A feature and appearance based method for eye detection on gray intensity face images

Visal Kith, Mohamed El-Sharkawy, Tonya Bergeson-Dana, Salwa El-Ramly, Said Elnoubi

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

10 Citations (Scopus)

Abstract

This paper presents a robust and precise eye detection algorithm on gray intensity face images. Our method combines the strength of two existing methods which are a feature based method and an appearance based method to detect and locate a precise pupil center. It includes the following three steps. First, the feature based method is used. The method uses a projection function to detect all possible regions of each left and right eye. Second, the appearance based method is used to filter out all non eye regions, and keep only one region for each left and right eye. All possible regions will go through a Principal Component Analysis (PCA). Third, a modified hybrid projection function is used to locate the pupil center for both eyes. The experimental results show that the proposed method has an efficient performance with the accuracy of more than 90.52%.

Original languageEnglish
Title of host publication2008 International Conference on Computer Engineering and Systems, ICCES 2008
Pages41-47
Number of pages7
DOIs
StatePublished - 2008
Event2008 International Conference on Computer Engineering and Systems, ICCES 2008 - Cairo, Egypt
Duration: Nov 25 2008Nov 27 2008

Other

Other2008 International Conference on Computer Engineering and Systems, ICCES 2008
CountryEgypt
CityCairo
Period11/25/0811/27/08

Fingerprint

Principal component analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Kith, V., El-Sharkawy, M., Bergeson-Dana, T., El-Ramly, S., & Elnoubi, S. (2008). A feature and appearance based method for eye detection on gray intensity face images. In 2008 International Conference on Computer Engineering and Systems, ICCES 2008 (pp. 41-47). [4772963] https://doi.org/10.1109/ICCES.2008.4772963

A feature and appearance based method for eye detection on gray intensity face images. / Kith, Visal; El-Sharkawy, Mohamed; Bergeson-Dana, Tonya; El-Ramly, Salwa; Elnoubi, Said.

2008 International Conference on Computer Engineering and Systems, ICCES 2008. 2008. p. 41-47 4772963.

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

Kith, V, El-Sharkawy, M, Bergeson-Dana, T, El-Ramly, S & Elnoubi, S 2008, A feature and appearance based method for eye detection on gray intensity face images. in 2008 International Conference on Computer Engineering and Systems, ICCES 2008., 4772963, pp. 41-47, 2008 International Conference on Computer Engineering and Systems, ICCES 2008, Cairo, Egypt, 11/25/08. https://doi.org/10.1109/ICCES.2008.4772963
Kith V, El-Sharkawy M, Bergeson-Dana T, El-Ramly S, Elnoubi S. A feature and appearance based method for eye detection on gray intensity face images. In 2008 International Conference on Computer Engineering and Systems, ICCES 2008. 2008. p. 41-47. 4772963 https://doi.org/10.1109/ICCES.2008.4772963
Kith, Visal ; El-Sharkawy, Mohamed ; Bergeson-Dana, Tonya ; El-Ramly, Salwa ; Elnoubi, Said. / A feature and appearance based method for eye detection on gray intensity face images. 2008 International Conference on Computer Engineering and Systems, ICCES 2008. 2008. pp. 41-47
@inproceedings{7a6f96c46a90407e978611a775cae6cc,
title = "A feature and appearance based method for eye detection on gray intensity face images",
abstract = "This paper presents a robust and precise eye detection algorithm on gray intensity face images. Our method combines the strength of two existing methods which are a feature based method and an appearance based method to detect and locate a precise pupil center. It includes the following three steps. First, the feature based method is used. The method uses a projection function to detect all possible regions of each left and right eye. Second, the appearance based method is used to filter out all non eye regions, and keep only one region for each left and right eye. All possible regions will go through a Principal Component Analysis (PCA). Third, a modified hybrid projection function is used to locate the pupil center for both eyes. The experimental results show that the proposed method has an efficient performance with the accuracy of more than 90.52{\%}.",
author = "Visal Kith and Mohamed El-Sharkawy and Tonya Bergeson-Dana and Salwa El-Ramly and Said Elnoubi",
year = "2008",
doi = "10.1109/ICCES.2008.4772963",
language = "English",
isbn = "9781424421152",
pages = "41--47",
booktitle = "2008 International Conference on Computer Engineering and Systems, ICCES 2008",

}

TY - GEN

T1 - A feature and appearance based method for eye detection on gray intensity face images

AU - Kith, Visal

AU - El-Sharkawy, Mohamed

AU - Bergeson-Dana, Tonya

AU - El-Ramly, Salwa

AU - Elnoubi, Said

PY - 2008

Y1 - 2008

N2 - This paper presents a robust and precise eye detection algorithm on gray intensity face images. Our method combines the strength of two existing methods which are a feature based method and an appearance based method to detect and locate a precise pupil center. It includes the following three steps. First, the feature based method is used. The method uses a projection function to detect all possible regions of each left and right eye. Second, the appearance based method is used to filter out all non eye regions, and keep only one region for each left and right eye. All possible regions will go through a Principal Component Analysis (PCA). Third, a modified hybrid projection function is used to locate the pupil center for both eyes. The experimental results show that the proposed method has an efficient performance with the accuracy of more than 90.52%.

AB - This paper presents a robust and precise eye detection algorithm on gray intensity face images. Our method combines the strength of two existing methods which are a feature based method and an appearance based method to detect and locate a precise pupil center. It includes the following three steps. First, the feature based method is used. The method uses a projection function to detect all possible regions of each left and right eye. Second, the appearance based method is used to filter out all non eye regions, and keep only one region for each left and right eye. All possible regions will go through a Principal Component Analysis (PCA). Third, a modified hybrid projection function is used to locate the pupil center for both eyes. The experimental results show that the proposed method has an efficient performance with the accuracy of more than 90.52%.

UR - http://www.scopus.com/inward/record.url?scp=67649562727&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649562727&partnerID=8YFLogxK

U2 - 10.1109/ICCES.2008.4772963

DO - 10.1109/ICCES.2008.4772963

M3 - Conference contribution

AN - SCOPUS:67649562727

SN - 9781424421152

SP - 41

EP - 47

BT - 2008 International Conference on Computer Engineering and Systems, ICCES 2008

ER -