 |
Technical Program
Paper Detail
| Paper: | TP-P6.8 |
| Session: | Face Recognition |
| Time: | Tuesday, October 10, 14:20 - 17:00 |
| Presentation: |
Poster
|
| Title: |
ELLIPTIC METRIC K-NN LEARNING METHOD WITH ASYMPTOTIC MDL MEASURE |
| Authors: |
Takami Satonaka; Kumamoto Prefectual College of Technology | | | | | Keiichi Uchimura; Kumamoto University | | |
| Abstract: |
We describe an adaptive metric learning model combining the generative model and the discriminative model for the face recognition. The asymptotic model based on the MDL criterion is formulated for each class to estimate the variance by using small training examples. The feature fusion method is introduced to assume the missing patterns between the classes and to deal with the k-th nearest neighbor classification. The metric parameters obtained from the asymptotic MDL estimation are refined by using the synthesized feature patterns. We demonstrate an improved performance for face recognition on the ORL and UMIST face database. |
|
