Abstract | ||
---|---|---|
We propose a novel framework for detecting human faces based on correspondences between triplets of detected local features and their counterparts in an affine invariant face appearance model.Th e method is robust to partial occlusion, feature detector failure and copes well with cluttered background. Both the appearance and configuration probabilities are learned from examples. The method was tested on the XM2VTS database and a limited number of images with cluttered background with promising results - 2% false negative rate - was obtained. |
Year | Venue | Keywords |
---|---|---|
2002 | SSPR/SPR | learned affine correspondences,configuration probability,novel framework,cluttered background,feature detector failure,face detection,xm2vts database,local feature,limited number,false negative rate,affine invariant face appearance,th e method |
Field | DocType | ISBN |
Affine transformation,Facial recognition system,Computer vision,Object-class detection,Feature detection,Pattern recognition,Computer science,Active appearance model,Affine invariant,Artificial intelligence,Face detection | Conference | 3-540-44011-9 |
Citations | PageRank | References |
7 | 0.83 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Miroslav Hamouz | 1 | 106 | 7.98 |
J. Kittler | 2 | 14346 | 1465.03 |
Jiri Matas | 3 | 335 | 35.85 |
Petr Bílek | 4 | 7 | 0.83 |