such as watch lists and video
surveillance. In this paper, we present correlation filter-based feature analysis methods that effectively exploit available
generic training data to represent a large number of subjects and thus improve the performance for LPFR. We first
introduce a general framework - class-dependence feature analysis (CFA), which uses correlation filters to provide a
discriminant feature representation for LPFR. We then introduce two variants of the correlation filter-based CFA
methods: 1) the kernel correlation filter CFA (KCFA) that generates nonlinear decision boundaries and significantly
improves the recognition performance without greatly increasing the computational load, and 2) the binary coding CFA
that uses binary coding to reduce the number of correlation filters and applies error control coding (ECC) to improve the
recognition performance. These two variants offer ways to tradeoff between the computational complexity and the
recognition accuracy of the CFA methods. We test our proposed algorithms on the face recognition grand challenge
(FRGC) database and show that the correlation filter-based CFA approach improves the recognition rate and reduces the
computational load over the conventional correlation filters.
In this paper, we propose a novel method for performing robust super-resolution of face images by solving the practical
problems of the traditional manifold analysis. Face super-resolution is to recover a high-resolution face image from a
given low-resolution face image by modeling the face image space in view of multiple resolutions. In particular, face
super-resolution is useful to enhance face images captured from surveillance footage. Face super-resolution should be
preceded by analyzing the characteristics of the face image distribution. In literature, it has been shown that face images
lie on a nonlinear manifold by various manifold learning algorithms, so if the manifold structure is taken into
consideration for modeling the face image space, the results of face super-resolution can be improved. However, there
are some practical problems which prevent the manifold analysis from being applied to super-resolution. Almost all of
the manifold learning methods cannot generate mapping functions for new test images which are absent from a training
set. Also, there exists another significant problem when applying the manifold analysis to super-resolution; superresolution
seeks to recover a high-dimensional image from a low-dimensional one while manifold learning methods
perform the exact opposite for dimensionality reduction.
To break those limitations of applying the manifold analysis to super-resolution, we propose a novel face superresolution
method using Locality Preserving Projections (LPP). LPP gives an advantage over other manifold learning
methods in that it has well-defined linear projections which allow us to formulate well-defined mappings between highdimensional
data and low-dimensional data. Moreover, we show that LPP coefficients of an unknown high-resolution
image can be inferred from a given low-resolution image using a MAP estimator.
This paper presents a fully automatic real-time face recognition system from video by using Active Appearance Models
(AAM) for fitting and tracking facial fiducial landmarks and warping the non-frontal faces into a frontal pose. By
implementing a face detector for locating suitable initialization step of the AAM shape searching and fitting process,
new facial images are interpreted and tracked accurately in real time (15fps). Using an Active Appearance Model
(AAM) for normalizing facial images under different poses and expressions is crucial to providing improved face
recognition performance as most systems degrade matching performance with even smallest pose variation.
Furthermore the AAM is a more robust feature registration tracking approach as most systems detect and locate the eyes
while AAMs detect and track multiple fiducial points on the face holistically. We show examples of AAM fitting and
tracking and pose normalization including an illumination pre-processing step to remove specular and cast shadow
illumination artifacts on the face. We show example pose normalization images as well as example matching scores
showing the improved performance of this pose correction method.
Distortion-tolerant correlation filter methods have been applied to many video-based automatic target recognition (ATR) applications, but in a single-frame architecture. In this paper we introduce an efficient framework for combining information from multiple correlation outputs in a probabilistic way. Our framework is capable of handling scenes with an unknown number of targets at unknown positions. The main algorithm in our framework uses a probabilistic mapping of the correlation outputs and takes advantage of a position-independent target motion model in order to efficiently compute
posterior target location probabilities. An important feature of the framework is the ability to incorporate any existing correlation filter design, thus facilitating the construction of a distortion-tolerant multi-frame ATR. In our simulations, we incorporate the minimum average correlation energy Mellin radial harmonic (MACE-MRH) correlation filter design, which allows the user to specify the desired scale response of the filter. We test our algorithm on real and synthesized infrared (IR) video sequences that exhibit various degrees of target scale distortion. Our simulation results show that the multi-frame algorithm significantly improves the recognition performance of a MACE-MRH filter while requiring only a marginal increase in computation. We also show that, for an equivalent amount of added computation, using larger filter banks instead of multi-frame information is unable to provide a comparable performance increase.
The Face Recognition Grand Challenge (FRGC) dataset is one of the most challenging datasets in the face recognition community, in this dataset we focus on the hardest experiment under the harsh un-controlled conditions. In this paper we compare how other popular face recognition algorithms like Direct Linear Discriminant Analysis (D-LDA) and Gram-Schmidt LDA methods compare to traditional eigenfaces, and fisherfaces. However, we also show that all these linear subspace methods can not discriminate faces well due to large nonlinear distortions in the face images. Thus we present our proposed Class dependence Feature Analysis (CFA) method which we demonstrate to produce superior performance compared to other methods by representing nonlinear features well. We perform this by extending the traditional CFA framework to use Kernel Methods and propose a proper choice of kernel parameters which improves the overall face recognition performance is significantly over the competing face recognition algorithms. We present results of this proposed approach on a large scale database from the Face Recognition Grand Challenge (FRGC)v2 which contains over 36,000 images focusing on Experiment 4 which poses the harshest scenario containing images captured under un-controlled indoor and outdoor conditions yielding significant illumination variations.
