Infrared Face Recognition Based on Local Binary Pattern and Multi-objective Genetic Algorithm
To extract the discrimination local structural features,an improved infrared face recognition method based on LBP is proposed in this paper.To get robust local features in infrared face,local binary pattern representation is applied to our method,instead of holistic feature extraction method. The main drawback of LBP patterns representation is that the dimension of LBP pattern features is relatively high.Feature selection algorithm based on multi-objective genetic algorithm (MOGA)is proposed to analyze and discard patterns that are not relevant to the recognition task.The experimental results demonstrate the infrared face recognition method based on LBP+MOGA proposed outperforms the traditional methods based on LBP or PCA+LDA.
Tu Wei Xie Zhihua
Key Lab of Optic-Electronic and Communication Jiangxi Sciences and Technology Normal University Nanchang,Jiangxi,China
国际会议
深圳
英文
359-362
2011-06-06（万方平台首次上网日期，不代表论文的发表时间）