Image Restoration using Multilayer Neural Networks with Minimization of Total Variation Approach
Noise reduction is a very important task in image processing. In this aim, many approaches and methods have been developed and proposed in the literature. In this paper, we present a new restoration method for noisy images by minimizing the Total Variation (TV) under constraints using a multilayer neural network (MLP). Indeed, the obtained Euler-Lagrange functional is resolved by minimizing an error functional. The MLP parameters (weights) in this case are adjusted to minimize appropriate functional and provides optimal solution. The proposed method can restore degraded images and preserves the discontinuities. The effectiveness of our approach has been tested on synthetic and real images, and compared with known restoration methods
Keywords: Image restoration, Partial Differential Equations, Total variation, Multilayer neural network.
Download Full-Text
ABOUT THE AUTHORS
Mohammed Debakla
Is a PhD student in computer Science University of Science and Technology of Oran (USTO) - ALGERIA. He received the diploma of engineering in Computer Science from the University of Oran (USTO) - ALGERIA in 1996. He received the diploma of teaching in Computer Science from the University of Oran (USTO) - ALGERIA, in 2005. Is a teacher at the University of Mascara - Algeria, since 2005. His research interests are in the field of image processing and optimization methods.
Khalifa Djemal
Received his diploma degree in Optical, Image and Signal Processing in 1999 from the National School of Physics at the University of Marseille, France and his Ph.D. in Image and Signal Processing, 2002, from the University of Toulon, France. Since 2003, he is an Associate Professor at the Electrical Engineering Department of the Institute of Technology at the University of Evry Val d’Essonne, France. He works now within the S.I.M.O.B team of the IBISC Laboratory. His current research interests are in the areas of image and data processing (Restoration, Segmentation, Clusteringand CBIR). Dr. Djemal chaired the International Conference on Image Processing Theory, Tools and Applications IPTA, in 2008, 2010 and 2012, and also International Workshop on Medical Image Analysis and Description for Diagnosis Systems, MIAD, in 2009, 2010 and 2011. He was the chair of some special sessions in a number of conferences. He acted as technical chairman for a number of conferences. He is a reviewer for a number of international journals and conferences.
Mohamed Benyettou
Is a professor in department of computer science, University of Sciences and Technologies Mohamed Boudiaf USTO, ORAN-ALGERIA. He’s also a director of laboratory of modeling and optimization LAMOSI, his main research interests include: artificial intelligence, image processing, optimization methods…
Mohammed Debakla
Is a PhD student in computer Science University of Science and Technology of Oran (USTO) - ALGERIA. He received the diploma of engineering in Computer Science from the University of Oran (USTO) - ALGERIA in 1996. He received the diploma of teaching in Computer Science from the University of Oran (USTO) - ALGERIA, in 2005. Is a teacher at the University of Mascara - Algeria, since 2005. His research interests are in the field of image processing and optimization methods.
Khalifa Djemal
Received his diploma degree in Optical, Image and Signal Processing in 1999 from the National School of Physics at the University of Marseille, France and his Ph.D. in Image and Signal Processing, 2002, from the University of Toulon, France. Since 2003, he is an Associate Professor at the Electrical Engineering Department of the Institute of Technology at the University of Evry Val d’Essonne, France. He works now within the S.I.M.O.B team of the IBISC Laboratory. His current research interests are in the areas of image and data processing (Restoration, Segmentation, Clusteringand CBIR). Dr. Djemal chaired the International Conference on Image Processing Theory, Tools and Applications IPTA, in 2008, 2010 and 2012, and also International Workshop on Medical Image Analysis and Description for Diagnosis Systems, MIAD, in 2009, 2010 and 2011. He was the chair of some special sessions in a number of conferences. He acted as technical chairman for a number of conferences. He is a reviewer for a number of international journals and conferences.
Mohamed Benyettou
Is a professor in department of computer science, University of Sciences and Technologies Mohamed Boudiaf USTO, ORAN-ALGERIA. He’s also a director of laboratory of modeling and optimization LAMOSI, his main research interests include: artificial intelligence, image processing, optimization methods…
