Twelve Directional Feature Extraction for Handwritten English Character Recognition
Sumedha B. Hallale1, Geeta D. Salunke2
1Sumedha B. Hallale, Department of Electronics and Telecommunication, Pune University, Genba Sopanrao Moze College of Engineering, Balewadi Pune (M.H), India.
2Prof. Geeta Salunke, Department of Electronics and Telecommunication, Pune University, Genba Sopanrao Moze College of Engineering, Balewadi Pune (M.H), India.
Manuscript received on 21 May 2013 | Revised Manuscript received on 28 May 2013 | Manuscript published on 30 May 2013 | PP: 39-42 | Volume-2 Issue-2, May 2013 | Retrieval Number: B0577052213/2013©BEIESP
Open Access | Ethics and 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: Directional features have been successfully used for the recognition of both machine printed as well as handwritten characters. Selection of feature extraction method is probably the single most important factor in achieving high performance in pattern recognition. In this paper, twelve directional features are used for the recognition of handwritten English alphabets and numerals. The properties of similarity measure are analysed with directional pattern matching. Then the comparison is made between recognition rate of conventional and twelve directional feature extraction techniques. The experiment shows that directional feature extraction techniques are better than conventional one.
Keywords: Feature Extraction, Pattern Recognition, Directional Pattern Matching, Recognition Rate.
Scope of the Article: Pattern Recognition