20 April 2016 Efficient face recognition using local derivative pattern and shifted phase-encoded fringe-adjusted joint transform correlation
Author Affiliations +
Abstract
An improved shifted phase-encoded fringe-adjusted joint transform correlation technique is proposed in this paper for face recognition which can accommodate the detrimental effects of noise, illumination, and other 3D distortions such as expression and rotation variations. This technique utilizes a third order local derivative pattern operator (LDP3) followed by a shifted phase-encoded fringe-adjusted joint transform correlation (SPFJTC) operation. The local derivative pattern operator ensures better facial feature extraction in a variable environment while the SPFJTC yields robust correlation output for the desired signals. The performance of the proposed method is determined by using the Yale Face Database, Yale Face Database B, and Georgia Institute of Technology Face Database. This technique has been found to yield better face recognition rate compared to alternate JTC based techniques.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bikram Kumar Biswas, Mohammad S. Alam, Suparna Chowdhury, "Efficient face recognition using local derivative pattern and shifted phase-encoded fringe-adjusted joint transform correlation", Proc. SPIE 9845, Optical Pattern Recognition XXVII, 98450I (20 April 2016); doi: 10.1117/12.2222499; https://doi.org/10.1117/12.2222499
PROCEEDINGS
10 PAGES


SHARE
Back to Top