Like many visual patterns, captured images from the same iris biometric experience relative nonlinear deformations and partial occlusions. These distortions are difficult to normalize for when comparing iris images for match evaluation. We define a probabilistic framework in which an iris image pair constitute observed variables, while parameters of relative deformation and occlusion constitute unobserved latent variables. The relation between these variables are specified in a graphical model, allowing maximum a posteriori probability (MAP) approximate inference in order to estimate the value of the hidden states. To define the generative probability of the observed iris patterns, we rely on the similarity values produced by correlation filter outputs. As a result, we are able to develop an algorithm which returns a robust match metric at the end of the estimation process and works reasonably quickly. We show recognition results on two sets of real iris images: the CASIA database, collected by the Chinese Academy of Sciences, and a database collected by the authors at Carnegie Mellon University.
In real life scenario, we may be interested in face recognition for identification purpose when we only got sketch of the face images, for example, when police tries to identify criminals based on sketches of suspect, which is drawn by artists according to description of witnesses, what they have in hand is a sketch of suspects, and many real face image acquired from video surveillance. So far the state-of-the-art approach toward this problem tries to transform all real face images into sketches and perform recognition on sketch domain. In our approach we propose the opposite which is a better approach; we propose to generate a realistic face image from the composite sketch using a Hybrid subspace method and then build an illumination tolerant correlation filter which can recognize the person under different illumination variations. We show experimental results on our approach on the CMU PIE (Pose Illumination and Expression) database on the effectiveness of our novel approach.
Correlation filters are attractive for automatic target recognition (ATR) applications due to such attributes as shift invariance, distortion tolerance and graceful degradation. Composite correlation filters are designed to handle target distortions by training on a set of images that represent the expected distortions during testing. However, if the distortion can be described algebraically, as in the case of in-plane rotation and scale, then only one training image is necessary. A recently introduced scale-tolerant correlation filter design, called the Minimum Average Correlation Energy Mellin Radial Harmonic (MACE-MRH) filter, exploits this algebraic property and allows the user to specify the scale response of the filter. These filters also minimize the average correlation energy in order to help control the sidelobes in the correlation output and produce sharper, more detectable peaks. In this paper we show that applying non-linearities in the frequency domain (leading to fractional power scale-tolerant correlation filters) can significantly improve the resulting peak sharpness, yielding larger peak-to-correlation energy values for true-class targets at various scales in a scene image. We investigate the effects of fractional power transformations on MACE-MRH filter performance by using a testbed of fifty video sequences consisting of long-wave infrared (LWIR) imagery, in which the observer moves along a flight path toward one or more ground targets of interest. Targets in the test sequences suffer large amounts of scale distortion due to the approach trajectory of the camera. MACE-MRH filter banks are trained on single targets and applied to each sequence on a frame-by-frame basis to perform target detection and recognition. Recognition results from both fractional power MACE-MRH filters and regular MACE-MRH filters are provided, showing the improvement in scale-tolerant recognition from applying fractional power non-linearities to these filters.
In the modern world, the ever-growing need to ensure a system's security has spurred the growth of the newly emerging technology of biometric identification. The present paper introduces a novel set of facial biometrics based on quantified facial asymmetry measures in the frequency domain. In particular, we show that these biometrics work well for face images showing expression variations and have the potential to do so in presence of illumination variations as well. A comparison of the recognition rates with those obtained from spatial domain asymmetry measures based on raw intensity values suggests that the frequency domain representation is more
robust to intra-personal distortions and is a novel approach for performing biometric identification. In addition, some feature analysis based on statistical methods comparing the asymmetry measures across different individuals and across different expressions is presented.
In this work we apply a computationally efficient, closed form design of a jointly optimized filter bank of correlation filter classifiers for biometric verification with the use of multiple biometrics from individuals. Advanced correlation filters have been used successfully for biometric classification, and have shown robustness in verifying faces, palmprints and fingerprints. In this study we address the issues of performing robust biometric verification when multiple biometrics from the same person are available at the moment of authentication; we implement biometric fusion by using a filter bank of correlation filter classifiers which are jointly optimized with each biometric, instead of designing separate independent correlation filter classifiers for each biometric and then fuse the resulting match scores. We present results using fingerprint and palmprint images from a data set of 40 people, showing a considerable advantage in verification performance producing a large margin of separation between the impostor and authentic match scores. The method proposed in this paper is a robust and secure method for authenticating an individual.
