We propose three biometric systems for performing 1) Multi-modal Three-Dimensional (3D) ear + Two-Dimensional (2D) face recognition, 2) 3D face recognition, and 3) hybrid 3D ear recognition combining local and holistic features. For the 3D ear component of the multi-modal system, uncalibrated video sequences are utilized to recover the 3D ear structure of each subject within a database. For a given subject, a series of frames is extracted from a video sequence and the Region-of-Interest (ROI) in each frame is independently reconstructed in 3D using Shape from Shading (SFS). A fidelity measure is then employed to determine the model that most accurately represents the 3D structure of the subject’s ear. Shape matching between a probe and gallery ear model is performed using the Iterative Closest Point (ICP) algorithm. For the 2D face component, a set of facial landmarks is extracted from frontal facial images using the Active Shape Model (ASM) technique. Then, the responses of the facial images to a series of Gabor filters at the locations of the facial landmarks are calculated. The Gabor features are stored in the database as the face model for recognition. Match-score level fusion is employed to combine the match scores obtained from both the ear and face modalities. The aim of the proposed system is to demonstrate the superior performance that can be achieved by combining the 3D ear and 2D face modalities over either modality employed independently. For the 3D face recognition system, we employ an Adaboost algorithm to builda classifier based on geodesic distance features. Firstly, a generic face model is finely conformed to each face model contained within a 3D face dataset. Secondly, the geodesic distance between anatomical point pairs are computed across each conformed generic model using the Fast Marching Method. The Adaboost algorithm then generates a strong classifier based on a collection of geodesic distances that are most discriminative for face recognition. The identification and verification performances of three Adaboost algorithms, namely, the original Adaboost algorithm proposed by Freund and Schapire, and two variants – the Gentle and Modest Adaboost algorithms – are compared. For the hybrid 3D ear recognition system, we propose a method to combine local and holistic ear surface features in a computationally efficient manner. The system is comprised of four primary components, namely, 1) ear image segmentation, 2) local feature extraction and matching, 3) holistic feature extraction and matching, and 4) a fusion framework combining local and holistic features at the match score level. For the segmentation component, we employ our method proposed in [111], to localize a rectangular region containing the ear. For the local feature extraction and representation component, we extend the Histogram of Categorized Shapes (HCS) feature descriptor, proposed in [111], to an object-centered 3D shape descriptor, termed Surface Patch Histogram of Indexed Shapes (SPHIS), for surface patch representation and matching. For the holistic matching component, we introduce a voxelization scheme for holistic ear representation from which an efficient, element-wise comparison of gallery-probe model pairs can be made. The match scores obtained from both the local and holistic matching components are fused to generate the final match scores. Experimental results conducted on the University of Notre Dame (UND) collection J2 dataset demonstrate that theproposed approach outperforms state-of-the-art 3D ear biometric systems in both accuracy and efficiency.

A number of researchers have shown that ear recognition is a viable alternative to more common biometrics such as fingerprint, face and iris because the ear is relatively stable over time, the ear is non-invasive to capture, the ear is expressionless, and both the ear’s geometry and shape have significant variation among individuals. Researchers have used different approaches to enhance ear recognition. Some researchers have improved upon existing algorithms, some have developed algorithms from scratch to assist with recognizing individuals by ears, and some researchers have taken algorithms tried and tested for another purpose, i.e., face recognition, and applied them to ear recognition. These approaches have resulted in a number of state-of-the-art effective methods to identify individuals by ears. However, most ear recognition research has been done using ear images that were captured in an ideal setting: ear images have near perfect lighting for image quality, ears are in the same position for each subject, and ears are without earrings, hair occlusions, or anything else that could block viewing of the entire ear. In order for ear recognition to be practical, current approaches must be improved. Ear recognition must move beyond ideal settings and demonstrate effectiveness in an unconstrained environment reflective of real world conditions. Ear recognition approaches must be scalable to handle large groups of people. And, ear recognition should demonstrate effectiveness across a diverse population. This dissertation advances ear recognition from ideal settings to real world settings. We devised an ear recognition framework that outperformed state-of-the-art recognition approaches using the most challenging sets of publicly available ear images and the most voluminous set of unconstrained ear images that we are aware of. We developed a Convolutional Neural Network-based solution for ear normalization and description, we designed a two-stage landmark detector, and we fused learned and handcrafted descriptors. Using our framework, we identified some individuals that are wearing earrings and that have other occlusions, such as hair. The results suggest that our framework can be a gateway for identification of individuals in real world conditions.

Reducing the dimensionality of the original pattern space in a definition of feature space while maintaining discriminatory power for classification is a general goal in pattern recognition. To accomplish this goal in the area of ear biometrics a highly recognized work was proposed by D. Hurley in 2D space. We were inspired by his work and developed a new method for 3D data. In a different way to Hurley’s work we obtain a potential energy surface from 3D depth image which underlies the force field and associated vector field has its own characteristics. Our feature extraction is conducted by combining two different approaches; an algorithmic approach as well as an analytical approach, both are based on the vector force field and geometrical approach which is based on 3D ear surface. To validate the technique, the ICP algorithm is used. This work differs from Hurley’s work not only because of the algorithm, but also because of the nature of the 3D data which delivers topological information of the images. We exploit geometry to acquire surface information of the ear which yields richer features than the original work. The performance of the proposed method was evaluated using the University of Notre Dame (UND) collection J2 database and MATLAB has been used as the software package. / phone number: 0700099273

Biometrics includes the study of automatic methods for distinguishing human beings based on physical or behavioral traits. The problem of finding good biometric features and recognition methods has been researched extensively in recent years. Our research considers the use of ears as a biometric for human recognition. Researchers have not considered this biometric as much as others, which include fingerprints, irises, and faces. This thesis presents a novel approach to recognize individuals based on their outer ear images through spatial segmentation. This approach to recognizing is also good for dealing with occlusions. The study will present several feature extraction techniques based on spatial segmentation of the ear image. The study will also present a method for classifier fusion. Principal components analysis (PCA) is used in this research for feature extraction and dimensionality reduction. For classification, nearest neighbor classifiers are used. The research also investigates the use of ear images as a supplement to face images in a multimodal biometric system. Our base eigen-ear experiment results in an 84% rank one recognition rate, and the segmentation method yielded improvements up to 94%. Face recognition by itself, using the same approach, gave a 63% rank one recognition rate, but when complimented with ear images in a multimodal system improved to 94% rank one recognition rate. / Master of Science