Open AccessHand Writing Recognition System using Neural Networks
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a5310.119119
Subject(s) - computer science , artificial neural network , artificial intelligence , field (mathematics) , intelligent character recognition , pattern recognition (psychology) , process (computing) , speech recognition , sorting , reading (process) , character recognition , writing system , intelligent word recognition , natural language processing , image (mathematics) , algorithm , linguistics , philosophy , mathematics , political science , pure mathematics , law , operating system
Handwritten Recognition is a process of pattern recognition which defines ability of a system to identify characters. There are many applications of Handwritten recognition (HWR) system such as reading postal addresses, bank check amounts, mail sorting and many more. HWR systems transcribes human written text into digital text. Plenty of research done in the field of recognizing handwritten characters but lacking in best accuracy is a challenge. In this proposed technique, offline HWR is done using Neural networks(NN) and Tensorflow is proposed. The proposed technique used to build a system which will be able to recognize the hand written characters with highest accuracy. The experiment is performed on proposed technique with accuracy of 85.5% compared to the state-of-the-art.