New method for jiaguwen image segmentation based on MRF and fuzzy clustering

JiaGuWen image segmentation is a challenge because of their illegible writing, serious noises and broken strokes. We propose a new segmentation method based on MRF and fuzzy clustering because of their good performance in image segmentation. The segmentation is based on a new random function conside...

Full description

Saved in:
Bibliographic Details
Published in2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) pp. 204 - 208
Main Authors Xiaoju, He, Zhiwu, Liao
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2017
Subjects
Clustering algorithms
Fuzzy clustering
Image segmentation
JiaGuWen image
Markov random
Markov random fields
Mathematical model
Pattern analysis
Security
Online AccessGet full text

Cover

More Information
Summary:JiaGuWen image segmentation is a challenge because of their illegible writing, serious noises and broken strokes. We propose a new segmentation method based on MRF and fuzzy clustering because of their good performance in image segmentation. The segmentation is based on a new random function considering both ambiguity and spatial relationship of image pieds simultaneously. The New adaptive balance coefficient is computed according to the gray level of the considering pixel and the mean, standard deviation of the neighbor. The final value of the new random function is searching by iteration. The experiments show that the new method has good performance for JiaGuWen image segmentation.
DOI:10.1109/SPAC.2017.8304276