基于训练集重组的人脸识别算法研究  

Based on the Training Set of Recombinant Human Face Recognition Algorithm Research

作　　者：李春芝[1,2] 陈晓华[1,3] 

机构地区：[1]湖州师范学院信息工程学院,浙江湖州313000 [2]华东师范大学信息科学技术学院,上海200241 [3]华东师范大学软件学院,上海200062

出　　处：《电脑编程技巧与维护》2013年第2期69-71,共3页Computer Programming Skills & Maintenance

基　　金：湖州市自然科学资金(2011YZ04)

摘　　要：传统的人脸识别算法都要依赖于面部特征的严格配准来归一化人脸以便提取人脸特征,而在非限定条件系统中,传统识别算法提取特征偏差较大,且容易受姿态、表情、光照等噪声干扰。基于此,提出先对训练图像进行特征配准,再重建训练样本用于识别。实验结果表明,本方法较传统的识别算法具有较高的识别性能。The traditional algorithms for face recognition is aim on face images that are accurate alignment and have been normalized, unfortunately, face features are extracted inaccurately in non-qualification system by the traditional algorithms. And the traditional algorithms are sensitive to noise such as posture, facial expressions, lighting etc. This paper presents the training face images should be registered firstly and then used to feature extraction. Experimental results show that the method presented in this paper performs better than the traditional algorithm.

关 键 词：非负矩阵分解 二维主元分析 训练样本重建 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]