Journal of Intelligent Computing and MathematicsOpen Access
Journal of Intelligent Computing and Mathematics[JICM] is an international peer-reviewed journal that publishes original and high-quality research papers in all related areas. All papers published will be open access to all readers. To build a platform for scientific research and academic exchange for scholars, focusing on the development and research, introducing worldwide research, theory and practice, and promoting international exchanges.
ISSN: N/A (Print)
Frequency: Bimonthly
ISSN: 2771-9952 (Online)
Website: https://doi.org/10.55571/jicm
Email: journal@4dpublishinggroup.com / jicm@4dpublishinggroup.com
Indexing and Abstracting:Google Scholar; CrossRef; ResearchBib; WorldCat; CiteFactor
Email: journal@4dpublishinggroup.com / jicm@4dpublishinggroup.com
Indexing and Abstracting:Google Scholar; CrossRef; ResearchBib; WorldCat; CiteFactor
Handwritten Devanagari Digits Recognition Using Residual Neural Network
DOI: https://doi.org/10.55571/jicm.2022.04011
Authors:Bandyopadhyay Shaon
Affiliation: Department of Computer Science, Dr. B. C. Roy Engineering College, West Bengal, India
Information: Journal of Intelligent Computing and Mathematics. April 2022 Vol.1, No.1, pp 1-7
Authors:Bandyopadhyay Shaon
Affiliation: Department of Computer Science, Dr. B. C. Roy Engineering College, West Bengal, India
Information: Journal of Intelligent Computing and Mathematics. April 2022 Vol.1, No.1, pp 1-7
Abstract:Handwritten digit recognition is a highly evolved research domain of pattern recognition. It is used to classify pre-segmented handwritten digits. The Devanagari script is one of the writing systems of various Indian languages including Sanskrit and Hindi. In this paper, an efficient Handwritten Devanagari numeral digit recognition using ResNet is proposed. Deep learning is a recent research trend in this field. Architectures like Residual neural Networks (ResNet) are being used. ResNet is an architecture that is computationally expensive and normally used to provide high accuracy in classification problems. The structural design of the network consists of sacks of two convolutional (Conv2D) layers with Batch Normalization and an activation function called Relu. We evaluated our scheme on 16000 handwritten samples of Devanagari numerals from the UCI machine learning database and from the experiment we have achieved 99.40% recognition rate.
Keywords:CNN; ResNet; Handwritten digits recognition; Devanagari: Hindi: Sanskrit; UCI
Cite This Article:Shaon B. (2022). Handwritten Devanagari Digits Recognition Using Residual Neural Network. Journal of Intelligent Computing and Mathematics, Vol.1, No.1, pp 1-7. https://doi.org/10.55571/jicm.2022.04011
Keywords:CNN; ResNet; Handwritten digits recognition; Devanagari: Hindi: Sanskrit; UCI
Cite This Article:Shaon B. (2022). Handwritten Devanagari Digits Recognition Using Residual Neural Network. Journal of Intelligent Computing and Mathematics, Vol.1, No.1, pp 1-7. https://doi.org/10.55571/jicm.2022.04011
