基于SIFT算法的多表情人脸识别

目前人脸识别系统在识别表情变化的人脸图像时识别准确率会降低,多表情人脸识别在人脸识别领域仍是一个热门的研究方向。本文采用SIFT算法对多表情人脸进行识别,在多表情人脸库上进行了两类仿真实验:实验一中对比了同一个人的不同表情的识别效果,实验二中对比了两个不同的人的相同表情的识别效果,实验结果表明SIFT算法能够克服不同人脸间的整体相似性并能有效提取出人脸的局部细节特征。对Jaffe表情库进行仿真实验,取得了当阈值T=0.35时对多表情人脸图像的正确识别率95.69%,实验结果表明,将SIFT算法应用于多表情人脸识别有巨大的潜在科研价值。

Recognition of expression-variant faces based on SIFT method

Prior research has shown that the performance of face recognition systems in variant expression condition degrades seriously compared with invariant expression condition. Face recognition with variant expression is a challenging problem. In this paper, SIFT method is proposed to research on face recognition with variant expression. Two experiments using SIFT method are performed on a variant expression face database. In experiment 1, two images of one person with different expression are compared. In experiment 2, two images of different persons with the same expression are compared. Experimental results show that SIFT method could overcome the whole comparability of different faces and extract the local detail features of face. Recognizing the variant expression face images in Jaffe library, we get the right recognition rate of 95.59% when threshold equals 0.35, the experiment demonstrates the huge potential of SIFT method in application to face recognition with variant expression.