基于DWT和模块2DPCA的红外人脸识别方法  

Infrared Face Recognition Based on DWT and Modular 2DPCA

作　　者：伍世虔[1] 梁伟[1] 韦礼珍[1] 方志军[1] 

机构地区：[1]江西财经大学信息管理学院,江西南昌330013

出　　处：《广西师范大学学报（自然科学版）》2008年第3期218-221,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(60665001;60462003);江西省自然科学基金资助项目(0611025)

摘　　要：提出一种结合图像离散小波变换和模块2DPCA的方法。首先通过DWT将红外人脸图像通过小波一级分解成4个子带,用模块2DPCA的方法对4个子带进行特征提取,得到4个子带的特征向量,然后对每个子带进行分类,将所得4个识别结果进行决策融合,得到最终的识别结果。同基于PCA和模块2DPCA方法相比,所提出的方法能很好利用人脸图像的有用判别信息,并得到更好的识别效果。An efficient method for infrared face recognition by combining DWT and PCA techniques is proposed. Each infrared face image is first decomposed into four sub-images by using DWT, based on which the PCA technique is employed to extract the features. The initial recognition is performed on the sub-band features and the final result is determined by fusing the initial recognition. The experiments conducted illustrate that the method proposed in this paper has better performance.

关 键 词：离散小波变换 模块二维主元分析 红外人脸识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]