Chen, Yan

Leedham, Graham

2004

Global and local adaptive thresholding techniques have been shown effective on particular types of documents. None produces consistently good results on all types of documents. In this paper a novel method, called the multistage-approach, is presented and compared against some existing single-stage algorithms. The multistage approach recursively breaks down an image into sub-regions using quad-tree decomposition and extracts local features from each sub-region until an appropriate thresholding method can be applied to each sub-region. Quantitative analysis using word recall and on 300 degraded historical images obtained from the Library of Congress demonstrate the method is superior to any existing single methods.

Proceedings of the 17th International Conference on Pattern Recognition (ICPR'04), v.1, p. 445-449

0769521282

1051-4651

https://hdl.handle.net/1959.11/18020

Institute of Electrical and Electronics Engineers (IEEE)

The Multistage Approach to Information Extraction in Degraded Document Images

Conference Publication

Publication