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

Optical Character Recognition Using Grid Infrastructure


Santosh Kumar Kasaudhan , Galgotias College of Engineering and Tehnology; Shubham Saxena, Galgotias College of Engineering and Tehnology; Varun Upadhyay, Galgotias College of Engineering and Tehnology; Lucknesh Kumar, Galgotias College of Engineering and Tehnology


Optical Character Recognition, Neural Network, Grid Infrastructure, Kohonen Neural Network


As in the running world, there is a lot of demand for the software systems to recognize characters and words in computer system when information is scanned through paper documents as we know that we have number of newspapers and books which are in printed format related to different subjects. These days there is a huge demand in “storing the information available in these paper documents in to a computer storage disk and then later reusing this information by searching process”. Compared to various existing available character recognition systems it improves the accuracy of recognizing the characters during document processing. Since our character recognition is based on a grid infrastructure, heterogeneous characters of different universal languages with different font properties and alignments are recognized easily. We proposed a novel algorithm in this paper to extract text/characters from a scanned image using neural networks by using a method for combining independently trained networks to achieve higher performance. Proposed system consists of the following steps 1) Image Processing 2) Image Training 3) Image Recognition 4) Image Editing and 5) Image Searching. In our paper it is shown that, the proposed system is better than the existing systems and try to improve the efficiency and accuracy of recognizing the characters from a scanned image.

Other Details

Paper ID: IJSRDV4I20874
Published in: Volume : 4, Issue : 2
Publication Date: 01/05/2016
Page(s): 1043-1045

Article Preview

Download Article