计算机应用 ›› 2012, Vol. 32 ›› Issue (08): 2316-2319.DOI: 10.3724/SP.J.1087.2012.02316

• 图形图像技术 • 上一篇    下一篇

基于多级纹理频谱特征与PCA的人脸识别算法

党鑫鹏,刘文萍   

  1. 北京林业大学 信息学院,北京 100083
  • 收稿日期:2012-01-13 修回日期:2012-03-05 发布日期:2012-08-28 出版日期:2012-08-01
  • 通讯作者: 刘文萍
  • 作者简介:党鑫鹏(1989-),男,山西临汾人,硕士研究生,主要研究方向:人脸识别、数字图像处理;
    刘文萍(1971-),女,河北清苑人,副教授,博士,主要研究方向:数字图像处理、视频分析与检索、模式识别、人工智能。
  • 基金资助:
    中央高校基本科研业务专项资金资助项目(YX2011-28);国家973计划项目(2009CB421105)

Face recognition algorithm based on multi-level texture spectrum features and PCA

DANG Xin-peng,LIU Wen-ping   

  1. College of Information, Beijing Forestry University, Beijing 100083, China
  • Received:2012-01-13 Revised:2012-03-05 Online:2012-08-28 Published:2012-08-01
  • Contact: LIU Wen-ping

摘要: 针对主成分分析(PCA)算法在人脸识别中识别率低的问题,提出一种图像纹理频谱特征与PCA相结合的人脸识别算法。该算法利用纹理单元算子提取人脸图像纹理频谱特征,然后用PCA对所提取的特征降维,最后利用最近邻(KNN)分类器进行人脸识别。在ORL人脸库和Yale人脸库上对所提出的算法进行了测试,识别率均高于PCA、模块化二维PCA(M2DPCA)等方法,分别为96.5%和95%。实验结果表明了该算法的有效性和准确性。

关键词: 人脸识别, 图像纹理频谱, 纹理单元, 主成分分析, K最近邻分类器

Abstract: To improve the recognition rate of Principal Component Analysis (PCA) algorithm in face recognition, a new algorithm combining the image texture spectrum feature with PCA was proposed. Firstly, the texture unit operator was used to extract the texture spectrum feature of the face image. Secondly, PCA approach was used to reduce the dimensions of the texture spectrum feature. Finally, K-Nearest Neighbor (KNN) classification was chosen to recognize the face. ORL and Yale face database were used to test the proposed algorithm, and the recognition accuracies were 96.5% and 95% respectively, which were higher than those of PCA and Modular Two-Dimensional PCA (M2DPCA). The experimental results demonstrate the efficiency and accuracy of the proposed algorithm.

Key words: face recognition, image texture spectrum, texture unit, Principal Component Analysis (PCA), K-Nearest Neighbor (KNN) classification

中图分类号: