Fuzzy sparse autoencoder framework for single image per person face recognition

Yuwei Guo, Licheng Jiao, Shuang Wang, Shuo Wang, Fang Liu

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)
234 Downloads (Pure)


The issue of single sample per person (SSPP) face recognition has attracted more and more attention in recent years. Patch/local-based algorithm is one of the most popular categories to address the issue, as patch/local features are robust to face image variations. However, the global discriminative information is ignored in patch/local-based algorithm, which is crucial to recognize the nondiscriminative region of face images. To make the best of the advantage of both local information and global information, a novel two-layer local-to-global feature learning framework is proposed to address SSPP face recognition. In the first layer, the objective-oriented local features are learned by a patch-based fuzzy rough set feature selection strategy. The obtained local features are not only robust to the image variations, but also usable to preserve the discrimination ability of original patches. Global structural information is extracted from local features by a sparse autoencoder in the second layer, which reduces the negative effect of nondiscriminative regions. Besides, the proposed framework is a shallow network, which avoids the over-fitting caused by using multilayer network to address SSPP problem. The experimental results have shown that the proposed local-to-global feature learning framework can achieve superior performance than other state-of-the-art feature learning algorithms for SSPP face recognition.
Original languageEnglish
Pages (from-to)2402-2415
Number of pages14
JournalIEEE Transactions on Cybernetics
Issue number8
Early online date29 Aug 2017
Publication statusPublished - 17 Jul 2018


  • fuzzy rough set
  • one sample per person face recognition
  • sparse autoencoder
  • two-layer feature learning


Dive into the research topics of 'Fuzzy sparse autoencoder framework for single image per person face recognition'. Together they form a unique fingerprint.

Cite this