DocumentCode :
3060078
Title :
Character Segmentation of Handwritten Bangla Text by Vertex Characterization of Isothetic Covers
Author :
Bag, Soumen ; Bhowmick, Partha ; Harit, Gaurav ; Biswas, Arindam
Author_Institution :
Comput. Sc. & Eng. Dept., IIT Kharagpur, Kharagpur, India
fYear :
2011
fDate :
15-17 Dec. 2011
Firstpage :
21
Lastpage :
24
Abstract :
Segmentation of cursive handwriting is one of the most challenging problems in the area of handwritten character recognition. In this paper, we propose a novel approach towards character segmentation in a handwritten document. It is based on the vertex characterization of outer isothetic polygonal covers so that each cover corresponds to a particular word or part of a word. The proposed method has the potential to segment skewed text without deskewing them. Experiment is done on several Bangla handwritings of different individuals. The average success rate is 96.04%. This method can be considered as a significant preprocessing step towards the development of a handwritten Bangla OCR system.
Keywords :
computational geometry; document image processing; handwriting recognition; handwritten character recognition; image segmentation; natural language processing; optical character recognition; text analysis; cursive handwriting segmentation; handwritten Bangla OCR system; handwritten Bangla text character segmentation; handwritten document; outer isothetic polygonal covers; vertex characterization; Accuracy; Character recognition; Computers; Feature extraction; Image segmentation; Optical character recognition software; Reservoirs; Bangla handwriting; Character segmentation; Isothetic cover; OCR;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2011 Third National Conference on
Conference_Location :
Hubli, Karnataka
Print_ISBN :
978-1-4577-2102-1
Type :
conf
DOI :
10.1109/NCVPRIPG.2011.12
Filename :
6132991
Link To Document :
بازگشت