Structural Run Based Feature Vector to Classify Printed Tamil Characters Using Neural Network

Abstract

Feature Extraction plays most crucial and important role in character recognition. The selection of stable and representative set of features is the main problem in pattern recognition. Because of font characteristics and style variation of machine printed Tamil characters, feature extraction remains a problem. Feature extraction involves reducing the amount of resources required to describe a set of data. In this paper, new method has been proposed to extract structural features from Machine printed Tamil characters using horizontal and vertical projections. Based on the structural properties of upper and lower modifiers, characters are divided into various categories and features are extracted accordingly. The extracted features from the real life degraded documents are classified to identify the characters. The system has been tested with printed Tamil characters and achieves 99.67% character recognition accuracy on average. Experimental results show that structure and category of the characters are identified by the proposed method for the regular characters of various sizes.

Authors and Affiliations

Karthigaiselvi. M, Kathirvalavakumar. T

Keywords

Related Articles

Use of Electronic Resources by M.Sc. Chemistry Students at Arts Science and Commerce College Chopda Dist-Jalgaon

The libraries and information services has been changed due to the development of information and communication technology. Electronics resources role is very important as information repositories are use of information...

Type III Radio Burst Emission and Sunspot Cycles

The paper considers the formation of type III solar radio bursts caused by plasma excitation and to examine the sunspot cycle length with an emphasis on the intervals between consecutive maxima and minima. From an elabor...

Cross-Border Voluntary Network for Disaster Prevention (Hungary-Slovakia)

Košice (Slovakia) and Miskolc (Hungary) are connected not only by historical, social and cultural roots, but also by common threats (river Hernád, industrial vulnerability, transport of dangerous goods). The European Uni...

Omnidirectional Band Gaps in Heterostructure Materials Composed of Meta-materials and Magnetic Materials

Enlarged band gap in photonic heterostructure (PC1/PC2) composed of metamaterials and magnetic materials is studied using simple transfer matrix method. As we know that the meta-materials have the unusual electromagnetic...

Solar Water Pump

Solar powered water pumping systems have become the interest of many people in the recent years. Acknowledging that nature has provided a bounty of energy which can be converted into electrical energy has created innovat...

Download PDF file
  • EP ID EP391532
  • DOI 10.9790/9622-0707014463.
  • Views 130
  • Downloads 0

How To Cite

Karthigaiselvi. M, Kathirvalavakumar. T (2017). Structural Run Based Feature Vector to Classify Printed Tamil Characters Using Neural Network. International Journal of engineering Research and Applications, 7(7), 44-63. https://europub.co.uk/articles/-A-391532