ABSTRACT
Despite promising results in character recognition techniques, research on handwritten characters from Indian regional scripts is still limited. In fact, most character recognizers in Indian languages are far less accurate than those built for English alphanumeric characters. Traditional techniques rely on extracted characteristics that require extensive knowledge of the chosen script, which is never practical. In such a circumstance, automatically extracting features may create interest. This study demonstrates how deep CNN VGG-16 networks can be used to increase character recognition accuracy. We have used nine different datasets from three separate Indian regional languages, Devanagari, Bangla, and Odia, to validate the model's efficacy further. When the samples were very noisy, it was revealed that the VGG model performed exceptionally well. The model recognized up to 3% better accuracy when the input samples were noisy and without applying any preprocessing. Furthermore, the model was implemented via transfer learning rather than being trained from scratch. This accomplishment could pave the way for constructing an automatic character recognition system for Indian regional scripts. The model outperforms recognition accuracy by around 1% for two datasets, cMATERdb 3.1.2 Bangla Basic and NITROHCS_V1.0 Odia Basic, compared to the existing approaches in the literature.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
Raghunath Dey
Dr. Raghunath Dey is currently working as an Assistant Professor in the School of Computer Engineering Department, KIIT Deemed to be University, Bhubaneswar, Odisha. He has done M.E. in Information Technology from Jadavpur University, Kolkata, W.B. in the year 2012. Dr. Dey received his PhD award from IIIT Bhubaneswar, Odisha in the year 2022. He has eleven years of teaching experience. He has published many research publications in peer-reviewed journals such as Multimedia Tools and Applications, International Journal of Information Technology. He has delivered presentations at many international conferences. His area of research lies in Pattern Recognition, Machine Learning, and Offline Optical Character Recognition.
Rakesh Chandra Balabantaray
Dr. Rakesh Chandra Balabantaray is currently working as Associate Professor in the Department of Computer Science and Engineering, also Dean (Academics) in IIIT, Bhubaneswar, Odisha, India. He did his Masters in Computer Science in the year 2001 and Ph.D. in Computer Science in the year 2008 from Utkal University, Odisha, India. He has more than hundred publications in various reputed journals and conferences. His major area of research is Artificial Intelligence, Natural Language Processing and Information Retrieval.
Sidharth Samanta
Mr. Sidharth Samanta is currently a Ph.D. research scholar in the Department of Computer Science and Engineering, International Institute of Information Technology, Bhubaneswar, Odisha, India. He obtained his master's degree in computer science and engineering in the year 2019 from Utkal University, Odisha, India. His research interests include machine learning, image processing, computer vision and applications.