Facial features extraction in color images using enhanced active shape model

Mohammad H. Mahoor, Mohamed Abdel-Mottaleb

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

46 Citations (Scopus)

Abstract

In this paper, we present an improved Active Shape Model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction.

Original languageEnglish
Title of host publicationFGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Pages144-148
Number of pages5
Volume2006
DOIs
StatePublished - Nov 14 2006
EventFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition - Southampton, United Kingdom
Duration: Apr 10 2006Apr 12 2006

Other

OtherFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition
CountryUnited Kingdom
CitySouthampton
Period4/10/064/12/06

Fingerprint

Feature extraction
Color
Experiments

Keywords

  • Active shape model
  • Color image
  • Face recognition
  • Facial feature extraction
  • Lips detection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Mahoor, M. H., & Abdel-Mottaleb, M. (2006). Facial features extraction in color images using enhanced active shape model. In FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (Vol. 2006, pp. 144-148). [1613012] https://doi.org/10.1109/FGR.2006.51

Facial features extraction in color images using enhanced active shape model. / Mahoor, Mohammad H.; Abdel-Mottaleb, Mohamed.

FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. Vol. 2006 2006. p. 144-148 1613012.

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

Mahoor, MH & Abdel-Mottaleb, M 2006, Facial features extraction in color images using enhanced active shape model. in FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. vol. 2006, 1613012, pp. 144-148, FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition, Southampton, United Kingdom, 4/10/06. https://doi.org/10.1109/FGR.2006.51
Mahoor MH, Abdel-Mottaleb M. Facial features extraction in color images using enhanced active shape model. In FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. Vol. 2006. 2006. p. 144-148. 1613012 https://doi.org/10.1109/FGR.2006.51
Mahoor, Mohammad H. ; Abdel-Mottaleb, Mohamed. / Facial features extraction in color images using enhanced active shape model. FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. Vol. 2006 2006. pp. 144-148
@inproceedings{cd03a9a063fb47b698e8262409ce282c,
title = "Facial features extraction in color images using enhanced active shape model",
abstract = "In this paper, we present an improved Active Shape Model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction.",
keywords = "Active shape model, Color image, Face recognition, Facial feature extraction, Lips detection",
author = "Mahoor, {Mohammad H.} and Mohamed Abdel-Mottaleb",
year = "2006",
month = "11",
day = "14",
doi = "10.1109/FGR.2006.51",
language = "English",
isbn = "0769525032",
volume = "2006",
pages = "144--148",
booktitle = "FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition",

}

TY - GEN

T1 - Facial features extraction in color images using enhanced active shape model

AU - Mahoor, Mohammad H.

AU - Abdel-Mottaleb, Mohamed

PY - 2006/11/14

Y1 - 2006/11/14

N2 - In this paper, we present an improved Active Shape Model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction.

AB - In this paper, we present an improved Active Shape Model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction.

KW - Active shape model

KW - Color image

KW - Face recognition

KW - Facial feature extraction

KW - Lips detection

UR - http://www.scopus.com/inward/record.url?scp=33750798244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750798244&partnerID=8YFLogxK

U2 - 10.1109/FGR.2006.51

DO - 10.1109/FGR.2006.51

M3 - Conference contribution

SN - 0769525032

SN - 9780769525037

VL - 2006

SP - 144

EP - 148

BT - FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition

ER -