Multi-font Optical Character Recognition Using Deep Learning
P.K. Sandhya Balakrishnan1, L. Pavithira2
1P.K. Sandhya Balakrishnan, Department of Computer Science, CMS College of Science and Commerce, Coimbatore (Tamil Nadu), India.
2Dr. L. Pavithira, Associate Professor, Department of Computer Science, CMS College of Science and Commerce, Coimbatore (Tamil Nadu), India.
Manuscript received on 03 June 2019 | Revised Manuscript received on 28 June 2019 | Manuscript Published on 04 July 2019 | PP: 300-302 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A10520681S419/2019©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: Deep learning (DL) is a new area of research in classification, in which the aim is moving us closer towards the objective of artificial intelligent. However, the results of a DBN are often highly based on settings in particular the combination of runtime parameter values. In this paper, Simulated Annealing (SA) is proposed to increase the results of Convolution Neural Network (CNN), as an alternate method for traditional CNN. Then the proposed SA-CNN classifier is implemented using RETAS OCR dataset and provided the improved recognition accuracy than the CNN classifier.
Keywords: Deep Learning, SA, CNN, OCR.
Scope of the Article: Deep Learning