| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
J. Matas and D. Koubaroulis and J. Kittler
ABSTRACT
The proposed method represents object or image colour structure by features computed from neighbourhoods with multi-modal colour density function. Stable invariants are derived from modes of colour density that are robustly estimated by the mean shift algorithm. The problem of extracting local invariant colour features is addressed directly, without a need for prior segmentation or edge detection. The signature is concise — an image is typically represented by a few hundred bytes, a few thousands for very complex scenes. We demonstrate the algorithm’s performance on a standard colour object recognition task using a publicly available dataset. Very good recognition performance (average match percentile 99.5) was achieved in real time (average 0.28 seconds per match) which compares favourably with results reported in the literature. The method has been shown to operate successfully under changing illumination, viewpoint, object pose, non-rigid deformation and partial occlusion. |
|
| Site generated on Friday, 06 January 2006
|