Title
Identification of unreliable segments to improve skeletonization of handwriting images
Abstract
An unavoidable problem of most existing skeletonization algorithms for handwriting images is the production of undesired artifacts or pattern distortions. This paper presents a method of identifying these unreliable segments to improve the skeletons of handwriting images. In this method, a novel feature called iteration time is exploited, by which each unreliable segment can be treated as a set of points with exceptional iteration times. First, the iteration time of each skeleton point is calculated, and an undirected graph is built from the skeleton whose edges are weighted by defining a distance measurement between each pair of connected nodes based on iteration time. Then the set of unreliable segments is achieved by a graph clustering algorithm with an effective clustering quality function. Finally, the probability of two jointed reliable segments belonging to a continuous pair is estimated by a best-matched method, and a cubic B-spline interpolation is applied to reconstruct unreliable parts of the skeleton. Experimental results show that the proposed method can detect unreliable segments effectively and produce a skeleton that is closer to the original writing trajectory.
Year
DOI
Venue
2011
10.1007/s10044-009-0166-x
Pattern Anal. Appl.
Keywords
Field
DocType
exceptional iteration time,handwritten recognitionthinning algorithmskeletoniterative algorithmgraph clustering,iteration time,effective clustering quality function,skeleton point,unreliable segment,handwriting image,best-matched method,unreliable part,continuous pair,graph clustering,spline interpolation
Distance measurement,Handwriting,Pattern recognition,Iterative method,Interpolation,Skeletonization,Artificial intelligence,Cluster analysis,Clustering coefficient,Trajectory,Mathematics,Machine learning
Journal
Volume
Issue
ISSN
14
1
1433-755X
Citations 
PageRank 
References 
2
0.36
21
Authors
4
Name
Order
Citations
PageRank
Zhewen Su1101.51
Zhongsheng Cao2323.64
Yuanzhen Wang38611.78
Xiaoqiong Zhen420.69