Open AccessDeep Learning Based Models for Offline Gurmukhi Handwritten Character and Numeral Recognition
Author(s) -
Manoj Kumar Mahto,
Karamjit Bhatia,
Rajendra K. Sharma
Publication year - 2022
Publication title -
elcvia. electronic letters on computer vision and image analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.15
H-Index - 11
ISSN - 1577-5097
DOI - 10.5565/rev/elcvia.1282
Subject(s) - computer science , numeral system , artificial intelligence , convolutional neural network , character (mathematics) , scripting language , speech recognition , character recognition , pattern recognition (psychology) , optical character recognition , deep learning , artificial neural network , natural language processing , image (mathematics) , mathematics , geometry , operating system
Over the last few years, several researchers have worked on handwritten character recognition and have proposed various techniques to improve the performance of Indic and non-Indic scripts recognition. Here, a Deep Convolutional Neural Network has been proposed that learns deep features for offline Gurmukhi handwritten character and numeral recognition (HCNR). The proposed network works efficiently for training as well as testing and exhibits a good recognition performance. Two primary datasets comprising of offline handwritten Gurmukhi characters and Gurmukhi numerals have been employed in the present work. The testing accuracies achieved using the proposed network is 98.5% for characters and 98.6% for numerals.