基于虚拟样本扩张法的单样本人脸识别算法研究

Virtual Sample Generating for Face Recognition from a Single Training Sample per Person

随着人脸识别技术的不断发展,单样本人脸识别已成为当今的一个热点。针对单样本人脸识别问题,提出了一种基于虚拟样本扩展的人脸识别方法,为给定的单训练样本增加虚拟图像,以增强单训练样本的分类信息,并对原样本及其虚拟样本进行特征变换,划分得到更多的子图像,利用二维主成分分析(2DPCA)实现特征抽取,一定程度上减轻了人脸的表情、姿态、光照等因素对识别效果的影响,提高了识别率。提出的方法分别在ORL及FERET两大人脸数据库上得到了验证。

Usually, that are assumed there are muhiple samples per person for feature extraction in many facerecognition methods. In many practical face recognition applications such as law enhancement, e-passport, and ID card identification, however, this assumption may not hold as there is only a single sample per person. To address this problem, a novel method is proposed that generating multiple samples with sample give by using virtual sample generating method so as to adding classes of each face, partitioning them into multiple sub-patches, using 2DPCA method to complete feature extraction. Experiment results on two widely used face databases are presented to dem- onstrate the efficacy of the proposed approach.