作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (22): 179-182. doi: 10.3969/j.issn.1000-3428.2012.22.044

• 人工智能及识别技术 • 上一篇    下一篇

基于DTCWT和LBP的低分辨率人脸识别

赵 敏,朱 明   

  1. (中国科学技术大学信息科学技术学院,合肥 230027)
  • 收稿日期:2011-12-23 修回日期:2012-02-29 出版日期:2012-11-20 发布日期:2012-11-17
  • 作者简介:赵 敏(1988-),女,硕士研究生,主研方向:模式识别,计算机视觉;朱 明,教授、博士生导师
  • 基金资助:
    国家自然科学基金资助项目(60975045);中国科学院战略性先导科技专项基金资助项目(XDA06030900)

Low-resolution Face Recognition Based on DTCWT and LBP

ZHAO Min, ZHU Ming   

  1. (School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China)
  • Received:2011-12-23 Revised:2012-02-29 Online:2012-11-20 Published:2012-11-17

摘要: 针对短时傅里叶变换频率分辨率较差的缺点,提出一种基于双树复小波变换(DTCWT)和局部二进制模式(LBP)直方图的低分辨率人脸识别方法。使用DTCWT获得人脸图像的多尺度多方向的频率幅度响应,采用LBP获取频率幅度响应的统计直方图,通过基于统计的一致性模式得到更加紧凑的统计分布特征。实验结果表明,该方法在低分辨率人脸上可以达到较高的识别准确率。

关键词: 人脸识别, 低分辨率, 双树复小波变换, 局部二进制模式, 特征提取, 一致性模式

Abstract: To address the frequency resolution insufficiency of Short-term Fourier Transform(STFT), a novel low-resolution face recognition method is proposed in this paper by combining Dual-tree Complex Wavelet Transform(DTCWT) and compact Local Binary Pattern(LBP) histogram. Face images are processed using DTCWT to obtain multi-scale and multi-direction frequency response, and then face features are conducted by applying LBP histogram. In addition, a statistical uniform pattern is introduced to improve the efficiency of the proposed algorithm. Experimental results show that this method has excellent recognition accuracy on low-resolution face recognition.

Key words: face recognition, low-resolution, Dual-tree Complex Wavelet Transform(DTCWT), Local Binary Pattern(LBP), feature extraction, consistency pattern

中图分类号: