A Robust Novel Method for Face Recognition from 2D Depth Images Using DWT and DCT Fusion

AbstractFace recognition has been an area of interest in pattern recognition for past few decades. This paper focuses on the problems of person identification using 2D Face Depth data. The use of unregistered 2D Face depth data increases operational speed of the system with huge database enrollment. Here the unregistered 2D Face Depth data is fed to classifier in multiple spectral representations. Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) are used for the spectral representations. Fusion of scores improves the recognition accuracy. Analysis which covers the FAR (False Acceptance Rate) and TRR (True Rejection Rate) is also done