Please use this identifier to cite or link to this item: https://doi.org/10.1142/S0218001402001551
Title: Segmentation of handwritten Chinese characters from destination addresses of mail pieces
Authors: Lu, Y. 
Tan, C.L. 
Shi, P.
Zhang, K.
Keywords: Character segmentation
Detection and removal of reference lines
Document image processing
Handwritten Chinese character
Postal automation
Issue Date: 2002
Source: Lu, Y., Tan, C.L., Shi, P., Zhang, K. (2002). Segmentation of handwritten Chinese characters from destination addresses of mail pieces. International Journal of Pattern Recognition and Artificial Intelligence 16 (1) : 85-96. ScholarBank@NUS Repository. https://doi.org/10.1142/S0218001402001551
Abstract: In this paper, we illustrate a method to segment handwritten Chinese characters from destination addresses of mail pieces. Fast Hough transform is utilized to detect the reference lines preprinted on the mail piece. In the segmentation, subassemblies of Chinese characters are merged based on the structural features of Chinese characters and the subassemblies' topological relations, viz. upper-lower, inside-outside and left-right relations. The width of subassemblies and the spacing between neighboring subassemblies in the whole image of the destination address are analyzed to guide the merging of the left-right subassemblies. Experimental results with real mail piece images show that the proposed approach has achieved a promising performance for segmenting handwritten Chinese characters.
Source Title: International Journal of Pattern Recognition and Artificial Intelligence
URI: http://scholarbank.nus.edu.sg/handle/10635/39320
ISSN: 02180014
DOI: 10.1142/S0218001402001551
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

8
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

7
checked on Dec 5, 2017

Page view(s)

70
checked on Dec 11, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.