Illumination-robust face recognition with Block-based Local Contrast Patterns
Yichuan Wang, Zhen Xu, Weifeng Li, Qingmin Liao
Abstract
This paper proposes a novel facial image representation Block-based Local Contrast Patterns (BLCP) for illumination-robust face recognition. This method is based on an effective texture descriptor local contrast patterns (LCP). We use the directed and undirected difference masks to calculate three types of local intensity contrasts: directed, undirected, and maximum difference responses. These response images are divided into several nonoverlapping blocks. In each block these responses are quantized and encoded into specific patterns. A joint histogram of these patterns is computed for each block and then we concatenate all the blocks' histograms into an enhanced feature vector to be used as a face descriptor. The experimental results on Extended Yale-B and FERET databases illustrate the effectiveness of our proposed method in illumination-robust face recognition.
BibTeX
@inproceedings{icassp2017_illuminationrobu,
title = {Illumination-robust face recognition with Block-based Local Contrast Patterns},
author = {Yichuan Wang and Zhen Xu and Weifeng Li and Qingmin Liao},
booktitle = {ICASSP 2017},
year = {2017}
}