Loading...
A fast and efficient method for document segmentation for OCR
Author(s)
Kruatrachue, Boontee
Suthaphan, Phisetphong
Date Issued
December 1, 2001
Type
Conference Paper
Abstract
This paper describes fast and efficient method for page segmentation of document containing nonrectangular block. The presented method is based on mixed top-down and bottom-up approach to document analysis. The segmentation is based on block of column (paragraph) extracting by a modified edge following algorithm. Instead of a pixel, a window of 32 by 32 pixel is used in the algorithm so that a paragraph can be extracted instead of a character. The document is scanned at 300 dpi and it is possible to extract more than one column into a block. Then, characters in the block are extracted using edge following algorithm and their boundaries are used to detect multicolumn cases (bottom-up). Since the block extraction only scans through border pixels of paragraphs and characters need to be extracted in the OCR process, this algorithm is faster with fewer overheads than algorithms that need to access all pixel of a document.
Citation
IEEE Region 10 International Conference on Electrical and Electronic Technology, 381-383, 2001
Subjects