Please use this identifier to cite or link to this item:
Title: Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images
Contributor(s): Leedham, Graham  (author); Yan, Chen (author); Takru, Kalyan (author); Tan, Joie Hadi Nata (author); Mian, Li (author)
Publication Date: 2003
DOI: 10.1109/ICDAR.2003.1227784
Handle Link:
Abstract: A number of techniques have previously been proposed for effective thresholding of document images. In this paper two new thresholding techniques are proposed and compared against some existing algorithms. The algorithms were evaluated on four types of difficult document images where considerable background noise or variation in contrast and illumination exists. The quality of the thresholding was assessed using the Precision and Recall analysis of the resultant words in the foreground.The conclusion is that no single algorithm works well for all types of image but some work better than others for particular types of images suggesting that improved performance can be obtained by automatic selection or combination of appropriate algorithm(s) for the type of document image under investigation.
Publication Type: Conference Publication
Conference Details: ICDAR 2003: 7th International Conference of Document Analysis and Recognition, Edinburgh, Scotland, 3rd - 6th August, 2003
Source of Publication: Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), v.2, p. 859-863
Publisher: IEEE: Institute of Electrical and Electronics Engineers Systems Computer Society
Place of Publication: United States of America
Field of Research (FOR): 080199 Artificial Intelligence and Image Processing not elsewhere classified
080104 Computer Vision
080106 Image Processing
Socio-Economic Objective (SEO): 890299 Computer Software and Services not elsewhere classified
810107 National Security
810199 Defence not elsewhere classified
Peer Reviewed: Yes
HERDC Category Description: E1 Refereed Scholarly Conference Publication
Other Links:
Statistics to Oct 2018: Visitors: 347
Views: 367
Downloads: 0
Appears in Collections:Conference Publication

Files in This Item:
2 files
File Description SizeFormat 
Show full item record


checked on Nov 30, 2018

Page view(s)

checked on May 3, 2019
Google Media

Google ScholarTM



Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.