会议专题

Fast Correction for the Extraction Results of Printed Mathematical Formulas

Mathematical formulas extraction is a prerequisite for their recognition, which affects the performance of formula recognition system directly. There exist various kinds of errors within the outcome of formula extraction resulted from some factors. This paper proposes a fast correction algorithm for formula extraction results, which corrects the errors existing in the extraction results according to the formula symbols features and corresponding knowledge, guided by users intention. Experimental results show that the algorithm could modify the results of formula extraction efficiently, which enhances the practicality of the formula recognition system.

printed mathematical formula formula extraction distribution features correction

Xue-dong Tian Bei Chen Yu-xia Wu Hui Wang

College of Mathematics and Computer Science, Hebei University Baoding, Hebei, China Hebei key labora Computing Center, Hebei University Baoding, Hebei, China Baoding Senior Technical College Baoding, Hebei, China

国际会议

2010 International Conference on Information Security and Artificial Intelligence(2010年信息安全与人工智能国际会议 ISAI 2010)

成都

英文

705-708

2010-12-17(万方平台首次上网日期,不代表论文的发表时间)