|Table of Contents|

[1] Lu Da**, Qian Yiping, Xie Mingpei, Pu Wei, et al. An Approach to Unsupervised Character ClassificationBased on Similarity Measure in Fuzzy Model* [J]. Journal of Southeast University (English Edition), 2002, 18 (4): 370-376. [doi:10.3969/j.issn.1003-7985.2002.04.017]
Copy

An Approach to Unsupervised Character ClassificationBased on Similarity Measure in Fuzzy Model*()
一种基于模糊模型相似测量的字符无监督分类法
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
18
Issue:
2002 4
Page:
370-376
Research Field:
Computer Science and Engineering
Publishing date:
2002-12-30

Info

Title:
An Approach to Unsupervised Character ClassificationBased on Similarity Measure in Fuzzy Model*
一种基于模糊模型相似测量的字符无监督分类法
Author(s):
Lu Da1** Qian Yiping1 Xie Mingpei2 Pu Wei1
1Department of Physics, Changshu College, Changshu 215500, China
2Department of Computer Science, Fudan University, Shanghai 200433, China
卢达1 钱忆平1 谢铭培2 浦炜1
1常熟高等专科学校物理系, 常熟 215500; 2复旦大学计算机科学系, 上海 200433
Keywords:
fuzzy model weighted fuzzy similarity measure unsupervised character classification matching algorithm classification hierarchy
模糊模型 加权模糊相似测量 字符无监督分类 匹配算法 分级归类
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2002.04.017
Abstract:
This paper presents a fuzzy logic approach to efficiently perform unsupervised character classification for improvement in robustness, correctness and speed of a character recognition system. The characters are first split into eight typographical categories. The classification scheme uses pattern matching to classify the characters in each category into a set of fuzzy prototypes based on a nonlinear weighted similarity function. The fuzzy unsupervised character classification, which is natural in the representation of prototypes for character matching, is developed and a weighted fuzzy similarity measure is explored.The characteristics of the fuzzy model are discussed and used in speeding up the classification process. After classification, the character recognition which is simply applied on a smaller set of the fuzzy prototypes, becomes much easier and less time-consuming.
提出了一种能有效完成对无监督字符分类的模糊逻辑方法, 以提高字符识别系统的速度, 正确性和鲁棒性.字符首先被分为8种印刷结构类, 然后采用模式匹配方法将各类字符分别转换成基于一非线性加权相似函数的模糊样板集合.模糊无监督字符的分类是字符匹配的一种自然范例并发展了加权模糊相似测量的研究.本文讨论了该模糊模型的特性并用以加快字符分类处理, 经过字符分类, 在字符识别时由于只需针对较小的模糊样板集合而变得容易和快速.

References:

[1] Akiyama T, Hagita N. Automated entry system for printed documents[J]. Pattern Recognition, 1990, 23(11):1141-1154.
[2] Schurmann J, Bartneck N, et al. Document analysis-from pixels to contents[A]. In: Proceedings of IEEE[C]. 1992, 80(7): 1101-1119.
[3] Srihari S N. Computer text recognition and error correction[M]. Silver Spring, MD, USA:Computer Science Press, 1985.
[4] Impedovo S, Ottaviano L. Optical character recognition — a survey[J]. Pattern Recognition, 1991, 5(1, 2):1-24.
[5] Bokser M. Omni document technologies[A]. In: Proceeding of the IEEE[C]. 1992, 80(7):1066-1078.
[6] Lu Da, McCane B, Pu Wei. Character preclassification based on fuzzy typographical analysis[A]. In: Proceeding of the 6th International Conference on Document Analysis and Recognition[C]. Seattle, Washington, USA: IEEE Press, 2001. 74-78.
[7] Lu Da, Pu Wei, Xie Mingpei. Precise detection algorithm for locating the baseline of a text line[J]. Mini-Micro System, 2000, 21(7):726-728.(in Chinese)
[8] Prakash M, Murty M. Growing subspace pattern recognition methods and their neural-network models[J]. IEEE Transactions on Neural Networks, 1997, 8(1): 161-168.
[9] Lu Da, Xie Mingpei. A segmentation method of topographic approach for merged character images based on skeletonization[J]. Journal of Chinese Information Processing, 1999, 13(2): 40-45.(in Chinese)

Memo

Memo:
* The project supported by the China Scholarship Council Foundation(99832097)and the National Science of Jiangsu Education Commission(99KGB140009).
** Born in 1947, male, associate professor.
Last Update: 2002-12-20