Face recognition across illumination

Saleh Aly, Alaa Sagheer, Naoyuki Tsuruta, Rin-Ichiro Taniguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Illumination variation in face images is one of the most difficult problems in face recognition system. The performance of self-organizing map-based face recognition system is highly degraded when the illumination of test images differ from training images. Illumination normalization is a way to solve this problem. Both global and local image enhancement methods are studied in this paper. Local histogram equalization method is highly improving the recognition accuracy of the CMU-PIE face database.

Original languageEnglish
Title of host publicationProceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07
Pages802-805
Number of pages4
Publication statusPublished - Dec 1 2007
Event12th International Symposium on Artificial Life and Robotics, AROB 12th'07 - Oita, Japan
Duration: Jan 25 2007Jan 27 2007

Other

Other12th International Symposium on Artificial Life and Robotics, AROB 12th'07
CountryJapan
CityOita
Period1/25/071/27/07

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Face recognition across illumination'. Together they form a unique fingerprint.

  • Cite this

    Aly, S., Sagheer, A., Tsuruta, N., & Taniguchi, R-I. (2007). Face recognition across illumination. In Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07 (pp. 802-805)