Please use this identifier to cite or link to this item:
Title: Word grouping in imaged documents using voronoi tessellation
Authors: WANG ZHE
Keywords: Document image processing, Voronoi tessellation, Word grouping, Connected componet, Voronoi neighborhood, Area voronoi diagram
Issue Date: 30-Mar-2005
Citation: WANG ZHE (2005-03-30). Word grouping in imaged documents using voronoi tessellation. ScholarBank@NUS Repository.
Abstract: In this thesis, a Voronoi tessellation based method is presented for word grouping in imaged documents. Voronoi tessellation of image elements provides an intuitive and appealing definition of proximity, which has been suggested as an effective tool for the description of relations among the neighboring objects in a digital document image. The Voronoi tessellation generated from the input image enables us to obtain neighbor relations between connected components. Based on the neighbor relations, the task of word extraction becomes the problem of selecting appropriate Voronoi edges separating connected components in the same word and then merging those components. For this purpose, we define four characteristic features and we would rely on the features to examine each pair of neighboring connected components locally, and then judge whether we should perform character merging or not. The proposed method has been evaluated on a variety of document images. The experimental results show that it has achieved promising results with a high accuracy, and is robust to various fonts, styles, sizes, as well as different text arrangements.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
wangzhe-revised2.pdf1.35 MBAdobe PDF



Page view(s)

checked on Jan 27, 2019


checked on Jan 27, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.