2-D Shape Decomposition into Overlapping Parts
We propose a method to generate component-based shape descriptions by the application of a perceptual grouping approach known as tensor voting. Based on previously described results on the generation of region, curve and junction saliencies and motivated by psychological findings about shape perception, we introduce extensions by a voting between junctions to create amodal completions, by a labeling of the junctions according to a catalog of junction types, and by a traversal algorithm to collect the local information into globally consistent part decompositions. In contrast to commonly used partitioning schemes, our method is able to create layered representations of overlapping parts. We consider this a major advantage together with the use of local operations and low computational costs whereas other approaches are based on highly iterative processes.
KeywordsInput Image Polarity Vector Shape Description Perceptual Grouping Illusory Contour
Unable to display preview. Download preview PDF.
- [Blu67]H. Blum. A transformation for extracting new descriptors of shape. In W. Wathen-Dunn, editor, Models for the Perception of Speech and Visual Form, pages 362–380, Cambride, MA, 1967. MIT Press.Google Scholar
- [Kof35]K. Koffka. Principles of Gestalt psychology. Harcourt Brace, New York, 1935.Google Scholar
- [LL99]L. Latecki and R. Lakmper. Conexity rule for shape decomposition based on discrete contour evolution. CVIU, 73:441–454, 1999.Google Scholar
- [Pen87]A. Pentland. Recognition by parts. In Proc. IEEE Int. Conf. on Computer Vision, pages 612–620, London, 1987.Google Scholar
- [Pet56]G. Petter. Nuove ricerche sperimentali sulla totalizzazione percettiva [New experimental research on perceptual totalization]. Rivista di Psicologia, 50:213–227, 1956.Google Scholar
- [Rom93]H. Rom. Part decomposition and shape description. Technical Report IRIS-93-319, Univ. of Southern California, 1993.Google Scholar
- [Sau99]E. Saund. Perceptual organization of occluding contours of opaque surfaces. CVIU, 76:70–82, 1999.Google Scholar
- [SR94]R. Shapley and D. Ringach. Similar mechanisms for illusory contours and amodal completion. Invest. Ophtalm. ℰ Visual Sci., 35:1089, 1994.Google Scholar
- [SU98]A. Sha‘ashua and S. Ullman. Structural saliency: the detection of globally salient structures using a locally connected network. In Proc. Int. Conf. on Computer Vision, pages 312–327, 1998.Google Scholar
- [TSK97]H. Tek, P. Stoll, and B. Kimia. Shocks from images: Propagation of orientation elements. In CVPR, pages 839–845, 1997.Google Scholar
- [UKD+99]W. Uttal, R. Kakarala, S. Dayanand, T. Shepherd, J. Kalki, C. Lunskis, and N. Liu. Computational Modeling of Vision. Dekker, New York, 1999.Google Scholar