Title :
A Baseline Dependent Approach for Persian Handwritten Character Segmentation
Author :
Alaei, Alireza ; Nagabhushan, P. ; Pal, Umapada
Author_Institution :
Dept. of Studies in Comput. Sci., Univ. of Mysore, Mysore, India
Abstract :
In this paper, an efficient approach to segment Persian off-line handwritten text-line into characters is presented. The proposed algorithm first traces the baseline of the input text-line image and straightens it. Subsequently, it over-segments each word/subwords using features extracted from histogram analysis and then removes extra segmentation points using some baseline dependent as well as language dependent rules. We tested the proposed character segmentation scheme with 2 different datasets. On a test set of 899 Persian words/subwords created by us, 90.26% of the characters were segmented correctly. From another dataset of 200 handwritten Arabic word images we obtained 93.49% correct segmentation accuracy.
Keywords :
feature extraction; handwritten character recognition; image segmentation; natural languages; text analysis; Persian handwritten character segmentation; Persian offline handwritten text-line segmentation; baseline dependent approach; features extraction; handwritten Arabic word images; histogram analysis; input text-line image; Algorithm design and analysis; Equations; Feature extraction; Handwriting recognition; Image segmentation; Shape; Smoothing methods; Baseline alignment; Character segmentation; Persian handwritten character recognition; Projection analysis;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.487