Face alignment using segmentation and a combined AAM in a PTZ camera

Kwontaeg Choi, Jung Ho Ahn, Hyeran Byun

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

3 Citations (Scopus)

Abstract

In this paper, we propose a novel framework for face alignment based on the Active Appearance Model (AAM) in surveillance systems with Pan-Tilt-Zoom (PTZ) cameras. The AAM converges poorly in face images which are affected by illumination factors, cluttered backgrounds and status of the camera. To search for robust face model parameters, we propose a robust AAM fitting method based on segmenting faces and combining Person-specific and Generic models to achieve accurate face alignment. We segment faces using histogram back-projection and a skin color histogram, which is updated using a skin mask extracted by the AAM. For robust face recognition, we combined Generic and Person-specific models with a slight reduction in processing time. The extracted AAM parameters are as accurate as those when using the Person-specific model and can be used as features for face recognition. Empirical experiments show that our proposed method extracts very accurate face parameters and is not sensitive to initial shapes.

Original languageEnglish
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages1191-1194
Number of pages4
DOIs
Publication statusPublished - 2006 Dec 1
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: 2006 Aug 202006 Aug 24

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume3
ISSN (Print)1051-4651

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period06/8/2006/8/24

Fingerprint

Cameras
Face recognition
Skin
Masks
Lighting
Color
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Choi, K., Ahn, J. H., & Byun, H. (2006). Face alignment using segmentation and a combined AAM in a PTZ camera. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006 (pp. 1191-1194). [1699739] (Proceedings - International Conference on Pattern Recognition; Vol. 3). https://doi.org/10.1109/ICPR.2006.523
Choi, Kwontaeg ; Ahn, Jung Ho ; Byun, Hyeran. / Face alignment using segmentation and a combined AAM in a PTZ camera. Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. pp. 1191-1194 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{d21cc52656f24eef88cddb3b8a44c61e,
title = "Face alignment using segmentation and a combined AAM in a PTZ camera",
abstract = "In this paper, we propose a novel framework for face alignment based on the Active Appearance Model (AAM) in surveillance systems with Pan-Tilt-Zoom (PTZ) cameras. The AAM converges poorly in face images which are affected by illumination factors, cluttered backgrounds and status of the camera. To search for robust face model parameters, we propose a robust AAM fitting method based on segmenting faces and combining Person-specific and Generic models to achieve accurate face alignment. We segment faces using histogram back-projection and a skin color histogram, which is updated using a skin mask extracted by the AAM. For robust face recognition, we combined Generic and Person-specific models with a slight reduction in processing time. The extracted AAM parameters are as accurate as those when using the Person-specific model and can be used as features for face recognition. Empirical experiments show that our proposed method extracts very accurate face parameters and is not sensitive to initial shapes.",
author = "Kwontaeg Choi and Ahn, {Jung Ho} and Hyeran Byun",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICPR.2006.523",
language = "English",
isbn = "0769525210",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "1191--1194",
booktitle = "Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006",

}

Choi, K, Ahn, JH & Byun, H 2006, Face alignment using segmentation and a combined AAM in a PTZ camera. in Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006., 1699739, Proceedings - International Conference on Pattern Recognition, vol. 3, pp. 1191-1194, 18th International Conference on Pattern Recognition, ICPR 2006, Hong Kong, China, 06/8/20. https://doi.org/10.1109/ICPR.2006.523

Face alignment using segmentation and a combined AAM in a PTZ camera. / Choi, Kwontaeg; Ahn, Jung Ho; Byun, Hyeran.

Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. p. 1191-1194 1699739 (Proceedings - International Conference on Pattern Recognition; Vol. 3).

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

TY - GEN

T1 - Face alignment using segmentation and a combined AAM in a PTZ camera

AU - Choi, Kwontaeg

AU - Ahn, Jung Ho

AU - Byun, Hyeran

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this paper, we propose a novel framework for face alignment based on the Active Appearance Model (AAM) in surveillance systems with Pan-Tilt-Zoom (PTZ) cameras. The AAM converges poorly in face images which are affected by illumination factors, cluttered backgrounds and status of the camera. To search for robust face model parameters, we propose a robust AAM fitting method based on segmenting faces and combining Person-specific and Generic models to achieve accurate face alignment. We segment faces using histogram back-projection and a skin color histogram, which is updated using a skin mask extracted by the AAM. For robust face recognition, we combined Generic and Person-specific models with a slight reduction in processing time. The extracted AAM parameters are as accurate as those when using the Person-specific model and can be used as features for face recognition. Empirical experiments show that our proposed method extracts very accurate face parameters and is not sensitive to initial shapes.

AB - In this paper, we propose a novel framework for face alignment based on the Active Appearance Model (AAM) in surveillance systems with Pan-Tilt-Zoom (PTZ) cameras. The AAM converges poorly in face images which are affected by illumination factors, cluttered backgrounds and status of the camera. To search for robust face model parameters, we propose a robust AAM fitting method based on segmenting faces and combining Person-specific and Generic models to achieve accurate face alignment. We segment faces using histogram back-projection and a skin color histogram, which is updated using a skin mask extracted by the AAM. For robust face recognition, we combined Generic and Person-specific models with a slight reduction in processing time. The extracted AAM parameters are as accurate as those when using the Person-specific model and can be used as features for face recognition. Empirical experiments show that our proposed method extracts very accurate face parameters and is not sensitive to initial shapes.

UR - http://www.scopus.com/inward/record.url?scp=34147105398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147105398&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.523

DO - 10.1109/ICPR.2006.523

M3 - Conference contribution

AN - SCOPUS:34147105398

SN - 0769525210

SN - 9780769525211

T3 - Proceedings - International Conference on Pattern Recognition

SP - 1191

EP - 1194

BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006

ER -

Choi K, Ahn JH, Byun H. Face alignment using segmentation and a combined AAM in a PTZ camera. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. p. 1191-1194. 1699739. (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2006.523