Touchless Written English Characters Recognition using Neural Network

Abstract

 Touchless written English character recognizer (TER), a new touchless approach to write and an intelligent approach to recognize English characters has been proposed in this paper. In TER, the inputs of English characters have been taken by touchless fashion i.e. by sensing specific color object with a moving hand tracking in front of a webcam. Then they have been recognized by efficient Artificial Neural Network (ANN). Like the application of other traditional computer input devices such as mouse or keyboard, TER can be extended to write and recognize English words and sentences by adding characters one by one to the text editor. Proposed TER has been applied for several different forms of touchless writings, namely 26 English characters and 10 English digits. Here for training, ANN with Scale Conjugate Gradient (SCG) method has been used that converges the training time faster and recognizes with good generalization ability. TER can be useful for the disabled persons.

Authors and Affiliations

Bikash Chandra Karmokar1 , M. A. Parvez Mahmud2 , Md. Kibria Siddiquee3 , Kawser Wazed Nafi4 , Tonny Shekha Kar5

Keywords

Related Articles

A Simulation And Analysis Of Secured S-DSR Protocol In Mobile Ad Hoc Networks

AMANET is as pecial kind of wireless network, which can be treated as a collection of mobile nodes co-existing with each other without the need of any fixed infrastructure. Because of the limited  physical security,...

Modified Genetic Algorithm for Maximum Clique Problem

Maximum clique problem is NP-hard problem which applies its application in determining the maximum connected sub graphs. Cliques are one of the basic concepts of graph theory and are used in many other mathematical probl...

Power Efficient Weighted Modulo 2n+1 Adder

The comparison of three different architectures for modulo 2n+1 adders are introduced in this paper. The first two architecture can be implemented different power consumptions, while maintain the same delay. The partitio...

A Novel Approach of a n effective image retrieval scheme using color, texture and shape features

In this paper, we present a new and effective color image retrieval scheme for combining all the three i.e. color, texture and shape information, which achieved higher retrieval efficiency. Firstly, the image is predeter...

 SE code optimization using Data Mining Approach

 Data mining also holds promises for other software engineering processes, which have to deal with uncertainty and intangible data such as cost estimation, effort estimation and quality. It can also aid in interesti...

Download PDF file
  • EP ID EP109270
  • DOI -
  • Views 100
  • Downloads 0

How To Cite

Bikash Chandra Karmokar1, M. A. Parvez Mahmud2, Md. Kibria Siddiquee3, Kawser Wazed Nafi4, Tonny Shekha Kar5 (2012).  Touchless Written English Characters Recognition using Neural Network. International Journal of Computer & organization Trends(IJCOT), 2(3), 80-84. https://europub.co.uk/articles/-A-109270