The study on the detection and recognition of the printed formula

Author

Li, Yonghua ; Wang, Kejun ; Guo, Qinchang ; Wu, Junfei

Author_Institution

Coll. of Autom., Harbin Eng. Univ., Harbin

fYear

2008

fDate

5-8 Aug. 2008

Firstpage

329

Lastpage

335

Abstract

At present, the widely applied OCR system has a high recognition for printed texts, however it doesn´t have a good recognition schema for formulas. In order to locate and recognize printed formulas accurately, this paper conducted researches according to the following several aspects: use Adaboost method to locate formulas automatically, image processing to obtain thinned formula area, moment method to revise formulas, domain method to segment formulas, template feature method to recognize characters, and two dimensional structural analysis based on character feature to recognize formulas. The method presented in this paper can achieve a good recognition.

Keywords

character recognition; feature extraction; image recognition; learning (artificial intelligence); method of moments; Adaboost method; OCR system; character recognition; moment method; printed formula recognition; printed texts; Automation; Character recognition; Educational institutions; Image processing; Image recognition; Image segmentation; Mechatronics; Moment methods; Optical character recognition software; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, 2008. ICMA 2008. IEEE International Conference on

Conference_Location

Takamatsu

Print_ISBN

978-1-4244-2631-7

Electronic_ISBN

978-1-4244-2632-4

Type

conf

DOI

10.1109/ICMA.2008.4798775

Filename

4798775