Novel Approach for Gray Images Restoration and Enhancement Using Bacterial Foraging Algorithm:Application to Neutron Imaging
Slami Saadi, Maâmar Bettayeb, Abderrezak Guessoum · International Journal of Intelligent Computing in Medical Sciences & Image Processing · 2011
In this work we implemented a new optimal approach for image restoration problem, which is useful for restoring and enhancing neutron radiography gray images. Our approach is based on using swarm intelligence optimization algorithms to solve a least squares minimization ill-posed problem. To solve such minimization ill-posed problem, many works have been done introducing intelligence techniques ranging from neural networks, fuzzy logic and genetic evolutionary algorithm, to swarm intelligence that we used in our work based on Bacterial Foraging optimization (BFO) algorithm. Instead of the standard Tikhonov regularization method which is most often used and to get smoothed images in presence of noise, a Laplacian constraint is introduced for regularization purposes. Using some image quality metrics such as mean square error (MSE) and peak signal to noise ratio (PSNR), we can judge that the obtained results show that the proposed swarm intelligence algorithm can be applicable for image deblurring and noise removal.