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

Fingerprint

Face recognition
Lighting
Image enhancement
Self organizing maps

All Science Journal Classification (ASJC) codes

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

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)

Face recognition across illumination. / Aly, Saleh; Sagheer, Alaa; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07. 2007. p. 802-805.

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

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, 12th International Symposium on Artificial Life and Robotics, AROB 12th'07, Oita, Japan, 1/25/07.
Aly S, Sagheer A, Tsuruta N, Taniguchi R-I. Face recognition across illumination. In Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07. 2007. p. 802-805
Aly, Saleh ; Sagheer, Alaa ; Tsuruta, Naoyuki ; Taniguchi, Rin-Ichiro. / Face recognition across illumination. Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07. 2007. pp. 802-805
@inproceedings{3499971104ae41a2b665534ee72fbbd7,
title = "Face recognition across illumination",
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.",
author = "Saleh Aly and Alaa Sagheer and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9784990288013",
pages = "802--805",
booktitle = "Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07",

}

TY - GEN

T1 - Face recognition across illumination

AU - Aly, Saleh

AU - Sagheer, Alaa

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2007/12/1

Y1 - 2007/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=78549257425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78549257425&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78549257425

SN - 9784990288013

SP - 802

EP - 805

BT - Proceedings of the 12th International Symposium on Artificial Life and Robotics, AROB 12th'07

ER -