The International Arab Journal of Information Technology (IAJIT)


An Improved Richardson-Lucy Algorithm Based on Genetic Approach for Satellite Image Restoration

In the process of satellite imaging, the observed image is blurred by optical system and atmospheric effects and corrupted by additive noise. The deconvolution of blurred and noisy satellite images is an ill-posed inverse problem. In the literature, a number of image restoration methods have been proposed to reconstruct an approximated version of the original image from a degraded observation. The iterative method known as Richardson-Lucy deconvolution has demonstrated its effectiveness to compensate for these degradations. The efficiency of this method obviously depends on the iteration count that has a direct impact on the expected result. This decisive and virtually unknown parameter leads to the estimation of approximate values which may affect the quality of the restored image. In this paper, the idea consists of optimizing the iteration count of the Richardson-Lucy deconvolution by applying the genetic approach in order to get a better restoration of the degraded satellite image.

[1] Banham M. and Katsaggelos A., Digital Image Restoration, IEEE Signal Processing Magazine, vol. 14, no. 2, pp. 24-41, 1997.

[2] Biggs D. and Andrews M., Acceleration of Iterative Image Restoration Algorithms, Applied Optics, vol. 36, no. 8, pp. 1766-1775, 1997.

[3] Campisi P. and Egiazarian K., Blind Image Deconvolution: Theory and Applications, CRC Press, 2007.

[4] Dash R. and Majhi B., Motion Blur Parameters Estimation for Image Restoration, Optik- International Journal for Light and Electron optics, vol. 125, no. 5, pp. 1634-1640, 2014.

[5] Dong W., Feng H., Xu Z., and Li Q., A Piecewise Local Regularized Richardson-Lucy Algorithm for Remote Sensing Image deconvolution, Optics and Laser Technology, vol. 43, no. 5, pp. 926-933, 2011.

[6] Fish D., Walker J., Brinicombe A., and Pike E., Blind Deconvolution by Means of the Richardson-Lucy Algorithm, Journal of the Optical Society of America A, vol. 12, no. 1, pp. 58-65, 1995.

[7] Hillery A. and Chin R., Iterative Wiener Filters for Image Restoration, IEEE Transactions on Signal Processing, vol. 39, no. 8, pp. 1892-1899, 1991.

[8] Jalobeanu A., Blanc-F raud L., and Zerubia J., Satellite Image Deblurring Using Complex Wavelet Packets, International Journal of Computer Vision, vol. 51, no. 3, pp. 205-217, 2003.

[9] Li Y. and Clarke K., Image Deblurring for Satellite Imagery using Small-Support- Regularized Deconvolution, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 85, pp. 148-155, 2013.

[10] Man K., Tang K., and Kwong S., Genetic Algorithms: Concepts and Designs, Springer Science and Business Media, 2012.

[11] Mitchell M., An Introduction to Genetic Algorithms, MIT Press, 1998.

[12] Moghaddam M. and Jamzad M., Motion Blur Identification in Noisy Images using Mathematical Models and Statistical Measures, Pattern Recognition, vol. 40, no. 7, pp. 1946- 1957, 2007.

[13] Molina R., Nunez J., Cortijo F. J., and Mateos J., Image Restoration in Astronomy: A Bayesian Perspective, IEEE Signal Processing Magazine, vol. 18, no. 2, pp. 11-29, 2001.

[14] Poli R., Langdon W., and McPhee N., A Field Guide to Genetic Programming, Lulu Enterprises, 2008.

[15] Saadi S., Guessoum A., Bettayeb M., and Abdelhafidi M., Blind Restoration of Radiological Images using Hybrid Swarm Optimized Model Implemented on FPGA, The International Arab Journal of Information Technology, vol. 11, no. 5, pp. 476-486, 2014.

[16] Shah M. and Dalal U., 3D-Image Restoration Technique using Genetic Algorithm to Solve Blurring Problems of Images, The Imaging Science Journal, vol. 62, no. 7, pp. 365-374, 2014.

[17] Yongpan W., Huajun F., Zhihai X., Chaoyue D., and Qi L., An Improved Richardson-Lucy Algorithm based on Local Prior, Optics and Laser Technology, vol. 42, no. 5, pp. 845-849, 2010.

[18] Zhao M., Zhang W., Wang Z., and Hou Q., Satellite Image Deconvolution Based on Nonlocal Means, Applied Optics, vol. 49, no. 32, pp. 6286-6294, 2010. 2n 2n 720 The International Arab Journal of Information Technology, Vol. 15, No. 4, July 2018 Fouad Aouinti received an engineering diploma in computer science in 2013 from National School of Applied Sciences, Tetouan, Morocco. He is a PhD student who works on image processing in MATSI laboratory of the Superior School of Technology, Mohammed I University, Oujda, Morocco. His main field of research interest is image restoration based on genetic algorithm, fuzzy logic and neural networks. M barek Nasri is Engineer of the National School of the Mineral Industry, Rabat, Morocco. He is Doctor in Science (PhD degree, 2004) of the Mohammed I University, Oujda, Morocco. He obtained the Habilitation degree in 2006 from the same University. He teaches the computer science. His field of research interest is in image processing and computer vision and their applications to the medical imaging, quality control and recognition of the handwritten writing. He is permanent member of the MATSI laboratory. Mimoun Moussaoui received his doctorate in Numerical Analysis in 1984 from University Paris XI (Orsay, France). He obtained his PhD in Nonlinear Analysis in 1991 from the Free University (Universit Libre) of Brussels Belgium. He is currently professor at the Mohammed I University of Oujda (Morocco). He teaches Mathematics for economics and scientists, Numerical analysis and linear programming. He supervised several theses in applied mathematics and computing. He is director of Mathematics, signal and image processing and computing research Laboratory (MATSI). Bouchta Bouali received his doctorate in a qualitative uncertainty principle for Lie groups in 2002 from Mohammed I University, Oujda, Morocco. He obtained the Habilitation degree in 2005 from the same University. He teaches the geometry, the group algebras and the image processing. His research interests are Lie groups, Lie algebras, Representation and Harmonic analysis on Lie groups and image processing. He is permanent member of the AGA laboratory.