Title :
Segmentation of Cursive Handwritten Words using Hypergraph
Author :
Lakshmi, P. Samrajya ; Hanmandlu, M. ; Swaroop, A.
Author_Institution :
N.I.T, Kurukshetra
Abstract :
Segmentation is a crucial step in the cursive script recognition process. A higher recognition rate is achieved if the characters of a word are correctly isolated. In this paper segmentation using hypergraph model is investigated. Hypergraph model treats an image as packets of pixels. By recombining these packets of different sizes a given image can be segmented with the guarantee that at least one of the combinations provides a correct segmentation
Keywords :
graph theory; handwritten character recognition; image segmentation; word processing; character segmentation; cursive handwritten words; cursive script recognition process; hypergraph model; word image; Bridges; Character recognition; Compaction; Handwriting recognition; Image databases; Image segmentation; Joining processes; Office automation; Pixel; Sorting;
Conference_Titel :
TENCON 2006. 2006 IEEE Region 10 Conference
Conference_Location :
Hong Kong
Print_ISBN :
1-4244-0548-3
Electronic_ISBN :
1-4244-0549-1
DOI :
10.1109/TENCON.2006.343710
