An Efficient Kannada Document Segmentation Method using Projection Profiles

Urolagin, Siddhaling and Prema, KV and Ramya, S N and Reddy, Subba N V (2011) An Efficient Kannada Document Segmentation Method using Projection Profiles. In: International Conference on Advanced Computing, Networking and Security, December 16-18, 2011, Surathkal, India,.

[img] PDF
Ramya_S.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

The Kannada documents segmentation into individual lines, words and characters poses many challenges. The Kannada aksharas have a lot variation in widths and heights because they are formed by combination of glyphs of basic symbols. Moreover an akshara is composed of two or more disconnected components. In this research we have proposed an efficient Kannada document segmentation method using projection profile. The experiments are conducted on several scanned documents with different fonts and character segmentation rate of 99.2% and consonant conjunct segmentation rate of 92.73% on an average are observed

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Document image analysis, document segmentation, Kannada script.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 25 Feb 2016 08:53
Last Modified: 01 Mar 2016 14:38
URI: http://eprints.manipal.edu/id/eprint/145394

Actions (login required)

View Item View Item