Contourlet and fourier transform features based 3D face recognition system

Abstract

Human face recognition based on geometrical structure has been an area of interest among researchers for the past few decades especially in pattern recognition. 3D Face recognition systems are of interest in this context. The main advantage of 3D Face recognition is the availability of geometrical information of the face structure which is more or less unique for a subject. This paper focuses on the problems of person identification using 3D Face data. Use of unregistered 3D Face data for feature extraction significantly increases the operational speed of the system with huge database enrollment. In this work, unregistered Face data, i.e. both texture and depth is fed to a classifier in spectral representations of the same data. 2-D Discrete Contourlet Transform and 2-D Discrete Fourier Transform is used here for the spectral representation which forms the feature matrix. Fusion of texture and depth statistical information of face is proposed in this paper since the individual schemes are of lower performance. Application of statistical method seems to degrade the performance of the system when applied to texture data and was effective in the case of depth data. Fusion of the matching scores proves that the recognition accuracy can be improved significantly by fusion of scores of multiple representations. FRAV3D database is used for testing the algorithm.