您的位置:首页  > 论文页面

一种改进的局部二值模式的人脸识别方法

发表时间:2011-04-30  浏览量:2157  下载量:958
全部作者: 梁武民,宋加涛,谢刚,谢克明,王亮
作者单位: 太原理工大学信息工程学院;宁波工程学院电子与信息工程学院
摘 要: 光照变化是当前影响人脸识别系统性能的一个重要因素。为有效克服光照变化的影响,提出一种基于改进局部二值模式算子的人脸识别方法。该方法首先采用邻域均值作为阈值对局部二值模式算子进行改进,以便更好地描述图像的局部纹理。其次,为更好地描述和反映人脸的主要部件特征,同时减少一些模式特征的冗余,采用所有发生模式99%的模式作为最终模式,在此基础上得到改进的局部二值模式图像,即局部二值模式算子(improved local binary pattern, ILBP)图像。最后采用主元分析法(principal component analysis, PCA)对人脸图像进行分类。使用AR和Yale人脸图像的实验表明:此方法能够显著地提高人脸识别率,特别是对含有光照变化的人脸图像。
关 键 词: 图像处理;人脸识别;局部二值模式;主元分析法;光照
Title: An improved local binary pattern face recognition method
Author: LIANG Wumin, SONG Jiatao, XIE Gang, XIE Keming, WANG Liang
Organization: College of Information Engineering, Taiyuan University of Technology; College of Electronic and Information Engineering, Ningbo University of Technology
Abstract: In the face recognition system, the illumination condition is a very important issue. In this paper, in order to effectively overcome the influence of the illumination change, an improved local binary pattern method is proposed. Firstly, neighborhood mean was used as a threshold to obtain better description of the local texture. Secondly, in order to better describe and reflect the large and complex parts of a face image, meanwhile reduce some redundant patterns, 99% of all occurred patterns of the LBP patterns were used as the final patterns. The original image was processed based on the final patterns, and the improved local binary pattern (ILBP) image was obtained. Finally principal component analysis (PCA) was used for classification. Experiments based on AR and Yale face database show that the ILBP image combined with PCA can significantly improve recognition accuracy and especially have strong robustness to illumination changes.
Key words: image processing; face recognition; local binary pattern; principal component analysis; illumination
发表期数: 2011年4月第8期
引用格式: 梁武民,宋加涛,谢刚,等. 一种改进的局部二值模式的人脸识别方法[J]. 中国科技论文在线精品论文,2011,4(8):705-711.
 
0 评论数 0
暂无评论
友情链接