Biometric Identification

Coherent Point Drift for Biometric Identification

Biometrics is being more and more widely used in recently year owing to the irreproducible characteristics of the human body. As one kind of biometrics, the ear has its own characters: the structure of the ear is rich and stable, and does not change radically over time; the ear is less variability with expressions, and has a more uniform distribution of color than faces. These unique characters of the ear make it possible to make up the drawbacks of other biometrics and to enrich the biometrics identification technology. At present ear recognition technology has been developed from the initial feasible research to the stage of how to enhance ear recognition performance further, for instance, 3D ear recognition, ear recognition with occlusion, and multi-pose ear recognition.

We have developed a simple and fast algorithm for ear recognition based on Principal Component Analysis that is capable to recognize ears with a low error rate. Moreover code is capable to perform 1:1 verification using an approach based on Coherent Point Drift (CPD) with a high degree of accuracy. The code for CPD has been developed by Andriy Myronenko and it is available athttp://www.bme.ogi.edu/~myron/matlab/cpd/. CPD is an excellent Matlab toolbox for rigid, affine and non-rigid point set registration and matching and allows to align two N-D point sets and recover the correspondences.

The proposed algorithm has been tested on USTB Ear Image Databases, using Dataset #1, that includes 185 ear images of 60 persons.

Index Terms: Matlab, source, code, ear, recognition, identification, matching, CPD, coherent, point, drift, PCA.