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

Introduction To Neural Network Based Approach For Optical Character Recognition

Author(s):

Minal Hedalkar , Thakur Polytechnic; Tanmayee Bhosale, Thakur Polytechnic; Priya Singh, Thakur Polytechnic; Anuradha Chakrawarti, Thakur Polytechnic

Keywords:

Character Recognition, Neural Network, Architecture of Text recognition system, Feature Extraction, Tesseract

Abstract

The Artificial Neural Network (ANN) is an information processing paradigm. The important element of this paradigm is the novel structure of the information processing system. These days, handwritten character recognition is a difficult problem due to the great variations of writing styles, different size of the characters, etc. OCR is a technology that enables you to convert different types of documents. For e.g. scanned paper documents, PDF files or images captured by a digital camera into editable and searchable data. The whole process of recognition includes segmentation of characters into line, word and characters. While the other part include recognition through feed forward neural network. Basically, for an offline handwritten alphabetical character recognition system using multi-layer feed forward neural network, a method of feature extraction along with the data to train the artificial neural network is used.

Other Details

Paper ID: IJSRDV3I120714
Published in: Volume : 3, Issue : 12
Publication Date: 01/03/2016
Page(s): 892-894

Article Preview

Download Article