Segmentation of Text and Graphics from Document Images

Abstract

Text, graphics and half-tones are the major constituents of any document page. While half-tone can be characterised by its inherent intensity variation, text and graphics share common characteristics except difference in spatial distri- bution. The success of document image analysis systems depends on the proper segmentation of text and graphics as text is further subdivided into other classes such as heading, table and math-zones. Segmentation of graphics is essential for better OCR performance and vectorization in computer vision applications. Graphics segmentation from text is particularly difficult in the context of graphics made of small components (dashed or dotted lines etc.) which have many features similar to texts.Here we propose a robust technique for segmenting all sorts of graphics and texts in any orientation from document pages.

An adaptive over-split and merge algorithm for page segmentation

“…(Wahl et al, 1982) and more recently published, e.g. (Chen and Ding, 2003;Chowdhury et al, 2007;O'Gorman, 1993), algorithms. They classify small parts of the image (pixels, groups of pixels, or connected components), and gather those of the same type together to form regions.…”

Text and Non-text Segmentation and Classification from Document Images

“…Thus, document layout analysis is very important as it allows automatic classification based on total content rather than just a few keywords Document layout analysis systems separate text and non-text regions and much research has been conducted in this area [ 1] - [27].…”

Local Similarity based Document Layout Analysis using Improved ARLSA

“…The bottom-up approach are both the oldest [1], [2] and more recently published [3]. They classify components from small zone and make group with them.…”