A Novel Weighted SVM Classifier Based on SCA for Handwritten Marathi Character Recognition

Abstract

The research on handwritten optical character recognition (OCR) of Marathi script is very challenging due to the complex structural properties of the script that are not observed in most other scripts. This paper gives an OCR framework for handwritten Marathi document classification and recognition system. Due to the large variety of symbols the Marathi characters recognition poses great challenge and their proximity in appearance. The weighted one-against-rest support vector machines (WOAR-SVM) assume a noteworthy part to deal with vast feature measures which are utilized for the classification. Here, a new sine cosine algorithm is proposed for the identification of handwritten Marathi text. By utilizing different morphological operations the preprocessing is finished and the Marathi text is flexibly segmented in three levels; line segmentation, word segmentation and character segmentation with Modified Pihu method. Various features like statistical, global transformation, geometrical and topological features are extracted from the preprocessed image by extraction techniques. Result obtained show that various features with WOAR-SVM classifier perform the best by yielding high accuracy as 95.14%.

Keywords:

• Optical character recognition
• WOAR-SVM
• Sine cosine algorithm
• Modified Pihu method
• Global transformation

Additional information

Notes on contributors

Surendra P. Ramteke

Surendra P Ramteke received BE degree in electronics and telecommunication engineering from BN College of Engineering Pusad Dist. Yavatmal in 2002 and ME degree in digital electronics from Prof Ram Meghe Institute of Technology & Research, Badnera Amravati affiliated to Sant Gadge Baba Amravati University Amravati, Maharashtra in 2011. He is currently working as an assistant professor and pursuing PhD degree at the Department of Electronics & Telecommunication Engineering, SSBTs College of Engineering & Technology Bambhori Jalgaon, Maharashtra, affiliated to North Maharashtra University Jalgaon India. He is life Member of ISTE. His areas of interests include image processing and pattern recognition.

Ajay A. Gurjar

Ajay A Gurjar belongs to the Department of Electronics and Telecommunication, Sipna College of Engineering and Technology, Amravati Maharashtra, India. After having procured bachelor's degree in electronics & telecommunication in 1995, he completed his master's degree in the same subject in 2003. Presently, he is working as a professor and dean Academics in Sipna College of Engineering & Technology, Amravati. Email: [email protected]

Dhiraj S. Deshmukh

Dhiraj S Deshmukh received BE degree in mechanical engineering from YCCE (PTDC), Nagpur affiliated to RTM Nagpur University, Nagpur and MTech degree in (HPE) from VRCE, Nagpur presently NIT, Nagpur. He pursued PhD in mechanical engineering from RTM Nagpur University, Nagpur in 2012. He is presently working as associate professor in mechanical engineering at G H Raisoni College of Engineering, Nagpur, Maharashtra, India. He has published 78 research papers in international journals, 17 research papers in international conference. His research interests includes heat power engineering. Email: [email protected]