High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

A Framework for Segmentation and Recognition of Hindi Letters

Author(s):

Shalini Dogra , Ssgi, yamunanagar, haryana, India ; Amit Sehgal, Ssgi, yamunanagar, haryana, india

Keywords:

Handwritten Character Recognition (HCR), Optical Character Recognition (OCR), Artificial Neural Network (ANN)

Abstract

Character recognition is one of the most interesting and fascinating areas of pattern recognition and artificial intelligence due to its numerous applications. It continues to be a challenging research area. OCR suggests to the practice of picture scanning of the text character-by-character, analysis of the scanned image then changing of the character image into information that a machine can simply examine .e.g. organizations and libraries taking physical replicas of books, magazines, or other old printed material and utilizing OCR to place them in computers. Segmentation is the crucial and most complex part of OCR method, and it gets difficult with handwritten text due to totally different writing styles and fonts used. In this paper, we propose a method for segmentation and recognition of Hindi Letters which takes offline handwritten input using variation of gradient, structural features and implement Gabor Filter and Chain Code for feature extraction and artificial neural network approach.

Other Details

Paper ID: IJSRDV5I41265
Published in: Volume : 5, Issue : 4
Publication Date: 01/07/2017
Page(s): 1095-1101

Article Preview

Download Article