Development Of Framework For DeNoising The Medical Images Using Adaptive Wavelet Thresholding

Abstract

Digital image processing brought a tremendous revolution in many fields; medical newlinefield is one of them. Medical images are used to detect the abnormalities and diseases in newlinehuman body; simply by analyzing them. During the acquisition process; noise signals newlinemay introduce in these images which will impact negatively in the diagnosis process. newlineNoise signals degrade the image quality by suppressing useful information present in the newlineform of edges, fine structures, textures etc. Hence it is essential to suppress noise signals newlinebecause noisy image may lead to any false interpretation done by the radiologists. newlineSuppression of noise signals from the medical images is called Medical Image Denoising newlinewhich is an important pre-processing task. Some of the examples of medical newlineimages are magnetic resonance images, computed tomography images, ultrasound newlineimages, x-ray images etc. These images are affected by different noise signals e.g. newlinemagnetic resonance images are affected severely by rician noise, computed tomography newlineimages are corrupted by Gaussian noise while speckle noise is the inherent property of newlineultrasound images. In this thesis we have taken two most common medical images viz. newlinecomputed tomography images and ultrasound images. To remove noise signals; various newlinefilters have been proposed but no any of these methods can be used as a global de-noising newlinetechnique because any filter which can remove one noise effectively; fails to remove newlineothers. Hence it is necessary to develop such a filter which can remove many noise newlinesignals because any image may be corrupted by more than one noise. This requirement newlinemotivates the researchers to go ahead to achieve such goal. newlineIn our thesis; a novel framework has been proposed to de-noise the medical images; newlinewhich reduces the effect of various noise signals such as additive white Gaussian noise, newlinespeckle noise and mixed noise. It consists of various spatial domain filters viz. median newlinefilter, median modified Wiener filter and bilateral filter. It also uses adaptive wavelet newlinethresholding and total va

Description

Keywords

Citation

item.page.endorsement

item.page.review

item.page.supplemented

item.page.referenced