摘要
红外成像具有抗干扰性强、独立于可见光源、防伪装、防欺诈等优点,这使得红外图像人脸识别可在很大程度上弥补可见光人脸识别技术的缺陷和不足,是今后人脸识别研究的一个重要方向。在深入分析红外人脸图像特性的基础上,研究了红外图像人脸识别的特点,并提出了一种新的红外图像统计人脸识别方法。实验结果表明,这种识别方法不论从理论上还是从实验上都是可行的,具有良好的识别能力。
Infrared image has a lot of advantages, such as strong anti-interference, independence to visible light source, defendence from camouflage and defendence against cheat. These advantages help infrared image face recognifion to a large extent to make up for the shortage of visible image face recognifion. Now infrared image face recognition is an important direction in the field of face recognition. Based on the analysis of characteristics of infrared image, the properties of infrared image face recognition ware analyzed and a new infrared image statistical face recognition method was proposed in this paper. Experimental results show that the recognition method is workable and has good partition capability.
出处
《国防科技大学学报》
EI
CAS
CSCD
北大核心
2006年第2期73-76,共4页
Journal of National University of Defense Technology
基金
国家863高技术资助项目(2001AA144170)
关键词
红外图像
人脸识别
统计分析
线性辨别分析
infrared image
face recognition
statistical analysis
Linear discriminant analysis
