FORMS: a flexible object recognition and modeling system
International Journal of Computer Vision
Supporting similarity queries in MARS
MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Processing Using Pulse-Coupled Neural Networks
Image Processing Using Pulse-Coupled Neural Networks
Object Recognition Using Appearance-Based Parts and Relations
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
AIPR '04 Proceedings of the 33rd Applied Imagery Pattern Recognition Workshop
Hi-index | 0.00 |
Towards the construction of a content based image recognition system it is important to isolate and also represent image segments. There have been several proposed methods of representing a shape but many are not sensitive to deviations of the appearance of an object. Furthermore, it is noted that the set of possible shapes is not distributed equally within a representation space. Thus, liberating the requirement that a basis set be orthonormal is justified. A method is presented here that extracts a basis set from an image database and defines shapes from this basis set. The results indicate that describing shapes from this basis set is robust to alterations of the shape such as small occlusions, limited skew, and limited range.