Hierarchical Image Segmentation—Part I: Detection of Regular Curves in a Vector Graph
International Journal of Computer Vision
Perceptual organization based computational model for robust segmentation of moving objects
Computer Vision and Image Understanding
Shape Representation and Classification Using the Poisson Equation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian inference for layer representation with mixed Markov random field
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Simultaneous segmentation and figure/ground organization using angular embedding
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Shape representation and classification using the Poisson equation
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Figure/Ground assignment in natural images
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Accurate Junction Detection and Characterization in Natural Images
International Journal of Computer Vision
Hi-index | 0.00 |
A common factor in all illusory contour figures is the perception of a surface occluding part of a background. In our previous work we have shown that by detecting junctions and assigning a proper set of hypothesis at each junction, we could diffuse this information and obtain surface reconstructions where the surface boundaries represented illusory contours. Amodal completions emerge at the overlapping surfaces. We here address the problem of selecting the best image organization (set of hypothesis). We propose two optimization criteria, one based on a coherence measure between pairs of junctions (correlation between the diffusion of each pair) and another one based on an entropy measure (sharpness of the reconstruction). We show their similarity and a statistical physics approach to select the best organization. The experiments suggest that despite the large number of possible organizations our approach may take a few steps to select the best organization (starting from random organizations).