BRAC University Institutional Repository

Skew angle detection of bangla script using radon transform

Show simple item record Habib, S. M. Murtoza Noor, Nawsher Ahamed Khan, Mumit 2010-10-28T04:20:59Z 2010-10-28T04:20:59Z 2006 2006
dc.description Includes bibliographical references (page 5).
dc.description.abstract Skew angle detection and correction an integral part of any OCR system. Without proper skew correction, the performance of an OCR will simply not be acceptable for most scanned images. We propose an innovative method for skew angle detection and correction for Bangla scripts using the Radon Transform. The basic idea is to identify the upper envelope by detecting the headline that accompanies most of the letters in the Bangla script, and then apply the Radon Transform to this upper envelope to get the skew angle. Once the angle is known, the correction is quite trivial to perform. While the current implementation handles only a single skew angle per text image, it can be extended to handle multiple skew angles by partitioning the document image. en_US
dc.description.statementofresponsibility S. M. Murtoza Habib
dc.description.statementofresponsibility Nawsher Ahamed Noor
dc.description.statementofresponsibility Mumit Khan
dc.format.extent 5 pages
dc.language.iso en en_US
dc.publisher BRAC University en_US
dc.subject Bangla language processing
dc.title Skew angle detection of bangla script using radon transform en_US
dc.type Technical report en_US
dc.contributor.department Center for Research on Bangla Language Processing (CRBLP), BRAC University

Files in this item

This item appears in the following Collection(s)

Show simple item record

Policy Guidelines

Search BRACU Repository

Advanced Search


My Account