Human face recognition is currently a very active research area with focus on ways to perform robust biometric identification. Many face recognition algorithms have been proposed, among the different approaches, frequency domain methods, like advanced correlation filters have been shown to exhibit better tolerance to illumination variations than traditional methods. In this paper, we propose a new frequency domain face recognition method which combines the Gabor transforms and a quaternion correlation filter for face recognition when the illumination conditions are changed. The Gabor transform provides optimally localized spatial and frequency domain representation of the original face images, and the quaternion correlation filters can jointly process multi-channel subbands for more robust face recognition. The numerical experiments show that the proposed method outperforms the previously compared advanced correlation filter methods.
This paper introduces an application of steganography for hiding cancelable biometric data based on quad-phase correlation filter classification. The proposed technique can perform two tasks: (1) embed an encrypted (cancelable) template for biometric recognition into a host image or (2) embed the biometric data required for remote (or later) classification, such as embedding a transformed face image into the host image, so that it can be transmitted for remote authentication or stored for later use. The novel approach is that we will encode Fourier information of the template (or biometric) in the spatial representation of the host image. More importantly we show that we only need two bits per pixel in the frequency domain to represent the filter and biometric, making it compact and ideal for application of data hiding. To preserve the template (or biometric) from vulnerabilities to successful attacks, we encrypt the filter or biometric image by convolving it with a random kernel which produces an image in the spatial domain that resembles white noise, thus essentially both the frequency and spatial representation will have no visible exploitable structure. We also present results on reduced complexity correlation filter classification performance when using biometric images recovered from stego-images.
Face identification must address many practical challenges, including illumination variations (not seen during the testing phase), facial expressions, and pose variations. In most face recognition systems, the recognition process is performed after a face has been located and segmented in the input scene. This face detection and segmentation process however is prone to errors which can lead to partial faces being segmented (sometimes also due to occlusion) for the recognition process. There are also cases where the segmented face includes parts of the scene background as well as the face, affecting the recognition performance. In this paper, we address how these issues can be dealt efficiently with advanced correlation filter designs. We report extensive set of results on the CMU pose, illumination and expressions (PIE) dataset where training filters are designed in two experiments: (1) the training gallery has 3 images from extreme illumination (2) the training gallery has 3 images from near-frontal illumination. In the testing phase however, we test both filters with the whole illumination variations while simultaneously cropping the test images to various sizes. The results show that the advanced correlation filter designs perform very well even with partial face images of unseen illumination variations including reduced-complexity correlation filters such as the Quad-Phase Minimum Average Correlation Energy (QP-MACE) filter that requires only 2 bits/frequency storage.
In this paper we address the issue of producing cancelable biometric templates; a necessary feature in the deployment of any biometric authentication system. We propose a novel scheme that encrypts the training images used to synthesize the single (minimum average correlation energy) filter for biometric authentication. We show theoretically that convolving the training images with any random convolution kernel prior to building the filter does not change the resulting correlation output peak-to-sidelobe ratios, thus preserving the authentication performance. However, different templates can be obtained from the same biometric by varying the convolution kernels thus enabling the cancelability of the templates. We evaluate the proposed method using the illumination subset of the CMU pose, illumination, expressions (PIE) face dataset and show that we are still able to achieve 100% face verification using the proposed encryption scheme. Our proposed method is interesting from a pattern recognition theory point of view, as we are able to 'encrypt' the data and perform recognition in the encrypted domain that performs as well as the unencrypted case, for a variety of encryption kernels; we show analytically that the recognition performance remains invariant to the proposed encryption scheme, while retaining the desired shift-invariance property of correlation filters.
Biometric verification refers to the process of matching an input biometric to stored biometric information. In particular, biometric verification refers to matching the live biometric input from an individual to the stored biometric template of that individual. Examples of biometrics include face images, fingerprint images, iris images, retinal scans, etc. Thus, image processing techniques prove useful in biometric recognition. In particular, composite correlation filters have proven to be effective. In this paper, we will discuss the application of composite correlation filters to biometric verification.
Composite correlation filters (also known as synthetic discriminant function or SDF filters) are attractive for automatic target recognition (ATR) due to their built-in shift-invariance and their potential for trading off distortion tolerance for discrimination. Although the recognition performances of many advanced correlation filters are attractive, their computational complexities can be daunting particularly for ATR applications where the target detection and identification must be achieved in limited time. In this paper, we discuss some methods to reduce the complexity of correlation filter design, performing the cross-correlation as well as the processing of the resulting correlation outputs.
In Carnegie Mellon University's CyberScout project, we are developing mobile and stationary sentries capable of autonomous reconnaissance and surveillance. In this paper, we describe recent advances in the areas of efficient perception algorithms (detection, classification, and correspondence) and mission planning. In detection, we have achieved improved rejection of camera jitter and environmental variations (e.g., lighting, moving foliage) through multi-modal filtering, and we have implemented panoramic backgrounding through pseudo-real-time mosaicing. In classification, we present methods for discriminating between individual, groups of individuals, and vehicles, and between individuals with and without backpacks. In correspondence, we describe an accurate multi-hypothesis approach based on both motion and appearance. Finally, in mission planning, we describe mapbuilding using multiple sensory cues and a computationally efficient decentralized planner for multiple platforms.
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.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.