A New Process of Color Images Recognition by Using ART-1 Neural Network

R. Thilepa, M. Thanikachalam

Abstract


In this paper ART1 neural network algorithm is used for recognition of color images which speeds up the process of Image processing and its recognition process. But, generally Adaptive Resonance Theory-1(ART-1) network is used only for processing binary digits, but in this paper it may also be used for image recognition. The given fact limits the loss of information as a result, two different colors in which inside one original image can be represented as a same value of binary color during recognition. These mistakes are overcome by our image recognition method here.This method is very attractive because of its low computational overhead, improved performance comparatively than other networks with less number of neurons. Experimental results are given finally which are encouraging in this paper.


Full Text: PDF DOI: 10.5539/cis.v4n1p217

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

Computer and Information Science   ISSN 1913-8989 (Print)   ISSN 1913-8997 (Online)
Copyright © Canadian Center of Science and Education

To make sure that you can receive messages from us, please add the 'ccsenet.org' domain to your e-mail 'safe list'. If you do not receive e-mail in your 'inbox', check your 'bulk mail' or 'junk mail' folders.