4.6 Article

Fast single sample face recognition based on sparse representation classification

期刊

MULTIMEDIA TOOLS AND APPLICATIONS
卷 80, 期 3, 页码 3251-3273

出版社

SPRINGER
DOI: 10.1007/s11042-020-09855-w

关键词

Single sample face recognition; ESRC; Positive sparse coefficient based ESRC; Large positive sparse coefficient based ESRC

资金

  1. National Natural Science Foundation of China [61802203]
  2. Natural Science Foundation of Jiangsu Province [BK20180761]
  3. China Postdoctoral Science Foundation Funded Project [2019 M651653]
  4. Jiangsu Planned Projects for Postdoctoral Research Funds [2019 K124]
  5. Nanjing University of Posts and Telecommunications Science Foundation [NY218119]

向作者/读者索取更多资源

The paper introduces a fast extended sparse representation classification method that significantly improves the computation efficiency of ESRC through strategies based on positive sparse coefficients and large positive sparse coefficients. Experimental results demonstrate the high utility and feasibility of this method in face recognition systems.
The extended sparse representation classification (ESRC) is one of the benchmark classification algorithms in the field of single sample face recognition (SSFR). However, when there are many single training samples, the execution time of ESRC cannot be acceptable in real face recognition systems. We assume the similarity principle of sparse representation under valid SSFR as that, if the test image is more similar to certain single training sample, the corresponding sparse coefficient of this single training sample may be larger, and the representation residual of this single training sample may be smaller. Based on this assumption, we propose the fast ESRC method to tackle many single training samples problem. Firstly, we propose the positive sparse coefficient based ESRC (PESRC) that selects to compute representation residuals of single training samples whose sparse coefficients of ESRC are positive. Then, we propose the statistical analysis of the sparse coefficient ratio, which is used to develop the large positive sparse coefficient based ESRC (LESRC) that calculates representation residuals of the single training samples corresponding to large positive sparse coefficients of PESRC. Finally, the experiment results on Extended Yale B, AR, CMU PIE and VGGFace2 face databases indicate that the proposed PESRC and LESRC can significantly improve the computation efficiency of ESRC. On our platform, the execution time of recognizing only one test image for ESRC or VGG + ESRC is over 130 s (the execution time of ESRC and VGG + ESRC are 562.71 s and 135.02 s) under 9125 single training samples, whereas the execution times of PESRC, LESRC, VGG + PESRC, and VGG + LESRC are 2.20s, 0.23 s, 0.71 s, and 0.03 s respectively.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据