Abstract | ||
---|---|---|
Indexing is an efficient method of recovering matchhypotheses in model-based object recognition. Unlikeother methods, which search for viewpoint-invariantshape descriptors to use as indices, we use a learningmethod to model the smooth variation in appearance oflocal feature sets (LFS). Indexing from LFS effectivelydeals with the problems of occlusion and missing features.The indexing functions generated by the learningmethod are probability distributions describing thepossible... |
Year | DOI | Venue |
---|---|---|
1994 | 10.1109/CVPR.1994.323840 | CVPR |
Keywords | Field | DocType |
image recognition,3-D model-based object recognition,image features,indexing functions learning,local feature sets,model types,occlusion,viewpoint-invariant shape descriptors | Computer vision,3D single-object recognition,Pattern recognition,Feature (computer vision),Computer science,Search engine indexing,Probability distribution,Feature (machine learning),Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
1994 | 1 | 1063-6919 |
Citations | PageRank | References |
20 | 5.30 | 11 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeffrey S. Beis | 1 | 20 | 5.30 |
D. G. Lowe | 2 | 15718 | 1413.60 |