By Topic

Recognition of Blurred Images Using Multilayer Neural Network Based on Multi-valued Neurons

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Aizenberg, I. ; Comput. Intell. Lab., Texas A&M Univ. - Texarkana, Texarkana, TX, USA ; Alexander, S. ; Jackson, J.

In this paper, we consider a problem of blurred image recognition using a multilayer neural network based on multi-valued neurons (MLMVN). Recognition of blurred images is a challenging problem because it is difficult or even impossible to find any relevant space of features for solving this problem in the spatial domain. The first crucial point of our approach is the use of the frequency domain as a feature space. Since Fourier phase spectrum of a blurred image remains almost unaffected, at least in the low frequency part, it is possible to use phases corresponding to the lowest frequencies as features for recognition. To preserve the physical nature of phase, it is very important to use a machine learning tool for its analysis that treats the phase properly. MLMVN is based on multi-valued neurons whose inputs and output are located on the unit circle and are determined exactly by phase. This approach makes it possible to recognize even heavily blurred images. Our solution works even for images so degraded they cannot be recognized using traditional image recognition techniques, furthermore, even visually

Published in:

Multiple-Valued Logic (ISMVL), 2011 41st IEEE International Symposium on

Date of Conference:

23-25 May 2011