Segmentation of Spontaneously Splitting Figures into Overlapping Layers

Authors:
Amin Massad;Bärbel Mertsching
Affiliations:
-;-
Venue:
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Year:
2001

Citing 8
Cited 1

A process-grammar for shape

Artificial Intelligence
Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space

International Journal of Computer Vision
Inferring global perceptual contours from local features

International Journal of Computer Vision - Special issue on computer vision research at the University of Southern California
Convexity rule for shape decomposition based on discrete contour evolution

Computer Vision and Image Understanding
Perceptual organization of occluding contours of opaque surfaces

Computer Vision and Image Understanding - Special issue on perceptual organization in computer vision
Computational Framework for Segmentation and Grouping

Computational Framework for Segmentation and Grouping
Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization

IEEE Transactions on Pattern Analysis and Machine Intelligence
2-D Shape Decomposition into Overlapping Parts

IWVF-4 Proceedings of the 4th International Workshop on Visual Form

A computational approach to illusory contour perception based on the tensor voting technique

CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a method to decompose binary 2-D shapes into layers of overlapping parts. The approach is based on a perceptual grouping framework known as tensor voting which has been introduced for the computation of region, curve and junction saliencies. Here, we discuss extensions for the creation of modal/amodal completions and for the extraction of overlapping parts augmented with depth assignments. Advantages of this approach are from a conceptual point of view the close relation to psychological findings about shape perception and regarding technical aspects a reduction of computational costs in comparison with other highly iterative methods.