Publication Date

2017-03-01

Availability

Embargoed

Embargo Period

2018-03-01

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PHD)

Department

Industrial Engineering (Engineering)

Date of Defense

2016-11-30

First Committee Member

Shihab S. Asfour

Second Committee Member

Mohamed Abdel-Mottaleb

Third Committee Member

Francesco Travascio

Fourth Committee Member

Mohamed Fahmy

Fifth Committee Member

Moataz Eltoukhy

Abstract

In the current era of Digital Information Technology, Biometrics authentication is massively used to protect user's privacy by confirming the legitimacy of their identity. Biometric identifiers are the distinctive, measurable characteristics used to label and describe individuals. Technology to verify a person’s identity based on his/her biometrics utilizes the information "someone who they are" instead of "something they know" (passwords) or "something they possess"(ID card). Biometric identifiers are usually categorized as physiological and behavioral characteristics. Physiological characteristics are related to the shape of the body. Examples include, but are not limited to face recognition, ear shape, fingerprint, DNA, palm print, hand geometry, iris recognition, and retina. Behavioral characteristics refer to the pattern of behavior of a person, including but not limited to typing rhythm, gait, and voice. Application of Biometrics authentication can be found in various domains, starting from forensics research, border security maintenance to securely access Bank ATMs and the web or mobile applications. Current growth trends in different biometrics applications present challenges to researchers. To address these challenges, we need new data storage and retrieval techniques to make the recognition process time efficient. We proposed a system for time efficient 3D ear biometrics from a large biometrics database. The proposed system has two components that are primarily responsible for: 1) automatic 3D ear segmentation and 2) hierarchical categorization of the 3D ear database using shape information and surface depth information, respectively. We use an active contour algorithm along with a tree structured graph to segment the ear region from the 3D profile images. The segmented 3D ear database is then categorized based on geometrical feature values, computed from the ear shape, into oval, round, rectangular and triangular categories. For the categorization based on the depth information, the feature space is partitioned using tree-based indexing techniques. We used indexing techniques with balanced split (KD tree) and unbalanced split (Pyramid tree) data structures to categorize the database separately, then compared their retrieval efficiency. Experiments are conducted to compare the average computation time per query when performing recognition through hierarchical categorization with the average computation time when recognition is based on sequential search. Experimental results conducted on the University of Notre Dame (UND) collection J2 dataset demonstrate that the proposed approach outperforms state-of-the-art 3D ear biometric systems in both accuracy and efficiency, explicitly the hierarchical clustering of the biometrics dataset result in 5 times faster search/ query compared with the state-of-the-art technique that uses sequential search. Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. We proposed a novel multimodal recognition system that trains a Deep Learning Network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising autoencoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. The proposed system has three components that are responsible for: 1) Automatically detecting images of different modalities present in the facial video clips; 2) Training supervised denoising sparse autoencoders to capture the modality specific discriminative representation while maintaining robustness to the variations; and 3) Train modality specific Sparse classifier (SRC), then perform score level fusion of the recognition results of all five modalities, or all the available modalities from the query video to obtain the multimodal recognition result. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips. Biometric identification using Surveillance Video has attracted the attention of many researchers as it can be applicable not only for robust identification but also personalized activity monitoring. We present a novel multimodal recognition system that extracts Frontal Gait and Low Resolution face images from frontal walking surveillance video clips to perform efficient biometric recognition. The proposed study addresses two important issues in surveillance video that did not receive appropriate attention in the past. First, it consolidates the Model-Free and Model-Based Gait feature extraction approaches to perform robust gait recognition only using the frontal view. Second, it uses a low-resolution face recognition approach which can be trained and tested using low-resolution face information. This eliminates the need for obtaining high-resolution face images to create the gallery, which is required in the majority of low-resolution face recognition techniques. Previous studies on frontal gait recognition incorporate assumptions to approximate the average gait cycle. However, we quantify the gait cycle precisely for each subject using only the frontal gait information. The approaches available in the literature use the high resolution images obtained in a controlled environment to train the recognition system. However, in our proposed system we train the recognition algorithm using the low resolution face images captured in the unconstrained environment. The proposed system has two components, one is responsible for performing Frontal Gait recognition and one is responsible for Low Resolution face recognition. Later, score level fusion is performed to fuse the results of the Frontal Gait recognition and the Low Resolution Face recognition. Experiments conducted on the Face and Ocular Challenge Series (FOCS) dataset resulted in a 93.5% Rank-1 for Frontal Gait recognition and 82.92% Rank-1 for Low Resolution face recognition, respectively. The score level multimodal fusion resulted in 95.9% Rank-1 recognition, which demonstrates the superiority and robustness of the proposed approach.

Keywords

3D Ear Biometrics; 3D Ear Segmentation; Multimodal Biometrics; Deep Learning; Low Resolution Face Recognition; Super Resolution.

Available for download on Thursday, March 01, 2018

Share

COinS