Search

The use of the ocular region as a biometric cue has gained considerable traction due to recent advances in automated iris recognition. However, a multitude of factors can negatively impact ocular recognition performance under unconstrained conditions (e.g., non-uniform illumination, occlusions, motion blur, image resolution, etc.). This dissertation develops techniques to perform iris and ocular recognition under challenging conditions. The first contribution is an image-level fusion scheme to improve iris recognition performance in low-resolution videos. Information fusion is facilitated by the use of Principal Components Transform (PCT), thereby requiring modest computational efforts. The proposed approach provides improved recognition accuracy when low-resolution iris images are compared against high-resolution iris images. The second contribution is a study demonstrating the effectiveness of the ocular region in improving face recognition under plastic surgery. A score-level fusion approach that combines information from the face and ocular regions is proposed. The proposed approach, unlike other previous methods in this application, is not learning-based, and has modest computational requirements while resulting in better recognition performance. The third contribution is a study on matching ocular regions extracted from RGB face images against that of near-infrared iris images. Face and iris images are typically acquired using sensors operating in visible and near-infrared wavelengths of light, respectively. To this end, a sparse representation approach which generates a joint dictionary from corresponding pairs of face and iris images is designed. The proposed joint dictionary approach is observed to outperform classical ocular recognition techniques. In summary, the techniques presented in this dissertation can be used to improve iris and ocular recognition in practical, unconstrained environments.

In this chapter, the problem of matching face against iris images using ocular information is considered. Face and iris images are typically acquired using different sensors: face recognition is predominantly conducted in the visible (VIS) spectrum while iris recognition is performed in the near-infrared (NIR) spectrum. Further, the subject-to-camera distance for face and iris recognition is substantially different. Due to these and other factors, the problem of matching face images against iris images is riddled with several challenges. To address this, we propose a novel matching algorithm based on Joint Dictionary-based Sparse Representation (JDSR) that exploits the use of ocular information available in both face and iris images. Experimental results on a database containing 1,358 images of 704 subjects indicate that the ocular region can provide better performance than the iris region in this challenging cross-modality matching scenario.

The term periocular refers to the facial region in the immediate vicinity of the eye. Acquisition of the periocular biometric is expected to require less subject cooperation while permitting a larger depth of field compared to traditional ocular biometric traits (viz., iris, retina, and sclera). In this work, we study the feasibility of using the periocular region as a biometric trait. Global and local information are extracted from the periocular region using texture and point operators resulting in a feature set for representing and matching this region. A number of aspects are studied in this work, including the 1) effectiveness of incorporating the eyebrows, 2) use of side information (left or right) in matching, 3) manual versus automatic segmentation schemes, 4) local versus global feature extraction schemes, 5) fusion of face and periocular biometrics, 6) use of the periocular biometric in partially occluded face images, 7) effect of disguising the eyebrows, 8) effect of pose variation and occlusion, 9) effect of masking the iris and eye region, and 10) effect of template aging on matching performance. Experimental results show a rank-one recognition accuracy of 87.32% using 1136 probe and 1136 gallery periocular images taken from 568 different subjects (2 images/subject) in the Face Recognition Grand Challenge (version 2.0) database with the fusion of three different matchers.

We consider the problem of matching face against iris images using ocular information. In biometrics, face and iris images are typically acquired using sensors operating in visible (VIS) and near-infrared (NIR) spectra, respectively. This presents a challenging problem of matching images corresponding to different biometric modalities, imaging spectra, and spatial resolutions. We propose the usage of ocular traits that are common between face and iris images (viz., iris and ocular region) to perform matching. Iris matching is performed using a commercial software, while ocular regions are matched using three different techniques: Local Binary Patterns (LBP), Normalized Gradient Correlation (NGC), and Joint Dictionary-based Sparse Representation (JDSR). Experimental results on a database containing 1358 images of 704 subjects indicate that ocular region can provide better performance than iris biometric under a challenging cross-modality matching scenario.

Under ideal image acquisition conditions, the iris biometric has been observed to provide high recognition performance compared to other biometric traits. Such a performance is possible by accurately segmenting the iris region from the given ocular image. This chapter discusses the challenges associated with the segmentation process, along with some of the prominent iris segmentation techniques proposed in the literature. The methods are presented according to their suitability for segmenting iris images acquired under different wavelengths of illumination. Furthermore, methods to refine and evaluate the output of the iris segmentation routine are presented. The goal of this chapter is to provide a brief overview of the progress made in iris segmentation.

