Paper Info
Title
3D Active Shape Model for Automatic Facial Landmark Location Trained with Automatically Generated Landmark Points
Abstract
In this paper, a 3D Active Shape Model (3DASM) algorithm is presented to automatically locate facial landmarks from different views. The 3DASM is trained by setting different shape and texture parameters of 3D Morphable Model (3DMM). Using 3DMM to synthesize training data offers us two advantages: first, few manual operations are need, except labeling landmarks on the mean face of 3DMM. Second, since the learning data are directly from 3DMM, landmarks have one to one correspondence between the 2D points detected from the image and 3D points on 3DMM. This kind of correspondence will benefit 3D face reconstruction processing. During fitting, 3D rotation parameters are added comparing to 2D Active Shape Model (ASM). So we separate shape variations into intrinsic change (caused by the character of different person) and extrinsic change (caused by model projection). The experimental results show that our method is robust to pose variation.
Year
DOI
Venue
2010
10.1109/ICPR.2010.926
ICPR
Keywords
Field
DocType
different view,automatically generated landmark points,active shape model,separate shape variation,extrinsic change,different person,intrinsic change,different shape,face reconstruction processing,mean face,morphable model,automatic facial landmark location,image reconstruction,face recognition,face,solid modeling,shape,pose estimation,databases
Iterative reconstruction,Computer vision,Active shape model,Facial recognition system,Bijection,Pattern recognition,Computer science,Pose,Active appearance model,Solid modeling,Artificial intelligence,Landmark
Conference
Citations 
PageRank 
References 
4
0.42
10
Authors
3
Name
Order
Citations
PageRank
Dianle Zhou191.57
Dijana Petrovska-Delacretaz2576.98
Bernadette Dorizzi3103882.70