Abstract | ||
---|---|---|
A new object recognition method, the Invariant Pixel Set Signature (IPSS), is introduced. Objects are represented with a probability density on the space of invariants computed from measurements (pixel values) inside convex hulls of n-tuples of interest points. Experimentally the method is tested on COIL- 20, a publicly available database of 72 views of 20 natural object rotating on a turntable. With a model built from a single view, recognition performance measured by the average match percentile is above for degrees and above for degrees. For some object, 100% first rank is achieved for all 72 views. Robustness to occlusion is shown using images with one half covered. For a small change of viewpoint ( degrees) recognition of the occluded object is perfect. |
Year | Venue | Keywords |
---|---|---|
2000 | BMVC | object recognition,convex hull,probability density |
Field | DocType | Citations |
Computer vision,3D single-object recognition,Pattern recognition,Computer science,Robustness (computer science),Regular polygon,Pixel,Invariant (mathematics),Artificial intelligence,Probability density function,Percentile,Cognitive neuroscience of visual object recognition | Conference | 14 |
PageRank | References | Authors |
6.47 | 17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiri Matas | 1 | 335 | 35.85 |
J. Burianek | 2 | 14 | 6.47 |
J. Kittler | 3 | 14346 | 1465.03 |