Elsevier

Procedia Computer Science

Volume 46, 2015, Pages 1518-1528
Procedia Computer Science

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

https://doi.org/10.1016/j.procs.2015.02.072Get rights and content
Under a Creative Commons license
open access

Abstract

Face 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.

Keywords

Rotation Invariance
Pose Correction
Depth Map
Spectral Transformations
and Principal Component Analysis

Cited by (0)

Peer-review under responsibility of organizing committee of the International Conference on Information and Communication Technologies (ICICT 2014).