Universiti Teknologi Malaysia Institutional Repository

A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network

Khan, Amjad Rehman and Mohamad, Dzulkifli (2008) A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network. International Journal of Computer Science and Security, 2 (3). pp. 29-35. ISSN 1985-1553 (online)

[img]
Preview
PDF - Published Version
99Kb

Official URL: http://www.cscjournals.org/csc/manuscript/Journals...

Abstract

This paper presents a new, simple and fast approach for character segmentation of unconstrained handwritten words. The developed segmentation algorithm over-segments in some cases due to the inherent nature of the cursive words. However the over segmentation is minimum. To increase the efficiency of the algorithm an Artificial Neural Network is trained with significant amount of valid segmentation points for cursive words manually. Trained neural network extracts incorrect segmented points efficiently with high speed. For fair comparison benchmark database IAM is used. The experimental results are encouraging

Item Type:Article
Uncontrolled Keywords:image analysis, segmentation, neural network, preprocessing, pattern matching.
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Computer Science and Information System (Formerly known)
ID Code:9951
Deposited By: Siti Najwa Hanim Kamarulzaman
Deposited On:23 Jun 2010 09:30
Last Modified:18 May 2011 07:37

Repository Staff Only: item control page