Title :
Chinese handwriting quality evaluation based on analysis of recognition confidence
Author :
Gao, Yan ; Jin, Lianwen ; Li, Nanxi
Author_Institution :
Sch. of Elec. & Info. Eng., South China Univ. of Technol., Guangzhou, China
Abstract :
Handwriting is one of the major activities in everybody´s life. In order to let people form good habit of writing, handwriting quality evaluation is an important and useful technology. In this paper, a method of Chinese handwriting quality evaluation is proposed based on analysis of online Chinese handwriting recognition confidence. For a given handwritten Chinese character, we firstly calculate the confidence level by the candidate distance obtained from the modified quadratic discriminant function (MQDF) classifier. Then the Chinese handwriting quality is evaluated according to different recognition confidence measurement levels. Experimental results show that the proposed method is reasonable and effective.
Keywords :
handwriting recognition; handwritten character recognition; image classification; natural language processing; Chinese handwriting quality evaluation; Chinese handwriting recognition confidence; modified quadratic discriminant function classifier; online Chinese handwriting recognition; Character recognition; Databases; Eigenvalues and eigenfunctions; Feature extraction; Handwriting recognition; Training; Writing; Character recognition; MQDF; confidence measurement; handwriting quality evaluation;
Conference_Titel :
Information and Automation (ICIA), 2011 IEEE International Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4577-0268-6
Electronic_ISBN :
978-1-4577-0269-3
DOI :
10.1109/ICINFA.2011.5948991
