Using salient region constraints on active appearance model initialization for facial feature extraction

Yuan Wong, Pau-Choo Chung

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

1 Citation (Scopus)

Abstract

Due to the high robustness, Active Appearance Model algorithm (AAM) has been adopted to find face feature points. However, if the initial position of the AAM does not properly cover these feature points, AAM will converge to an illogical location. To resolve this problem, this paper develops salient region constraints on AAM initialization for facial feature extraction. In this approach, we first identify the mouth region and adopt a mouth-constrained mean model as the initialization of the AAM. By this approach, the initial position can be placed closer to the target. The experiments show that the method is effective.

Original languageEnglish
Title of host publicationICS 2010 - International Computer Symposium
Pages24-27
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan
Duration: 2010 Dec 162010 Dec 18

Publication series

NameICS 2010 - International Computer Symposium

Other

Other2010 International Computer Symposium, ICS 2010
CountryTaiwan
CityTainan
Period10-12-1610-12-18

Fingerprint

Feature extraction
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Wong, Y., & Chung, P-C. (2010). Using salient region constraints on active appearance model initialization for facial feature extraction. In ICS 2010 - International Computer Symposium (pp. 24-27). [5685508] (ICS 2010 - International Computer Symposium). https://doi.org/10.1109/COMPSYM.2010.5685508
Wong, Yuan ; Chung, Pau-Choo. / Using salient region constraints on active appearance model initialization for facial feature extraction. ICS 2010 - International Computer Symposium. 2010. pp. 24-27 (ICS 2010 - International Computer Symposium).
@inproceedings{7dd32d59b76c4de7886f1e3761240b7f,
title = "Using salient region constraints on active appearance model initialization for facial feature extraction",
abstract = "Due to the high robustness, Active Appearance Model algorithm (AAM) has been adopted to find face feature points. However, if the initial position of the AAM does not properly cover these feature points, AAM will converge to an illogical location. To resolve this problem, this paper develops salient region constraints on AAM initialization for facial feature extraction. In this approach, we first identify the mouth region and adopt a mouth-constrained mean model as the initialization of the AAM. By this approach, the initial position can be placed closer to the target. The experiments show that the method is effective.",
author = "Yuan Wong and Pau-Choo Chung",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/COMPSYM.2010.5685508",
language = "English",
isbn = "9781424476404",
series = "ICS 2010 - International Computer Symposium",
pages = "24--27",
booktitle = "ICS 2010 - International Computer Symposium",

}

Wong, Y & Chung, P-C 2010, Using salient region constraints on active appearance model initialization for facial feature extraction. in ICS 2010 - International Computer Symposium., 5685508, ICS 2010 - International Computer Symposium, pp. 24-27, 2010 International Computer Symposium, ICS 2010, Tainan, Taiwan, 10-12-16. https://doi.org/10.1109/COMPSYM.2010.5685508

Using salient region constraints on active appearance model initialization for facial feature extraction. / Wong, Yuan; Chung, Pau-Choo.

ICS 2010 - International Computer Symposium. 2010. p. 24-27 5685508 (ICS 2010 - International Computer Symposium).

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

TY - GEN

T1 - Using salient region constraints on active appearance model initialization for facial feature extraction

AU - Wong, Yuan

AU - Chung, Pau-Choo

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Due to the high robustness, Active Appearance Model algorithm (AAM) has been adopted to find face feature points. However, if the initial position of the AAM does not properly cover these feature points, AAM will converge to an illogical location. To resolve this problem, this paper develops salient region constraints on AAM initialization for facial feature extraction. In this approach, we first identify the mouth region and adopt a mouth-constrained mean model as the initialization of the AAM. By this approach, the initial position can be placed closer to the target. The experiments show that the method is effective.

AB - Due to the high robustness, Active Appearance Model algorithm (AAM) has been adopted to find face feature points. However, if the initial position of the AAM does not properly cover these feature points, AAM will converge to an illogical location. To resolve this problem, this paper develops salient region constraints on AAM initialization for facial feature extraction. In this approach, we first identify the mouth region and adopt a mouth-constrained mean model as the initialization of the AAM. By this approach, the initial position can be placed closer to the target. The experiments show that the method is effective.

UR - http://www.scopus.com/inward/record.url?scp=79851497258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851497258&partnerID=8YFLogxK

U2 - 10.1109/COMPSYM.2010.5685508

DO - 10.1109/COMPSYM.2010.5685508

M3 - Conference contribution

SN - 9781424476404

T3 - ICS 2010 - International Computer Symposium

SP - 24

EP - 27

BT - ICS 2010 - International Computer Symposium

ER -

Wong Y, Chung P-C. Using salient region constraints on active appearance model initialization for facial feature extraction. In ICS 2010 - International Computer Symposium. 2010. p. 24-27. 5685508. (ICS 2010 - International Computer Symposium). https://doi.org/10.1109/COMPSYM.2010.5685508