Improvement of face recognition by eyeglasses removal

Yuan Kai Wang, Jia Hau Jang, Luo Wei Tsai, Kuo Chin Fan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

In this paper, we present a method based on Active Appearance Model (AAM) to remove eyeglasses from face images. The occluded regions are first roughly detected by the AAM search. Then, an ellipse model is used to fit the eyes' position. After eliminating the eye blocks, residual regions are further enhanced and extracted more precisely by the adaptive threshold method. Finally, the synthesized image is generated by iterative error compensation. Experimental results show that the proposed method provides an effective solution to the recognition of faces occluded by thick-rimmed eyeglasses.

Original languageEnglish
Title of host publicationProceedings - 2010 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010
Pages228-231
Number of pages4
DOIs
StatePublished - 2010
Event6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010 - Darmstadt, Germany
Duration: 15 Oct 201017 Oct 2010

Publication series

NameProceedings - 2010 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010

Conference

Conference6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010
Country/TerritoryGermany
CityDarmstadt
Period15/10/1017/10/10

Keywords

  • Active Appearance Models
  • Eyeglass removal
  • PCA reconstruction

Fingerprint

Dive into the research topics of 'Improvement of face recognition by eyeglasses removal'. Together they form a unique fingerprint.

Cite this