Design And Implementation of Special Symbol Recognition System using Support Vector Machine
Sanjay S. Gharde1, Vidya A. Nemade2, K. P. Adhiya3

1Sanjay S. Gharde, Department of Compter Engineering, SSBT’s COET, Jalgaon (Maharashtra), India.
2Vidya A. Nemade, Department of Compter Engineering, SSBT’s COET, Jalgaon (Maharashtra), India.
3K.P. Adhiya, Department of Compter Engineering, SSBT’s COET, Jalgaon (Maharashtra), India.
Manuscript received on 10 May 2013 | Revised Manuscript received on 18 May 2013 | Manuscript Published on 30 May 2013 | PP: 145-148 | Volume-2 Issue-6, May 2013 | Retrieval Number: F0820052613/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Recognition of printed mathematical symbols is a subject of growing interest to automatically convert scientific paper documents into electronic form. Several methods have been proposed for recognition of printed and handwritten symbols. Symbol recognition in mathematical expressions is also difficult because there is a large character set with a variety of font styles and font sizes. Generally, in many applications, it is necessary to copy the contents from some original documents which may be in PDF like format. While accessing the data from that document, if it encounters symbols it remains unread in the copied document. So it is very difficult to read the original document. In proposed work, Discrete Cosine Transform method is used to extract the features of the symbol and Support Vector Machine, which performs the classification task used as classifier. Support Vector Machine provides the high accuracy at the time of classification.
Keywords: Symbol Recognition, Discrete Cosine Transform, Support Vector Machine.

Scope of the Article: Pattern Recognition