Performance Evaluation and Prediction for 3D Ear Recognition

• Published in: Audio- and Video-Based Biometric Person Authentication pp. 748 - 757
• Main Authors: Chen, Hui, Bhanu, Bir, Wang, Rong
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Feature Point; Iterative Close Point; Pattern recognition. Digital image processing. Computational geometry; Range Image; Shape Index; Biometrics; Performance evaluation; Human; Image processing; Filter; Image databank; Ear; Database; Binomial distribution; Characteristic curve; Modeling
• ISBN: 9783540278870; 3540278877
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11527923_78

Existing ear recognition approaches do not give theoretical or experimental performance prediction. Therefore, the discriminating power of ear biometric for human identification cannot be evaluated. This paper addresses two interrelated problems: (a) proposes an integrated local descriptor for representation to recognize human ears in 3D. Comparing local surface descriptors between a test and a model image, an initial correspondence of local surface patches is established and then filtered using simple geometric constraints. The performance of the proposed ear recognition system is evaluated on a real range image database of 52 subjects. (b) A binomial model is also presented to predict the ear recognition performance. Match and non-matched distances obtained from the database of 52 subjects are used to estimate the distributions. By modeling cumulative match characteristic (CMC) curve as a binomial distribution, the ear recognition performance can be predicted on a larger gallery.