HANDWRITTEN CHARACTER RECOGNITION USING CNN

Authors

  • Madhu M Nayak Assistant Professor, Department of Computer Science and Engineering, GSSS Institute of Engineering & Technology for Women, Mysore, Karnataka, India Author
  • Vaidehi D MTech in CSE, GSSSIETW, Mysore, India Author

Keywords:

Handwritten Character Recognition, Convolutional Neural Networks (CNNs), Machine Learning, Deep Learning, Optical Character Recognition (OCR)

Abstract

This project explores the development of a Handwritten Character Recognition system utilizing machine learning and deep learning techniques, specifically convolutional neural networks (CNNs). The system demonstrates high accuracy in identifying handwritten characters from optical images or direct input methods. By leveraging advanced pre-processing methods, the project highlights its practical applicability in digitizing handwritten documents, automating postal services, and enhancing accessibility tools. Future work aims to expand the dataset, improve recognition of cursive and connected characters, and integrate real-time applications. The project underscores the potential of transfer learning and other deep learning architectures to create sophisticated, versatile handwritten character recognition systems.

References

K.Gaurav, Bhatia P.K : “Hidden Markov models for off-line cursive handwriting recognition”, in C.R. Rao (ed.): Handbook of Statistics 31, 421 – 442, Elsevier, 2019.

Salvador España –Boquera : ”Continuous handwritten script recognition”, in Doermann, D.Tombre,K.(eds.): Handbook of Document Image Processing and Recognition , Springer Verlag 2020.

A. Brakensiek, J. Rottland,A.Kosmala, J.Rigoll . A new combination scheme for “HMM-based classifiersand its application to handwriting recognition”. In Proc.16th Int. Conf. on Pattern Recognition, volume 2, pages 332–337. IEEE, 2022.

Downloads

Published

2024-07-01

How to Cite

Madhu M Nayak, & Vaidehi D. (2024). HANDWRITTEN CHARACTER RECOGNITION USING CNN. INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING AND TECHNOLOGY (IJCET), 15(3), 219-229. https://mylib.in/index.php/IJCET/article/view/IJCET_15_03_021