A Multiscale Neural Network Method for Image Restoration
DOI:
https://doi.org/10.5540/tema.2008.09.01.0041Abstract
This paper describes a novel neural network based multiscale image restoration approach. The method uses a Multilayer Perceptron (MLP) trained with synthetic gray level images of artificially degraded co-centered circles. The main difference of the present approach to existing ones relies on the fact that the space relations are used and they are taken from different scales, which makes it possible for the neural network to establish space relations among the considered pixels in the image. This approach attempts at coming up with a simple method that leads to an optimum solution to the problem without the need to establish a priori knowledge of existing noise in the images. The multiscale data is acquired by considering different window sizes around a pixel. The performance of the proposed approach is close to existing restoration techniques but it was observed that the resulting images showed a slight increase in contrast and brightness. The proposed technique is also used as a preprocessing phase in a real-life classification problem of medical Magnetic Resonance Images (MRI) by using a fuzzy classification technique.References
[1] M. Bertero, P. Boccacci, “Introduction to Inverse Problems in Imaging”, Philadelphia, Bristol, 1998.
J. Bezdek, R. Ehrlich, W. Full, FCM: The fuzzy c-means algorithm. Computers & Geosciences, 10, No. 2-3, (1984), 491–263.
Y.M. Bishop, S.E. Feinberg, P.W. Holland, “Discrete Multivariate Analysis: Theory and Practice”, Cambridge: MIT Press, 1975.
A.P.A. Castro, J.D.S. Silva, Neural Network-Based Multiscale Image Restoration Approach. In: Proceeding on Electronic Imaging, Vol. 6497, San Jose, pp. 3854–3859, 2007.
A.P.A. Castro, J.D.S. Silva, Neural Network-Based Multiscale Image Restoration Approach. In: Proceedings of IPDO, Miami, 2007.
J. Chen, J. Benesty, Y. Huang, S. Doclo, New insights into the noise reduction wiener filter, IEEE Trans. on Audio, Speech and Language Processing, 14, No.4 (2006), 1218–1234.
I. Drummond, S. Sandri, A clustering-based possibilistic method for image classification, Lecture Notes in Computer Science, 3171 (2004), 454–463.
I. Drummond, S. Sandri, A clustering-based fuzzy classifier, Frontiers in Artificial Intelligence and Applications, 131, No. 1 (2005), 247–254.
R.C. Gonzalez, R.C. Woods, “Digital Image Processing”, New York, Addison Wesley, 1992.
S. Haykin, “Redes Neurais: Princ´ıpios e Pr´atica”, P. Alegre, Bookman, 2001.
K.V.D. Heijden, “Image BasedMeasurement Systems”, New York,Wiley, 1994.
A.K. Jain, “Fundamentals of Digital Image Processing”, New Jersey, Prentice Hall, Inc, 1989.
A.D. Kulkarni, “Computer Vision and Fuzzy-Neural Systems”, New Jersey, Prentice Hall, 2001.
Y.D. Wu, Q.Z. Zhu, S.X. Sun, H.Y. Zhang, Image restoration using variational PDE-based neural network, Neurocomputing, 69, No. 16-18, (2006), 2364–2368.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License that allows the sharing of the work with acknowledgment of authorship and initial publication in this journal.
Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
Authors are allowed and encouraged to publish and distribute their work online (eg, in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes as well as increase impact and the citation of the published work (See The effect of open access).
This is an open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the
author. This is in accordance with the BOAI definition of open access
Intellectual Property
All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License under attribution BY.