Algorithm for segmentation of documents based on texture features


The ascending approach to segmentation of scanned documents in the area of background, text, and photographs is considered. In the first stage, the image is divided into blocks. For each block, a series of texture features is calculated. On the basis of these features, the type of the block is determined. Various positions and sizes of blocks, 26 texture features, and 4 algorithms of classification of blocks were considered. In the second stage, the type of block was corrected on the basis of the analysis of neighboring regions. For estimating the results, the error matrix and the ICDAR 2007 criterion are used.

DOI: 10.1134/S1054661813010136

Extracted Key Phrases

8 Figures and Tables

Cite this paper

@article{Vilkin2013AlgorithmFS, title={Algorithm for segmentation of documents based on texture features}, author={Aleksey Vil’kin and Ilia V. Safonov and Maria A. Egorova}, journal={Pattern Recognition and Image Analysis}, year={2013}, volume={23}, pages={153-159} }