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
AN - SCOPUS:79851497258
SN - 9781424476404
T3 - ICS 2010 - International Computer Symposium
SP - 24
EP - 27
BT - ICS 2010 - International Computer Symposium
T2 - 2010 International Computer Symposium, ICS 2010
Y2 - 16 December 2010 through 18 December 2010
ER -