An adaptive thresholding method for binarization of blueprint Images

Citation
Ms. Zhao et al., An adaptive thresholding method for binarization of blueprint Images, PATT REC L, 21(10), 2000, pp. 927-943
Citations number
8
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN RECOGNITION LETTERS
ISSN journal
01678655 → ACNP
Volume
21
Issue
10
Year of publication
2000
Pages
927 - 943
Database
ISI
SICI code
0167-8655(200009)21:10<927:AATMFB>2.0.ZU;2-O
Abstract
This paper proposes an adaptive logical thresholding method for the binariz ation of blueprint images. The new method exploits the geometric features o f blueprint images. This is implemented by utilizing a robust windows opera tion, which is based on the assumption that the objects have "c" shape in a small area. We make use of multiple window sizes in the windows operation. This not only reduces computation time but also separates effectively thin lines ti-om wide lines. Our method can automatically determine the thresho ld of images. Experiments show that our method is effective for blueprint i mages and achieves good results over a wide range of images. (C) 2000 Elsev ier Science B.V. All rights reserved.