OPTICAL HANDWRITTEN DEVNAGARI CHARACTER RECOGNITION USING ARTIFICIAL NEURAL NETWORK APPROACH

Authors

  • JYOTI A.PATIL Ashokrao Mane Group of Institution, Vathar Tarf Vadgaon, India.
  • DR. SANJAY R. PATIL Ashokrao Mane Group of Institution, Vathar Tarf Vadgaon, India.

Keywords:

Classification, 64 dimensional features, Shadow features, feed forward neural network;

Abstract

Character recognitions play a wide role in the fast moving world with the growing technology, by providing more scope to perform research in OCR techniques.In the field of pattern recognitionDevnagarihandwrittencharacterrecognition isone of the challenging research area. Character recognition is defined as electronic translation of scanned images of handwritten or printed text into a machine encoded text. In this paper proposed an off line handwritten Devnagari character recognition technique with the use of feed forward neuralnetwork.For training the neural networka handwritten Devnagaricharacter which is resized into 20x30 pixels is used. The same character is then given to the neural network as input with different set of neurons in hidden layer after the training process, and their recognition accuracy rate is calculated and compared for different Devnagari characters. Good recognition accuracy rates has been given by the proposed system comparable to that of other handwritten character recognition systems.

Downloads

Published

2021-03-27

Issue

Section

Articles