Feature Extraction Techniques Based on Swarm Intelligence in OCR
Shrinivas R. Zanwar1, Abbhilasha S. Narote2, Sandipann P. Narote3

1Shrinivas R. Zanwar, Electronics and Telecommunication Engineering department, CSMSS, Chh. Shahu College of Engineering, Aurangabad, India.
2Abhilasha S. Narote, Electronics and Telecommunication Engineering department, S.K.N. College of Engineering, Pune, India.
3Sandipann P. Narote, Electronics and Telecommunication Engineering department, Government Residence Women’s Polytechnic, Tasgaon, Sangli, India. 

Manuscript received on September 16, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 13-19 | Volume-8 Issue-12, October 2019. | Retrieval Number: L24801081219/2019©BEIESP | DOI: 10.35940/ijitee.L2480.1081219
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: Optical Character Recognition is a most recent field in area of pattern recognition and machine learning in last decade. In this article, the suitable techniques are designated for better character recognition in document into machine readable form. It is belonging with Content Based Image Retrieval (CBIR) system, which solve the delinquent of searching images in huge dataset. The recognition technique of handwritten character is not developed efficiently till, because of variations in size, shape, style, slats etc. in writing skill of human being. To overcome such problems, the part of concentration is feature extraction and algorithm that take care of such variation. In this paper independent component analysis is used for extracting features. For feature vector selection particle swarm optimization and firefly algorithms are applied. It is observed that due to distributed neighborhood pixel of an image, the PSO gives better recognition rates.
Keywords: Independent Component Analysis, Particle Swarm Optimization, Firefly Algorithm, Pattern Recognition
Scope of the Article: Artificial Intelligence