A Novel Approach to Recognize the off-line Handwritten Numerals using MLP and SVM Classifiers

Abstract

This paper presents a new approach to off-line handwritten numeral recognition. Recognition of handwritten numerals has been one of the most challenging task in pattern recognition. Recognition of handwritten numerals poses serious problems because of high variability in numeral shapes written by individuals. This paper concerns with offline handwritten numeral recognition based on MLP and SVM classifiers. The performance of character recognition system depends heavily on what kind of features extraction techniques are being used. In this work, we have collected 1200 samples of isolated numerals, contributed by 24 writers and each one has written it five times. In this paper we propose a modified Hough transformation technique and four view projection Profiles technique to extract the feature of numerals. Using the modified Hough transformation technique, we have achieved maximum accuracy of about 93.12% and 72.5% by SVM and MLP classifiers and with four view projection profiles technique; we obtained the 96.04% and 98.73% recognition accuracy by SVM and MLP classifiers.

Authors and Affiliations

Mamta Garg , Deepika Ahuja

Keywords

Related Articles

The Design and Implementation of Land Management Information System (LMIS), Bauchi State Ministry of Lands and Survey

The need to collection, store, process and disseminate information about land availability, ownership and titles is a fundamental task that should be performed by any responsible agency in charge of land administration....

Secure Routing Using ASOR Protocol for MANETs

Privacy protection is one of the critical issues in Mobile Adhoc Networks. To provide unobservability and unlinkability on the network was the major requirements. Although ,there was number of secure protocols available...

CRYPTOGRAPHIC METHOD FOR DIGITAL DOCUMENT

Due to the recent development of computers and computer networks, huge amount of digital data can easily be transmitted or stored. However, transmitted data in networks or stored data in computers may easily substitute b...

Multiple Object Removal Using Exemplar-Based Image Inpainting

The art of filling missing data in an image is known as image inpainting.The main purpose of inpainting process is to reconstruct missing regions in a visually plausible way. The propose system suggest a new algorithm fo...

A Survey of Cyber Crimes 

Now a days Cyber Crime is the most significant challenges in India .Cyber Crimes are generally referred as criminal activities that use computers or networks. It can range from fraud to unsolicited emails (spam). It can...

Download PDF file
  • EP ID EP130738
  • DOI -
  • Views 104
  • Downloads 0

How To Cite

Mamta Garg, Deepika Ahuja (2013). A Novel Approach to Recognize the off-line Handwritten Numerals using MLP and SVM Classifiers. International Journal of Computer Science & Engineering Technology, 4(7), 953-958. https://europub.co.uk/articles/-A-130738