Self-organizing maps for the skeletonization of sparse shapes
Authors:
- V. CherkasskyVCV. Cherkassky
- N. PapanikolopoulosNPN. Papanikolopoulos
- 1 January 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 11 (1) , 241-248
Abstract
This paper presents a method for computing the skeleton of planar shapes and objects which exhibit sparseness (lack of connectivity), within their image regions. Such sparseness in images may occur due to poor lighting conditions, incorrect thresholding or image subsampling. Furthermore, in document image analysis, sparse shapes are characteristic of texts faded due to aging and/or poor ink quality. Due to the lack of pixel level connectivity, conventional skeletonization techniques perform poorly on such (sparse) shapes. Given the pixel distribution for a shape, the proposed method involves an iterative evolution of a piecewise-linear approximation of the shape skeleton by using a minimum spanning tree-based self-organizing map (SOM). By constraining the SOM to lie on the edges of the Delaunay triangulation of the shape distribution, the adjacency relationships between regions in the shape are detected and used in the evolution of the skeleton. The SOM, on convergence, gives the final skeletal shape. The skeletonization is invariant to Euclidean transformations. The potential of the method is demonstrated on a variety of sparse shapes from different application domains.Keywords
This publication has 18 references indexed in Scilit:
- Faxed document image restoration using gray level representation2002
- Enhancing degraded document images via bitmap clustering and averaging2002
- Thinning approach for noisy digital patternsPattern Recognition, 1996
- Self-Organization as an Iterative Kernel Smoothing ProcessNeural Computation, 1995
- Hierarchic Voronoi skeletonsPattern Recognition, 1995
- Statistical analysis of self-organizationNeural Networks, 1995
- Topology representing networksNeural Networks, 1994
- Relative neighborhood graphs and their relativesProceedings of the IEEE, 1992
- Derivation of a class of training algorithmsIEEE Transactions on Neural Networks, 1990
- Variants of self-organizing mapsIEEE Transactions on Neural Networks, 1990