TY - JOUR
T1 - Lip segmentation under MAP-MRF framework with automatic selection of local observation scale and number of segments
AU - CHEUNG, Yiu Ming
AU - Li, Meng
AU - Cao, Xiaochun
AU - You, Xinge
N1 - This work was supported in part by the Research Grant Council of Hong Kong under Project HKBU 210309, in part by the Faculty Research Grants, Hong Kong Baptist University, Hong Kong, under Project FRG2/11-12/067 and Project FRG2/12-13/082, in part by the National Science Foundation of China under Grant 61272366, Grant 61272203, and Grant 61332012, in part by the 100 Talents Programme, Chinese Academy of Sciences, Beijing, China, in part by the International Scientific and Technological Cooperation Project under Grant 2011DFA12180, in part by the National Science and Technology Research and Development Program under Grant 2012BAK02B06, and in part by the Ph.D. Programs Foundation, Ministry of Education of China, under
Grant 20110142110060.
PY - 2014/8
Y1 - 2014/8
N2 - This paper addresses the problem of segmenting lip region from frontal human face image. Supposing each pixel of the target image has an optimal local scale from the segmentation viewpoint, we treat the lip segmentation problem as a combination of observation scale selection and observed data classification. Accordingly, we propose a hierarchical multiscale Markov random field (MRF) model to represent the membership map of each input pixel to a specific segment and local-scale map simultaneously. Subsequently, lip segmentation can be formulated as an optimal problem in the maximum a posteriori (MAP)-MRF framework. Then, we present a rival-penalized iterative algorithm to implement the segmentation, which is independent of the number of predefined segments. The proposed method mainly features two aspects: 1) its performance is independent of the predefined number of segments, and 2) it takes into account the local optimal observation scale for each pixel. Finally, we conduct the experiments on four benchmark databases, i.e. AR, CVL, GTAV, and VidTIMIT. Experimental results show that the proposed method is robust to the segment number that changes with a speaker's appearance, and can enhance the segmentation accuracy by taking advantage of the local optimal observation scale information.
AB - This paper addresses the problem of segmenting lip region from frontal human face image. Supposing each pixel of the target image has an optimal local scale from the segmentation viewpoint, we treat the lip segmentation problem as a combination of observation scale selection and observed data classification. Accordingly, we propose a hierarchical multiscale Markov random field (MRF) model to represent the membership map of each input pixel to a specific segment and local-scale map simultaneously. Subsequently, lip segmentation can be formulated as an optimal problem in the maximum a posteriori (MAP)-MRF framework. Then, we present a rival-penalized iterative algorithm to implement the segmentation, which is independent of the number of predefined segments. The proposed method mainly features two aspects: 1) its performance is independent of the predefined number of segments, and 2) it takes into account the local optimal observation scale for each pixel. Finally, we conduct the experiments on four benchmark databases, i.e. AR, CVL, GTAV, and VidTIMIT. Experimental results show that the proposed method is robust to the segment number that changes with a speaker's appearance, and can enhance the segmentation accuracy by taking advantage of the local optimal observation scale information.
KW - Lip segmentation
KW - local scale selection
KW - MAP-MRF framework
KW - number of segments
UR - https://www.scopus.com/pages/publications/84904352459
U2 - 10.1109/TIP.2014.2331137
DO - 10.1109/TIP.2014.2331137
M3 - Journal article
C2 - 24956364
AN - SCOPUS:84904352459
SN - 1057-7149
VL - 23
SP - 3397
EP - 3411
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 8
M1 - 6837537
ER -