Title :
A learning algorithm detecting the similar Chinese characters´ boundary based on unequal-contraction of dimension
Author :
Jinying, Chen ; Yijiang, Jin ; Shaoping, Ma
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Abstract :
In a recognition system of off-line handwritten Chinese characters, which has a proper recognition rate, improving the recognition rate of similar characters is the key to raising the whole recognition rate. K-L transformation, linear projection, and nonlinear projection are used to visualize the distribution of high-dimension Chinese character vectors. By making comparison experiments between very-similar and very-different Chinese characters, we summarize the distribution characteristic of the high-dimension similar Chinese characters. Utilizing the Mahalanobis distance to measure the similarity of characters and according to the results of statistical experiments, we present a learning algorithm to determine the similar Chinese characters´ boundary based on unequal-contraction of dimension
Keywords :
Karhunen-Loeve transforms; handwritten character recognition; learning (artificial intelligence); vectors; K-L transformation; Mahalanobis distance; distribution characteristic; handwritten Chinese characters; high-dimension Chinese character vectors; learning algorithm; linear projection; nonlinear projection; recognition rate; Character recognition; Computer science; Handwriting recognition; Intelligent systems; Laboratories; Visualization;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.862563
