Paper Info
Title
Local Segmentation of Touching Characters Using Contour Based Shape Decomposition
Abstract
We propose a contour based shape decomposition approach that provides local segmentation of touching characters. The shape contour is linearized into edge lets and edge lets are merged into boundary fragments. The connection cost between boundary fragments is obtained by considering local smoothness, connection length and a stroke-level property called the Same Stroke Rate. Samples of connections among boundary fragments are randomly generated and the one with the minimum global cost is selected to produce the final segmentation of the shape. To obtain a bipartite segmentation using this approach, we perform an iterative search for the parameters that finally yields two components on a shape. Experimental results on synthetic shape images and the LTP dataset show that this contour based shape decomposition technique is promising and it is effective for providing local segmentation of touching characters.
Year
DOI
Venue
2012
10.1109/DAS.2012.53
Document Analysis Systems
Keywords
Field
DocType
shape decomposition technique,local smoothness,local segmentation,synthetic shape image,final segmentation,bipartite segmentation,connection cost,shape decomposition,shape decomposition approach,boundary fragment,touching characters,shape contour,smoothness,accuracy,skeleton,image segmentation,segmentation,iterative methods,shape,handwriting recognition
Computer vision,Active shape model,Scale-space segmentation,Pattern recognition,Computer science,Iterative method,Segmentation,Bipartite graph,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Smoothness
Conference
Citations 
PageRank 
References 
2
0.38
8
Authors
5
Name
Order
Citations
PageRank
Le Kang13069.32
David Doermann24313312.70
Huaigu Cao334729.09
Rohit Prasad446539.06
Premkumar Natarajan587479.46