A New Binarization Algorithm by Using the local Thresholding and Clustering Algorithm for the Document Image

In this paper, we proposed the new binarization algorithm that gives the improved image for the document with the severe brightness difference. This algorithm utilized the local threshold values by the Sauvola's algorithm and FCM clustering algorithm. We perform the thresholding by using the ce...

Full description

Saved in:
Bibliographic Details
Published inInternational Information Institute (Tokyo). Information Vol. 18; no. 10; p. 4379
Main Authors Kwon, Young-Man, Chung, Dong Kun, Kim, Myung-Gwan
Format Journal Article
LanguageEnglish
Published Koganei International Information Institute 01.10.2015
Subjects
Algorithms
Brightness
Clustering
Clusters
Performance evaluation
Thresholds
Online AccessGet full text

Cover

More Information
Summary:In this paper, we proposed the new binarization algorithm that gives the improved image for the document with the severe brightness difference. This algorithm utilized the local threshold values by the Sauvola's algorithm and FCM clustering algorithm. We perform the thresholding by using the center of cluster for the local threshold values. As an experimental result for our proposed algorithm, we got the better binary images compared to the result of other algorithms. So we can conclude the proposed algorithm is superior to the other algorithms.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1343-4500
1344-8994