Tuesday 21st of November 2017
 

Multiple Skew Estimation In Multilingual Handwritten Documents


D. S. Guru, M Ravikumar and S. Manjunath

In Indian scenario, most of the time the office documents such as forwarded notices and other documents are multilingual with multiple skews. This poses new challenges in the field of document image analysis. In this direction we are presenting a method of estimating the skew in handwritten multilingual documents. From a handwritten multilingual document image each word is segmented using morphological operations and connected component analysis. Skew of each word is estimated by fitting a minimum circumscribing ellipse. The orientation of each word is estimated and then words are clustered using adaptive k-means clustering to identify the multiple blocks present in the document and average orientation of each block is estimated. In order to corroborate the efficacy of the proposed model experimentation on our own dataset is carried out.

Keywords: Multilingual Handwritten Document; Multiple Skew; Connected Component Analysis; Adaptive Clustering

Download Full-Text


ABOUT THE AUTHORS

D. S. Guru
Department of Studies in Computer Science, University of Mysore, Mysore-570016, Karnataka, India

M Ravikumar
Department of Studies in Computer Science, University of Mysore, Mysore-570016, Karnataka, India

S. Manjunath
PG Department of Computer Science, JSS College of Arts Commerce and Science, Mysore-570025, Karnataka, India


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »