A Novel Method on Malayalam Handwritten Character Recognition
Anish S1, Preeja V2
1Anish S, M.Tech Student, Department of Computer Science and Engineering, Sree Chitra Thirunal College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
2Preeja V, Assistant Professor, Department of Computer Science and Engineering, Sree Chitra Thirunal College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
Manuscript received on 15 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 234-237 | Volume-4 Issue-6, August 2015 | Retrieval Number: F4224084615/15©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: Handwritten Character Recognition (HCR) is one of the most challenging and active areas of research in the field of pattern recognition. It has a wide range of applications like preservation of documents into digital form, managing rare books etc. HCR is a difficult process due to the variants of handwriting styles of different individuals. Thus the success rate of any HCR system greatly depends upon the language that these systems are working on, and the amount of character sets in each language. Malayalam, a south Indian language and official language in the state of Kerala has a rich amount of character sets. Recognizing all those characters is a difficult task. In any types of character recognition systems, recognition rates play a vital role in the overall efficiency of the system. Several researches are going on this field to improve recognition rates. This paper deals with texture extraction model for character recognition process. In this model co-occurrence matrix and Euclidean distance are used to recognize the characters in an image
Keywords: Binarization, Co-Occurrence Matrix, Euclidean Distance, Segmentation
Scope of the Article: Pattern Recognition