Publication: Noise level reduction in digital images using anisotropic diffusion filter
Loading...
Date
2008-05-01
Authors
Mohamad Noh, Haidi Fazril
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Nowadays, the digital image processing field had impacted many fields around the world including medicine, printing and publishing. There are many devices that can be used to acquire a digital image, for example scanner, mobile phone and digital camera. However, during the acquisition of the digital image, noise will be introduced into the image. Images that are contaminated with noise will be difficult to analyze because the quality and the important features of the image has loss. Fortunately noise can be reduced by filtering. Common filters that are used nowadays are median filter and mean filter. Median and mean filter are approved to be effective in reducing impulse noise while preserving sharp edges and fine details in the filtered images. A method has been proposed in order to reduce images that are contaminated with uniform and Gaussian noise. The proposed method will reduce the noise level in the digital images while preserving the edges and fine details of the image. The method proposed is known as nonlinear anisotropic diffusion filter. Anisotropic diffusion filter is a filter that performs scale-space filtering using a diffusion process. The diffusion coefficient is chosen to encourage smoothing within a region in preference to smoothing across the boundaries. The anisotropic diffusion filter in this project is implemented using C++. The experimental result of this project is good evidence in order to prove that the anisotropic diffusion filter is effective in reducing noise in the digital images.