Script Identification for printed document images at text-line  level using DCT and PCA 

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2013, Vol 12, Issue 5

Abstract

 The progress of information technology and the wide reach of the Internet are drastically changing all fields of activity in modern days. As a result, a very large number of people would be required to interact  more frequently with computer systems. To develop the human–machine interaction more effective in such  situations, it is desirable to have systems capable of handling inputs in a variety of forms such as  printed/handwritten paper documents. In a multi-lingual country like India, where more than 22 official  languages and 12 different scripts are used for these languages. it is an utmost essential & complicated for  designing an OCR system and it became more difficult if the document consist of multiple languages so for an  automated multilingual environment such document processing systems relying on OCR would clearly need to  identify the script type of the document files, so that specific tool of OCR can be selected. In this paper, a script identification approach for Indian scripts is proposed at text-line level. It is a  Visual appearance-based script recognition method. The recognition is based upon features extracted using  Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA) algorithm and for further  extraction we use Modified-KNN. The proposed method is tested on printed document images in 11 major  Indian languages, 95% recognition accuracy is obtained.

Authors and Affiliations

Monali Jindal

Keywords

Related Articles

Main Content Mining from Multi Data Region Deep Web Pages

Abstract: An Automatic Data extraction from the deep web pages is an endeavoring errand. Colossal web substance are gotten to as per well-known interest submitted to Web databases and the returned data records are e...

 Document Management System with Enhanced Security

 This paper provides the design of a Document Management System designed for a Small to Medium scale enterprises with a special emphasis on security, it also describes a new symmetric encryption algorithm Secured...

 Resource-Diversity Tolerant: Resource Allocation in the Cloud Infrastructure Services

Abstract: The cloud offers data processing, data centers to process and preserve the transactional data of the clients. Dynamic capacity provisioning is promising approach for reducing energy consumption by dynamicallych...

 Application of Artificial Intelligence in Software Engineering

Software development is a very complex process that, at present, is primarily a human activity. Programming, in software development, requires the use of different types of knowledge. So, automating software development...

 Optimized Fuzzy Routing for MANET

 temporary network without the aid of any established infrastructure of centralized administration. In suchenvironment, the nodes operate both as hosts as well as routers. Due to mobility, the topology of the networ...

Download PDF file
  • EP ID EP120378
  • DOI -
  • Views 107
  • Downloads 0

How To Cite

Monali Jindal (2013).  Script Identification for printed document images at text-line  level using DCT and PCA . IOSR Journals (IOSR Journal of Computer Engineering), 12(5), 97-102. https://europub.co.uk/articles/-A-120378