Gender classification with jointing multiple models for occlusion images

Chiao Wen Kao, Hui Hui Chen, Bor Jiunn Hwang, Yu Ju Huang, Kuo Chin Fan

Research output: Contribution to journalArticlepeer-review


A facilitated and effective gender recognition approach is desirable for various applications such as for intelligent surveillance systems, human-computer interactions, and consumer behavior analysis. Since the human face conveys clear sexual dimorphism, the use of facial features seems an intuitive way to recognize gender. This paper proposes an efficient gender classification method using multiple classifiers to overcome the occlusion problem. The experiment is tested via 5-fold cross validation on the FERET and AR databases to evaluate the performance. The results show the proposed approach achieves higher accuracy than previous methods.

Original languageEnglish
Pages (from-to)105-123
Number of pages19
JournalJournal of Information Science and Engineering
Issue number1
StatePublished - Jan 2019


  • Component based
  • Gender classification
  • Multiple classifiers
  • Occlusion image
  • SVM


Dive into the research topics of 'Gender classification with jointing multiple models for occlusion images'. Together they form a unique fingerprint.

Cite this