基于决策融合的红外人脸识别方法  

Infrared Face Recognition Based on Decision Fusion

作　　者：韦礼珍[1] 伍世虔[1] 方志军[1] 李润午[1] 

机构地区：[1]江西财经大学信息管理学院,南昌330013

出　　处：《华东理工大学学报（自然科学版）》2007年第B06期63-66,105,共5页Journal of East China University of Science and Technology

基　　金：基金项目：国家自然科学基金（60665001,60662003,60462003,10626029）;江西省教育厅科技项目（2006-231）

摘　　要：提出了一种基于决策融合的红外人脸方法。分别通过离散小波变换＋主元分析＋线性辨别分析、二维PCA方法、离散小波变换＋傅里叶变换3种方法将测试图像进行分类，得到3个结果，然后将这3个结果进行融合得到最终的识别结果。实验结果表明：本文提出的方法更能利用人脸图像的有用判别信息，并得到更好的识别效果。A novel infrared face recognition method based on decision fusion was proposed. Just one method can only extract limited features of an infrared face, and some useful information related to recog-nition will be lost. So the recognition result of one method was not very accurate. This paper fused three different methods＇ results to make full use of the useful information of infrared facial image. These three methods are as follows, a new method based on PCA and LDA in wavelet domain, 2D-PCA and spectro-face. In addition, a simple but efficient decision fusion algorithm was implied and the final result was obtained. The experiments conducted illustrate that the method proposed in this paper has better perfor-mance.

关 键 词：红外图像 人脸识别 决策融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]