A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Texture segmentation based on a hierarchical Markov random field model
Signal Processing
Geometric aspects of visual object recognition
Geometric aspects of visual object recognition
Statistical learning, localization, and identification of objects
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Mean Shift Analysis and Applications
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Hi-index | 0.00 |
The objects appearance in the images is modified because of several external factors (i.e.: illumination, rotate, pose) and the application of the standard comparison algorithms does not answer suitably. For landing this problem, we present here an architecture based on a gradual recognition: The object is represented on a scale of categories, and the task of the algorithms of recognition is to concentrate on the determination of the category the most detailed according to information extracted from the image. It is not necessary any more to pass by several intermediate phases before starting the process of recognition. On this principle, we propose a model for the internal representation of a system of vision which tries to generalize the recognition of objects by taking into account the categorization.