Integration of visual modules: an extension of the Marr paradigm
Integration of visual modules: an extension of the Marr paradigm
Computer Vision, Graphics, and Image Processing
Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Perceptual Organization for Scene Segmentation and Description
IEEE Transactions on Pattern Analysis and Machine Intelligence
Inferring global perceptual contours from local features
International Journal of Computer Vision - Special issue on computer vision research at the University of Southern California
Perceptual Organization and Visual Recognition
Perceptual Organization and Visual Recognition
Figure-Ground Discrimination: A Combinatorial Optimization Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preattentive Grouping and Attentive Selection for Early Visual Computation
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume IV-Volume 7472 - Volume 7472
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Hi-index | 0.00 |
A network for the extraction of salient image structure in dot patterns is proposed which uses a phase diffusion process to label the image into holistic perceptual objects and the background. The image is processed using three successive stages, copying the design of biological visual mechanisms. The population coded direction specific edge representation generated from phase-dependent energy filters is used by a competitive and cooperative phase process to allow boundary completion, grouping of perceptual elements and the suppression of false responses generated by the edge detection stage.