An Improved Zone Based Hybrid Feature Extraction Model for Handwritten Alphabets Recognition using Euler Number
Om Prakash Sharma1, M. K. Ghose2, Krishna Bikram Shah3
1Om Prakash Sharma, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
2Dr. M. K. Ghose, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
3Krishna Bikram Shah, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
Manuscript received on April 11, 2012. | Revised Manuscript received on April 14, 2012. | Manuscript published on May 05, 2012. | PP: 504-508 | Volume-2 Issue-2, May 2012 . | Retrieval Number: B0620042212/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: 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: This paper presents an Improved Zone based Hybrid Feature Extraction Model using Euler Number, which not only improves the feature extraction process which was implemented in Diagonal Based Feature Extraction [1] but also helps in efficient classification of the handwritten alphabets. The use of Euler Number in addition to zoning increases the speed and the accuracy of the classifier as we are able to reduce the search space by dividing the character set into three groups.
Keywords: Handwritten Character Recognition, Feature Extraction, Binary Image, Euler Number, Feed Forward Neural Networks.