Multifont printed Chinese character recognition system

1991 ◽  
Author(s):  
Pak-kwong Wong
Keyword(s):  
Character Recognition ◽  
Chinese Character ◽  
Recognition System ◽  
Chinese Character Recognition

Research of Off-Line Handwritten Chinese Character Recognition System Based on Feedback Structure

2012 ◽  
Vol 433-440 ◽  
pp. 7046-7053 ◽  
Author(s):  
Jian Ping Wang ◽  
Hui Ying Cao ◽  
Jin Ling Wang ◽  
Cheng Hui Zhu
Keyword(s):  
Character Recognition ◽  
Chinese Character ◽  
Recognition System ◽  
Regulation Mechanism ◽  
Operating Mechanism ◽  
Chinese Character Recognition ◽  
Handwritten Chinese Character Recognition ◽  
Feedback Structure ◽  
The Operating Mechanism ◽  
Evaluation Mechanism

An offline handwritten Chinese character recognition system based on feedback structure is constructed. By imitating the feedback behavior in the human brain, the operating mechanism is presented. By comparing the recognition result character with the input character, four kinds of general characters recognition errors are defined. According to the analysis of the general errors, the evaluation mechanism and regulation mechanism of closed-loop based on feedback is made. Based on the trend of errors, the recognition process is adjusted to make the whole operating mechanism more reasonable. The results of simulation show that this system is efficient.

A Reliability Design Methodology for Chinese Character Recognition

1998 ◽  
Vol 12 (02) ◽  
pp. 159-172 ◽  
Author(s):  
Y. S. Huang ◽  
K. Liu ◽  
C. Y. Suen ◽  
Y. Y. Tang
Keyword(s):  
Character Recognition ◽  
Chinese Character ◽  
Nearest Neighbor ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Recognition System ◽  
Reliability Design ◽  
Chinese Character Recognition ◽  
Nearest Neighbor Rule ◽  
Pattern Distribution

This paper proposes a novel method which enables a Chinese character recognition system to obtain reliable recognition. In this method, two thresholds, i.e. class region thresholdRk and disambiguity thresholdAk, are used by each Chinese character k when the classifier is designed based on the nearest neighbor rule, where Rk defines the pattern distribution region of character k, and Ak prevents the samples not belonging to character k from being ambiguously recognized as character k. A novel algorithm to derive the appropriate thresholds Ak and Rk is developed so that a better recognition reliability can be obtained through iterative learning. Experiments performed on the ITRI printed Chinese character database have achieved highly reliable recognition performance (such as 0.999 reliability with a 95.14% recognition rate), which shows the feasibility and effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document