A Generic Grouping Algorithm and Its Quantitative Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour and Texture Analysis for Image Segmentation
International Journal of Computer Vision
Guest Editors' Introduction to the Special Section on Perceptual Organization in Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 2
Contour grouping with prior models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Perceptual organization has two essential factors that affect the grouping result directly: how to extract grouping cues and how to grouping. In this paper, a global contour-grouping algorithm based on spectral clustering is presented. First, a new grouping cue called wavelet edge is obtained in multi-scale space, which not only has the property of intensity and direction, but also has the property of singularity measured by lipschitz exponent. Thus grouping cues carry the information of both areas and edges. Secondly, a global grouping approach is presented by use of spectral clustering that has no limitation of neighborhood. Furthermore, the Gestalt principles are used to optimize the grouping result by adding penalty item in iterative process. The experiments show that this algorithm will be effective on condition that the singularities of the edges that belong to one object are equal or close, especially for partially occluded object.