Images observed in medical science have a greater amount of noise components. These noise components arise during the practice of collection, acquisition,and transmission. The minimization or elimination of noise is vital since it will affect the subsequent process like segmentation,classification,and compression. The main ideology of image denoising is to retain the original image without any noise from the noise corrupted image, and also to hold the detailed information at the maximum extent. In this reserach work, cuckoo search optimization technique with Non-linear Zernike filter was proposed for the filtering of medical images, where the noise present in the noisy image is optimized and filtered efficiently by employing a non-linear Zernike filter. The optimized features are fed to the backpropogation neural network for the generation of a denoised image. The quality of the image is measured by Peak signal to noise ratio (PSNR), Root Mean Square Error (RMSE).
Volume 11 | 06-Special Issue
Pages: 918-930