Full Text:   <3292>

CLC number: TP391.4

On-line Access: 2024-08-27

Received: 2023-10-17

Revision Accepted: 2024-05-08

Crosschecked: 0000-00-00

Cited: 0

Clicked: 6570

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE A 2004 Vol.5 No.11 P.1392-1397

http://doi.org/10.1631/jzus.2004.1392


An approach to offline handwritten Chinese character recognition based on segment evaluation of adaptive duration


Author(s):  LI Guo-hong, SHI Peng-fei

Affiliation(s):  Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, China

Corresponding email(s):   lgh0929@sjtu.edu.cn

Key Words:  Handwritten Chinese character, Segmentation boundary, Segment, Duration


Share this article to: More

LI Guo-hong, SHI Peng-fei. An approach to offline handwritten Chinese character recognition based on segment evaluation of adaptive duration[J]. Journal of Zhejiang University Science A, 2004, 5(11): 1392-1397.

@article{title="An approach to offline handwritten Chinese character recognition based on segment evaluation of adaptive duration",
author="LI Guo-hong, SHI Peng-fei",
journal="Journal of Zhejiang University Science A",
volume="5",
number="11",
pages="1392-1397",
year="2004",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.2004.1392"
}

%0 Journal Article
%T An approach to offline handwritten Chinese character recognition based on segment evaluation of adaptive duration
%A LI Guo-hong
%A SHI Peng-fei
%J Journal of Zhejiang University SCIENCE A
%V 5
%N 11
%P 1392-1397
%@ 1869-1951
%D 2004
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.2004.1392

TY - JOUR
T1 - An approach to offline handwritten Chinese character recognition based on segment evaluation of adaptive duration
A1 - LI Guo-hong
A1 - SHI Peng-fei
J0 - Journal of Zhejiang University Science A
VL - 5
IS - 11
SP - 1392
EP - 1397
%@ 1869-1951
Y1 - 2004
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.2004.1392


Abstract: 
This paper presents a methodology for off-line handwritten Chinese character recognition based on mergence of consecutive segments of adaptive duration. The handwritten Chinese character string is partitioned into a sequence of consecutive segments, which are combined to implement dissimilarity evaluation within a sliding window whose durations are determined adaptively by the integration of shapes and context of evaluations. The average stroke width is estimated for the handwritten Chinese character string, and a set of candidate character segmentation boundaries is found by using the integration of pixel and stroke features. The final decisions on segmentation and recognition are made under minimal arithmetical mean dissimilarities. Experiments proved that the proposed approach of adaptive duration outperforms the method of fixed duration, and is very effective for the recognition of overlapped, broken, touched, loosely configured Chinese characters.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1] Favata, J.T., 2001. Offline general handwritten word recognition using an approximate BEAM matching algorithm. IEEE Trans. on Pattern Recognition and Machine Intelligence, 23(9):1009-1021.

[2] Kahan, S., Pavlidis, T., Baird, H.S., 1987. On the recognition of printed characters of any fonts and sizes. IEEE Trans. on Pattern Recognition and Machine Intelligence, 9(2):274-288.

[3] Kim, G., Govindaraju, V., 1997. A lexicon driven approach to handwritten word recognition for real-time applications. IEEE Trans. on Pattern Recognition and Machine Intelligence, 19(4):366-379.

[4] Lee, S.W., Lee, D.J., 1996. A new methodology for gray-scale character segmentation and recognition. IEEE Trans. on Pattern Recognition and Machine Intelligence, 18(10):1045-1050.

[5] Liang, S., Shridhar, M., Ahmadi, M., 1994. Segmentation of touching characters in printed document recognition. Pattern Recognition, 27(6):825-840.

[6] Nafiz, A., Fatos, T.Y., 2002. Optical character recognition for cursive handwriting. IEEE Trans. on Pattern Recognition and Machine Intelligence, 24(6):801-813.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE