Share Email Print

Proceedings Paper

Efficient implementation of local adaptive thresholding techniques using integral images
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Adaptive binarization is an important first step in many document analysis and OCR processes. This paper describes a fast adaptive binarization algorithm that yields the same quality of binarization as the Sauvola method,1 but runs in time close to that of global thresholding methods (like Otsu's method2), independent of the window size. The algorithm combines the statistical constraints of Sauvola's method with integral images.3 Testing on the UW-1 dataset demonstrates a 20-fold speedup compared to the original Sauvola algorithm.

Paper Details

Date Published: 28 January 2008
PDF: 6 pages
Proc. SPIE 6815, Document Recognition and Retrieval XV, 681510 (28 January 2008); doi: 10.1117/12.767755
Show Author Affiliations
Faisal Shafait, German Research Ctr. for Artificial Intelligence (Germany)
Daniel Keysers, German Research Ctr. for Artificial Intelligence (Germany)
Thomas M. Breuel, Technical Univ. of Kaiserslautern (Germany)

Published in SPIE Proceedings Vol. 6815:
Document Recognition and Retrieval XV
Berrin A. Yanikoglu; Kathrin Berkner, Editor(s)

© SPIE. Terms of Use
Back to Top