The effect of lighting direction/condition on the performance of face recognition algorithms

Gamal Fahmy, Ahmed El-Sherbeeny, Susmita Mandala, Mohamed Abdel-Mottaleb, Hany Ammar

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

7 Citations (Scopus)

Abstract

In this paper, we measure the effect of the lighting direction in facial images on the performance of 2 well-known face recognition algorithms, an appearance based method and a facial feature based method. We collect hundreds/thousands of facial images of subjects with a fixed pose and under different lighting conditions through a unique facial acquisition laboratory designed specifically for this purpose. Then we present a methodology for automatically detecting the lighting direction of different face images based on statistics derived from the image. We also detect if there is any glare regions in some lighting directions. Finally we determine the most reliable lighting direction that will lead to a good quality/high performance facial image from both techniques based on our experiments with the acquired data.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6202
DOIs
StatePublished - Aug 29 2006
EventBiometric Technology for Human Identification III - Kissimmee, FL, United States
Duration: Apr 17 2006Apr 18 2006

Other

OtherBiometric Technology for Human Identification III
CountryUnited States
CityKissimmee, FL
Period4/17/064/18/06

Fingerprint

Face recognition
illuminating
Lighting
glare
Glare
acquisition
Statistics
statistics
methodology
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Fahmy, G., El-Sherbeeny, A., Mandala, S., Abdel-Mottaleb, M., & Ammar, H. (2006). The effect of lighting direction/condition on the performance of face recognition algorithms. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6202). [62020J] https://doi.org/10.1117/12.666527

The effect of lighting direction/condition on the performance of face recognition algorithms. / Fahmy, Gamal; El-Sherbeeny, Ahmed; Mandala, Susmita; Abdel-Mottaleb, Mohamed; Ammar, Hany.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6202 2006. 62020J.

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

Fahmy, G, El-Sherbeeny, A, Mandala, S, Abdel-Mottaleb, M & Ammar, H 2006, The effect of lighting direction/condition on the performance of face recognition algorithms. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6202, 62020J, Biometric Technology for Human Identification III, Kissimmee, FL, United States, 4/17/06. https://doi.org/10.1117/12.666527
Fahmy G, El-Sherbeeny A, Mandala S, Abdel-Mottaleb M, Ammar H. The effect of lighting direction/condition on the performance of face recognition algorithms. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6202. 2006. 62020J https://doi.org/10.1117/12.666527
Fahmy, Gamal ; El-Sherbeeny, Ahmed ; Mandala, Susmita ; Abdel-Mottaleb, Mohamed ; Ammar, Hany. / The effect of lighting direction/condition on the performance of face recognition algorithms. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6202 2006.
@inproceedings{a39f40107f5a472d88c7f38b983b5ceb,
title = "The effect of lighting direction/condition on the performance of face recognition algorithms",
abstract = "In this paper, we measure the effect of the lighting direction in facial images on the performance of 2 well-known face recognition algorithms, an appearance based method and a facial feature based method. We collect hundreds/thousands of facial images of subjects with a fixed pose and under different lighting conditions through a unique facial acquisition laboratory designed specifically for this purpose. Then we present a methodology for automatically detecting the lighting direction of different face images based on statistics derived from the image. We also detect if there is any glare regions in some lighting directions. Finally we determine the most reliable lighting direction that will lead to a good quality/high performance facial image from both techniques based on our experiments with the acquired data.",
author = "Gamal Fahmy and Ahmed El-Sherbeeny and Susmita Mandala and Mohamed Abdel-Mottaleb and Hany Ammar",
year = "2006",
month = "8",
day = "29",
doi = "10.1117/12.666527",
language = "English",
isbn = "0819462586",
volume = "6202",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - The effect of lighting direction/condition on the performance of face recognition algorithms

AU - Fahmy, Gamal

AU - El-Sherbeeny, Ahmed

AU - Mandala, Susmita

AU - Abdel-Mottaleb, Mohamed

AU - Ammar, Hany

PY - 2006/8/29

Y1 - 2006/8/29

N2 - In this paper, we measure the effect of the lighting direction in facial images on the performance of 2 well-known face recognition algorithms, an appearance based method and a facial feature based method. We collect hundreds/thousands of facial images of subjects with a fixed pose and under different lighting conditions through a unique facial acquisition laboratory designed specifically for this purpose. Then we present a methodology for automatically detecting the lighting direction of different face images based on statistics derived from the image. We also detect if there is any glare regions in some lighting directions. Finally we determine the most reliable lighting direction that will lead to a good quality/high performance facial image from both techniques based on our experiments with the acquired data.

AB - In this paper, we measure the effect of the lighting direction in facial images on the performance of 2 well-known face recognition algorithms, an appearance based method and a facial feature based method. We collect hundreds/thousands of facial images of subjects with a fixed pose and under different lighting conditions through a unique facial acquisition laboratory designed specifically for this purpose. Then we present a methodology for automatically detecting the lighting direction of different face images based on statistics derived from the image. We also detect if there is any glare regions in some lighting directions. Finally we determine the most reliable lighting direction that will lead to a good quality/high performance facial image from both techniques based on our experiments with the acquired data.

UR - http://www.scopus.com/inward/record.url?scp=33747723471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747723471&partnerID=8YFLogxK

U2 - 10.1117/12.666527

DO - 10.1117/12.666527

M3 - Conference contribution

SN - 0819462586

SN - 9780819462589

VL - 6202

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -