计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (11): 145-149.

• 图形图像处理 • 上一篇    下一篇

基于光照归一化分块完备LBP特征的人脸识别

周  巍1,程  勇2,曹雪虹1,2   

  1. 1.南京邮电大学 通信与信息工程学院,南京 210003
    2.南京工程学院 通信工程学院,南京 211167
  • 出版日期:2015-06-01 发布日期:2015-06-12

Face recognition based on illumination normalization and block-based completed local binary pattern

ZHOU Wei1, CHENG Yong2, CAO Xuehong1,2   

  1. 1.College of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
    2.School of Communication Engineering, Nanjing Institute of Technology, Nanjing 211167, China
  • Online:2015-06-01 Published:2015-06-12

摘要: 针对复杂光照条件下的人脸识别,提出了一种基于光照归一化分块完备局部二值模式(B-CLBP)特征的人脸识别算法。该方法对人脸图像进行光照归一化预处理,对处理后的人脸图像进行B-CLBP特征提取,融合成B-CLBP直方图,根据最近邻准则进行分类识别。在Extended Yale B人脸库上的实验结果表明,所提算法可以有效提高复杂光照条件下的人脸识别率。

关键词: 人脸识别, 光照归一化, 分块完备局部二值模式

Abstract: Aiming at the problem of face recognition under complex illumination, an effective face recognition method based on illumination normalization and block-based completed local binary pattern is proposed. The method performs illumination normalization on face images, then extracts the B-CLBP features from the processed face images in order to form the B-CLBP histogram, applies the nearest neighbor principle for face recognition. The experimental results on Extended Yale B face databases demonstrate that the proposed method can achieve significant recognition rate under complex illumination conditions.

Key words: face recognition, illumination normalization, Block-based Completed Local Binary Pattern(B-CLBP)