No abstract

Abstract-Despite the considerable progress in the field of imaging, the acquired image can undergo certain degradations which are mainly summarized in blur and noise. The objective of the restoration is to estimate from the observed image an image as close as possible to the original image. The iterative blind deconvolution (IBD) can be used effectively when no information about the distortion is known. This algorithm starts with a random initial estimate of the point spread function (PSF) whose its size affects strongly the restoration process of the degraded image. In this paper, we have implemented a fuzzy inference system (FIS) to determine the size of the PSF through the examination of the blurred satellite image edges and the measurement of the blur width in pixels around an obviously sharp object. The obtained results are encouraging, which confirms the good performance of the proposed approach.

In the process of satellite imaging, the observed image is blurred by optical system and atmospheric effects and corrupted by additive noise. The image restoration method known as Wiener deconvolution intervenes to estimate from the degraded image an image as close as possible to the original image. The effectiveness of this method obviously depends on the regularization term which requires a priori knowledge of the power spectral density of the original image that is rarely, if ever, accessible, hence the estimation of approximate values can affect the restored image quality. In this paper, the idea consists of applying the genetic approach to the Wiener deconvolution for satellite image restoration through the optimization of this regularization term in order to achieve the best possible result.

The image restoration method entitled Wiener deconvolution intervenes to improve the quality of images subjected to the degradation effects of both blur and noise. The effectiveness whose this method has demonstrated in this kind of situations, obviously depends on the regularization term that has a direct impact on the expected result. This regularization term requires a priori knowledge of the power spectral density of the original image that is rarely accessible, hence the estimation of approximate values can affect the image quality. An amelioration has been brought to this method, which consists to iterate the Wiener filter to estimate the power spectral density of the original image. The optimization of the iteration count of the iterative Wiener filter by genetic approach leads to the better result.Index Terms-Image restoration, Wiener deconvolution, power spectral density, iterative Wiener filter, genetic algorithm.978-1-4799-7511-2/15/$31.00

Selecting the parameters for the classification is a delicate process. We present in this paper a method for selecting the parameters by the genetic algorithm which optimizes the choice of parameters by minimizing a cost function. This function is defined by a Trace criterion. The approach is validated on some characters images. The proposed algorithm gives a fast convergence towards the optimal solution.