Abstract | ||
---|---|---|
Variations in illumination can have a dramatic effect on the appearance of an object in an image. In this pa- per we propose how to deal with illumination variations in eigenspace methods. We demonstrate that the eigenimages obtained by a training set under a single illumination con- dition (ambient light) can be used for recognition of objects taken under different illumination conditions. The major idea is to incorporate a set of gradient based$lter banks into the eigenspace recognition framework. This can be achieved since the eigenimage coeficients are invariant for linearly3ltered images (input and eigenimages). To achieve further illumination insensitivity we devised a robust proce- dure for coeficient recovery. The proposed approach has been extensively evaluated on a set of 2160 images and the results were compared to other approaches. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1109/ICCV.2001.937523 | Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference |
Keywords | Field | DocType |
computational geometry,object recognition,eigenimages,eigenspace recognition framework,gradient based filter banks,illumination insensitive eigenspaces,illumination variations,linearly filtered images,objects recognition,robust procedure | Training set,Computer vision,Pattern recognition,Computer science,Computational geometry,Invariant (mathematics),Artificial intelligence,Eigenvalues and eigenvectors,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISBN | Citations |
1 | 0-7695-1143-0 | 22 |
PageRank | References | Authors |
2.96 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Horst Bischof | 1 | 8751 | 541.43 |
Horst Wildenauer | 2 | 126 | 12.81 |
Ales Leonardis | 3 | 1636 | 147.33 |