基于二元树复小波特征表示的人脸识别方法  

Face recognition based on dual-tree complex wavelet feature

作　　者：黄中美[1] 张小洪[2] 杨丹[2] 

机构地区：[1]重庆大学数理学院,重庆400030 [2]重庆大学软件学院,重庆400030

出　　处：《计算机应用》2007年第5期1135-1137,共3页journal of Computer Applications

基　　金：重庆市自然科学基金资助项目(CSTC2005BA2002)

摘　　要：二元树复小波变换(DTCWT)具备近似平移不变、多方向选择、完全重构和高效计算等优点,适合于人脸特征提取。提出了一种新的基于二元树复小波变换的人脸特征表示方法,用二维DTCWT提取了人脸图像不同尺度、位置和方向的局部特征,并用多尺度多方向的信息生成DTCWT人脸特征图。实验证明了DTCWT人脸特征表示方法提取了最具可判别性的人脸特征,获取了高识别率和泛化能力,优于其他特征表示方法。Approximate shift invariance, good directional selectivity, computational efficiency properties of Dual-tree Complex Wavelet Transform （DTCWT） make it a good candidate for representing the face features. This paper proposed a new dual-tree complex wavelet feature representation for face recognition. We got the directional and spatial/frequency characteristics of the patterns and classify different face patterns in terms of these characteristics. Experimental results show that the proposed DTCWT based feature extraction, combined with the Fisherface recognition method, （DCF） can extract optimally discriminate face feature and achieve high recognition rate and generalization. In addition, our experiments verify that the proposed feature extraction based on DTCWT outperforms which based on Gabor wavelet.

关 键 词：二元树复小波变换 GABOR小波 FISHER脸 人脸识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]