Paper Info
Title
Improved Face Model Fitting Using Tensor-Based AAM
Abstract
In this paper, we propose a tensor-based active appearance model (AAM) which improves the fitting performance of conventional AAM. Tensor-based AAM generates the specific AAM basis vectors by indexing the model tensor in terms of the estimated input image variations. Experimental results show that the proposed tensor-based AAM reduces the average fitting error than the conventional AAM significantly.
Year
DOI
Venue
2008
10.1109/ISUVR.2008.15
Gwangju
Keywords
DocType
ISBN
face model fitting,average fitting error,face recognition,improved face model fitting,proposed tensor-based aam,tensor-based active appearance model,aam,model tensor,image classification,estimated input image variation,specific aam basis,conventional aam,image variations,tensor-based aam,tensors,fitting performance,shape,stacking,vectors,active shape model,active appearance model,face detection,lighting,principal component analysis,impedance matching,indexation,matrix decomposition,detectors,robustness,solid modeling,fitting,tensile stress,databases,singular value decomposition,biomedical imaging,computer vision,indexing,computational modeling,estimation,image recognition,virtual reality,mathematical model
Conference
978-0-7695-3259-2
Citations 
PageRank 
References 
0
0.34
8
Authors
2
Name
Order
Citations
PageRank
Daijin Kim11882126.85
Hyung-Soo Lee213213.10