Loading...
Please wait, while we are loading the content...
Similar Documents
Optimal Linear Combination of Facial Regions for Improving Identification Performance
| Content Provider | CiteSeerX |
|---|---|
| Author | Wong, Kin-Chung Lin, Wei-Yang Hu, Yu Hen Zhang, Xueqin |
| Abstract | Abstract — This paper presents a novel 3D multi-region face recognition algorithm that consists of new geometric summation invariant features, and an optimal linear feature fusion method. A summation invariant, which captures local characteristics of a facial surface, is extracted from multiple sub-regions of a 3D range image as the discriminative features. Similarity scores between two range images are calculated from the selected sub-regions. A novel fusion method based on linear discriminant analysis (LDA) is developed to maximize the verification rate by weighted combination of these similarity scores. Experiments on the FRGC (Face Recognition Grand Challenge) V2.0 dataset show that this new algorithm improves the recognition performance significantly in the presence of facial expressions. |
| File Format | |
| Language | English |
| Publisher Institution | of 30 9/24/2007 of Wisconsin – Madison |
| Access Restriction | Open |
| Subject Keyword | Facial Region Optimal Linear Combination Improving Identification Performance Range Image Similarity Score Recognition Performance Multi-region Face Recognition Multiple Sub-regions Summation Invariant Weighted Combination Optimal Linear Feature Fusion Method Linear Discriminant Analysis Facial Expression Verification Rate Face Recognition Grand Challenge Novel Fusion Method New Geometric Summation Invariant Feature Local Characteristic Facial Surface New Algorithm Dataset Show Discriminative Feature |
| Content Type | Text |
| Resource Type | Technical Report |
