Andreev, Andrey and Kirov, Nikolay (2008) Text Search in Document Images Based on Hausdorff Distance Measures. In: Proceedings of the International conference on computer systems and technologies and Workshop for PhD students in computing CompSysTech'08, Gabrovo, Bulgaria, 12-13 June. Association for Computing Machinery, Sofia, II.5-1. ISBN 9789549641523
![[thumbnail of CompSysTech.pdf]](https://eprints.nbu.bg/style/images/fileicons/application_pdf.png) Preview |
PDF
CompSysTech.pdf Available under License Creative Commons Public Domain Dedication. 2MB |
Abstract
The Hausdorff type distances between the sets of points on the plane are the commonly used similarity measures for binary images. In this work we present several such measures in a unified manner and introduce a new, naturally arisen variant of Hausdorff distance. The matching performance of all similarity measures is compared by computer experiments, using real word images from a scanned book.
| Item Type: | Book Section |
|---|---|
| Subjects: | Computer science and information technologies > Computer science. Computer programming Mathematics |
| ID Code: | 210 |
| Deposited By: | Доц. Николай Киров |
| Deposited On: | 08 Sep 2008 11:04 |
| Last Modified: | 21 Aug 2012 12:35 |
Repository Staff Only: item control page