27 February 2007 Neural network based multiscale image restoration approach
Author Affiliations +
Abstract
This paper describes a neural network based multiscale image restoration approach. Multilayer perceptrons are trained with artificial images of degraded gray level circles, in an attempt to make the neural network learn inherent space relations of the degraded pixels. The present approach simulates the degradation by a low pass Gaussian filter blurring operation and the addition of noise to the pixels at pre-established rates. The training process considers the degraded image as input and the non-degraded image as output for the supervised learning process. The neural network thus performs an inverse operation by recovering a quasi non-degraded image in terms of least squared. The main difference of the approach to existing ones relies on the fact that the space relations are taken from different scales, thus providing relational space data to the neural network. The approach is an attempt to come up with a simple method that leads to an optimum solution to the problem. Considering different window sizes around a pixel simulates the multiscale operation. In the generalization phase the neural network is exposed to indoor, outdoor, and satellite degraded images following the same steps use for the artificial circle image.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ana Paula A. de Castro, Ana Paula A. de Castro, José D. S. da Silva, José D. S. da Silva, } "Neural network based multiscale image restoration approach", Proc. SPIE 6497, Image Processing: Algorithms and Systems V, 64970Q (27 February 2007); doi: 10.1117/12.703468; https://doi.org/10.1117/12.703468
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Pattern Recognition Based On The Triple Correlation
Proceedings of SPIE (January 01 1987)
Image restoration with local adaptive methods
Proceedings of SPIE (September 07 2010)
Optimal design of 2D digital filters based on neural networks
Proceedings of SPIE (February 08 2005)

Back to Top