Abstract: Recently the method of sparse representation based on prototype plus variation model is applied in face recognition effectively. This algorithm only considers about the holistic face, but ignores the effect of local feature in the entire process. To solve this problem, this paper adds the idea of block processing. The Borda count method is used to assign different votes to various classes of the sub-modular. Then it classifies the faces according to the final votes. The experimental results on AR datasets validate that this method performs better than other methods when the faces are partially obscured or under different light conditions.

Key words: face recognition, sparse representation, Borda count, sub-modular

摘要： 最近基于原型（Prototype）加变差（Variation）表示模型的稀疏表示方法被有效用于人脸识别。由于该算法是基于整个人脸来考虑的，忽略了人脸局部特征对整个识别过程的影响。为了解决这个问题，引入了分块处理的思想，运用Borda计数的方法对每个子模块按照残差大小进行投票，根据最终的投票结果对人脸进行分类判别。在AR人脸库上的实验结果表明该方法与其他方法相比，在对具有部分遮挡和光照变化人脸的识别上具有更好的效果。

关键词: 人脸识别, 稀疏表示, Borda投票, 子模块