| 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. |
