DocumentCode :
3528599
Title :
From contours to characters segmentation of cursive handwritten words with neural assistance
Author :
Kurniawan, Fajri ; Rehman, Amjad ; Mohamad, Dzulkifli
Author_Institution :
Dept. of Comput. Graphics & Multimedia, Univ. Teknol. Malaysia, Skudai, Malaysia
fYear :
2009
fDate :
23-25 Nov. 2009
Firstpage :
1
Lastpage :
4
Abstract :
This paper presents a novel algorithm to resolve an open problem to correctly locating letter boundaries in off-line unconstrained cursive handwritten word images. The proposed algorithm is based on vertical contour analysis. Following preprocessing, during the course of pre-segmentation vertical contours are analyzed from right to left. Furthermore to improve accuracy of segmentation, trained ANN is employed to validate segment points. For fair analysis, experiments were performed on IAM benchmark database. Results obtained thus show that the proposed approach is capable to accurately locating the letter boundaries for unconstraint cursive handwritten words.
Keywords :
handwritten character recognition; image segmentation; learning (artificial intelligence); neural nets; IAM benchmark database; characters segmentation; neural assistance; off-line unconstrained cursive handwritten word images; presegmentation vertical contours; vertical contour analysis; Algorithm design and analysis; Artificial neural networks; Computer graphics; Feature extraction; Handwriting recognition; Image databases; Image resolution; Image segmentation; Neural networks; Performance analysis; character segmentation; contour analysis; cursive handwritten; neural network; off-line handwriting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME), 2009 International Conference on
Conference_Location :
Bandung
Print_ISBN :
978-1-4244-4999-6
Electronic_ISBN :
978-1-4244-5000-8
Type :
conf
DOI :
10.1109/ICICI-BME.2009.5417278
Filename :
5417278
Link To Document :
بازگشت