首页 | 官方网站   微博 | 高级检索  
     

基于DTCWT和LBP的低分辨率人脸识别
引用本文:赵敏,朱明.基于DTCWT和LBP的低分辨率人脸识别[J].计算机工程,2012,38(22):179-182.
作者姓名:赵敏  朱明
作者单位:中国科学技术大学信息科学技术学院,合肥,230027
基金项目:国家自然科学基金资助项目,中国科学院战略性先导科技专项基金资助项目
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
收稿时间:2011-12-23
修稿时间:2012-02-29

Low-resolution Face Recognition Based on DTCWT and LBP
ZHAO Min , ZHU Ming.Low-resolution Face Recognition Based on DTCWT and LBP[J].Computer Engineering,2012,38(22):179-182.
Authors:ZHAO Min  ZHU Ming
Affiliation:(School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China)
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.
Keywords:face recognition  low-resolution  Dual-tree Complex Wavelet Transform(DTCWT)  Local Binary Pattern(LBP)  feature extraction  consistency pattern
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程》浏览原始摘要信息
点击此处可从《计算机工程》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号