Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 2008.06a
- /
- Pages.869-870
- /
- 2008
Adaptive Smoothing Based on Bit-Plane and Entropy for Robust Face Recognition
환경에 강인한 얼굴인식을 위한 CMSB-plane과 Entropy 기반의 적응 평활화 기법
- Lee, Su-Young (School of Information and Communications Engineering Sungkyunkwan University) ;
- Park, Seok-Lai (School of Information and Communications Engineering Sungkyunkwan University) ;
- Park, Young-Kyung (School of Information and Communications Engineering Sungkyunkwan University) ;
- Kim, Joong-Kyu (School of Information and Communications Engineering Sungkyunkwan University)
- Published : 2008.06.18
Abstract
Illumination variation is the most significant factor affecting face recognition rate. In this paper, we propose adaptive smoothing based on combined most significant bit (CMSB) - plane and local entropy for robust face recognition in varying illumination. Illumination normalization is achieved based on Retinex method. The proposed method has been evaluated based on the CMU PIE database by using Principle Component Analysis (PCA).
Keywords