DocumentCode :
442177
Title :
Research on optical formulas extraction
Author :
Tian, Xue-dong ; Sun, Wei-Zhong ; Ha, Ming-Hu
Author_Institution :
Coll. of Phys. Sci. & Technol., Hebei Univ., Baoding, China
Volume :
8
fYear :
2005
fDate :
18-21 Aug. 2005
Firstpage :
4886
Abstract :
Automatic recognition and reconstruction of formulas are key parts in an OCR (optical character recognition) system. Mathematical formula extraction is the first step in this technique. Little has been done in this area. Some research was focused on mathematical formulas in printed documents. An approach containing both the MSE feature of CCXs and heuristic rules for mathematical formula extraction is proposed. The MSF feature of the CCXs based approach is used to extract isolated formulas from printed documents and some heuristic rules are used to extract the embedded formulas from image blocks. The experiments indicate that a combination of the two methods can obtain favorable results.
Keywords :
feature extraction; optical character recognition; CCX; MSE feature; OCR system; automatic formula recognition; automatic formula reconstruction; heuristic rules; optical characters recognition; optical mathematical formula extraction; Character recognition; Data mining; Educational institutions; Image reconstruction; Image storage; Internet; Optical character recognition software; Physics; Software libraries; Sun; MSE feature; OCR; heuristic rule; optical formula extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
Type :
conf
DOI :
10.1109/ICMLC.2005.1527803
Filename :
1527803
Link To Document :
بازگشت