Seybold Report ISSN: 1533-9211
K.Tulasiram
Associate Professor, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, tulasiramkorrapati@gmail.com
Spandana Reddy Muthyala
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, spandanam427@gmail.com
Sneha Bandi
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, snehareddymay8@gmail.com
Manasa Anagandla
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, manasaanagandla12345@gmail.com
Vol 17, No 07 ( 2022 ) | DOI: 10.5281/zenodo.6876942 | Licensing: CC 4.0 | Pg no: 30-36 | Published on: 25-07-2022
Abstract
Objective: Handwritten text recognition is one of the most active and hard study fields in AI and machine learning. To accomplish this a handwritten manuscript is scanned and converted into a basic text document.
Methods: The fundamental optical character recognition (OCR) methods examines a documents text and converts it into data processing codes. We focus on offline identification of handwritten English words by first detecting individual characters in this research. In the field optical character recognition, handwritten text recognition is still a study topic (OCR). This research presence a cost effective method for developing for handwritten text recognition system. In this paper a three layer artificial neural network (ANN) is used in a supervised learning technique.
Results: The trained system has high level of accuracy with an average of above 95%. So, by converting handwritten text documents to digital form , it is possible to split up difficult problems and reduce the amount of human intervention.
Keywords:
optical character recognition ,artificial neural network and handwritten text recognition.