Universiti Teknologi Malaysia Institutional Repository

Performance analysis of segmentation approach for cursive handwriting on benchmark database

Rehman, Amjad and Mohamad, Dzulkifli and Kurniawan, Fajri and Ilays, Mohammad (2009) Performance analysis of segmentation approach for cursive handwriting on benchmark database. In: 2009 IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2009. Institute of Electrical and Electronics Engineers, New York, 265 -270. ISBN 978-142443806-8

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/AICCSA.2009.5069335

Abstract

The purpose of this paper is to analyze improved performance of our segmentation algorithm on IAM benchmark database in comparison to others available in the literature from accuracy and complexity points of view. Segmentation is achieved by analyzing ligatures which are strong points for segmentation of cursive handwritten words. Following preprocessing, a new heuristic technique is employed to over-segment each word at potential segmentation points. Subsequently, a simple criterion is performed to come out with fine segmentation points based on character shape analysis. Finally, the fine segmentation points are fed to train neural network for validating segment points to enhance accuracy. Based on detailed analysis and comparison, it was observed that proposed approach increased the segmentation accuracy with minimum computational complexity.

Item Type:Book Section
Additional Information:7th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA-2009; Rabat; 10 May 2009 through 13 May 2009
Uncontrolled Keywords:benchmark database, handwritten words, heuristic techniques, performance analysis, segmentation accuracy, segmentation algorithms, shape analysis
Subjects:Q Science > QD Chemistry
Divisions:Chemical Engineering
ID Code:13043
Deposited By: Mrs Liza Porijo
Deposited On:13 Jul 2011 08:32
Last Modified:13 Jul 2011 08:32

Repository Staff Only: item control page