Thursday 22nd of February 2018

A Unified Framework for Information Extraction from Newspaper Images

Jitesh Kumar and Sanjay Kumar Dubey

Nowadays Newspapers are very common source of information which is easily available to all. It consists of all sorts of news like social news, political news and lots of advertisements. These advertisements/announcements are concentrated on some specific page. This paper proposes a system that can extract contact information like email address, website address and telephone number from newspaper advertisements regarding job, contract, biding and other announcements of company. Proposed system will be able to store old advertisements details for future references. It is very easy for human being to spot the words in an image but it takes lots of computation for a computer to extract and separate these words. This paper explains the necessary steps which are required to recognize optical characters like segmentation, smoothing, image processing and neural network implementation for image recognition.

Keywords: Optical Character Recognition, Neural Network, Image Processing

Download Full-Text


Jitesh Kumar
M. Tech student

Sanjay Kumar Dubey
Assistant Professor

IJCSI Published Papers Indexed By:





IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482

More contact details »