This chapter discusses the performance of five different iris segmentation algorithms on challenging periocular images. The goal is to convey some of the difficulties in localizing the iris structure in images of the eye characterized by variations in illumination, eyelid and eyelash occlusion, de-focus blur, motion blur, and low resolution. The five algorithms considered in this regard are based on the (a) integro-differential operator; (b) hough transform; (c) geodesic active contours; (d) active contours without edges ; and (e) directional ray detection method. Experiments on the Face and Ocular Challenge Series (FOCS) Database highlight the pros and cons of the individual segmentation algorithms.

The task of successfully matching face images obtained before and after plastic surgery is a challenging problem. The degree to which a face is altered depends on the type and number of plastic surgeries performed, and it is difficult to model such variations. Existing approaches use learning based methods that are either computationally expensive or rely on a set of training images. In this work, a fusion approach is proposed that combines information from the face and ocular regions to enhance recognition performance in the identification mode. The proposed approach provides the highest reported recognition performance on a publicly accessible plastic surgery database, with a rank-one accuracy of 87.4%. Compared to existing approaches, the proposed approach is not learning based and reduces computational requirements. Furthermore, a systematic study of the matching accuracies corresponding to various types of surgeries is presented.

We consider the problem of matching highly non-ideal ocular images where the iris information cannot be reliably used. Such images are characterized by non-uniform illumination, motion and de-focus blur, off-axis gaze, and non-linear deformations. To handle these variations, a single feature extraction and matching scheme is not sufficient. Therefore, we propose an information fusion framework where three distinct feature extraction and matching schemes are utilized in order to handle the significant variability in the input ocular images. The Gradient Orientation Histogram (GOH) scheme extracts the global information in the image; the modified Scale Invariant Feature Transform (SIFT) extracts local edge anomalies in the image; and a Probabilistic Deformation Model (PDM) handles nonlinear deformations observed in image pairs. The simple sum rule is used to combine the match scores generated by the three schemes. Experiments on the extremely challenging Face and Ocular Challenge Series (FOCS) database and a subset of the Face Recognition Grand Challenge (FRGC) database confirm the efficacy of the proposed approach to perform ocular recognition.

In this chapter, we describe the design and implementation of a distributed real-time face recognition system using a network of embedded cameras. We consider a scenario that simulates typical corridors and passages in airports and other indoor public spaces, where real-time human identification is of prime significance. We characterize system performance on an embedded camera network testbed which is assembled using commercial off-the-shelf components. We quantify the impact of multiple views on the accuracy of face recognition, and describe how distributed pre-processing and local filtering help in reducing both the network load, and the overall processing time.

The focus of this work is on improving the recognition performance of low-resolution iris video frames acquired under varying illumination. To facilitate this, an image-level fusion scheme with modest computational requirements is proposed. The proposed algorithm uses the evidence of multiple image frames of the same iris to extract discriminatory information via the Principal Components Transform (PCT). Experimental results on a subset of the MBGC NIR iris database demonstrate the utility of this scheme to achieve improved recognition accuracy when low-resolution probe images are compared against high-resolution gallery images.

Human recognition based on the iris biometric is severely impacted when encountering non-ideal images of the eye characterized by occluded irises, motion and spatial blur, poor contrast, and illumination artifacts. This paper discusses the use of the periocular region surrounding the iris, along with the iris texture patterns, in order to improve the overall recognition performance in such images. Periocular texture is extracted from a small, fixed region of the skin surrounding the eye. Experiments on the images extracted from the Near Infra-Red (NIR) face videos of the Multi Biometric Grand Challenge (MBGC) dataset demonstrate that valuable information is contained in the periocular region and it can be fused with the iris texture to improve the overall identification accuracy in non-ideal situations.

Performing face detection and identification in low-resolution videos (e.g., surveillance videos) is a challenging task. The task entails extracting an unknown face image from the video and comparing it against identities in the gallery database. To facilitate biometric recognition in such videos, fusion techniques may be used to consolidate the facial information of an individual, available across successive low-resolution frames. For example, super-resolution schemes can be used to improve the spatial resolution of facial objects contained in these videos (image-level fusion). However, the output of the super-resolution routine can be significantly affected by large changes in facial pose in the constituent frames. To mitigate this concern, an adaptive frame selection technique is developed in this work. The proposed technique automatically disregards frames that can cause severe artifacts in the super-resolved output, by examining the optical flow matrices pertaining to successive frames. Experimental results demonstrate an improvement in the identification performance when the proposed technique is used to automatically select the input frames necessary for super-resolution. In addition, improvements in output image quality and computation time are observed. The paper also compares image-level fusion against score-level fusion where the low-resolution frames are first spatially interpolated and the simple sum rule is used to consolidate the match scores corresponding to the interpolated frames. On comparing the two fusion methods, it is observed that score-level fusion outperforms image-level fusion.