Application Analysis of Contourlet Transform in Image Denoising of Flue-Cured Tobacco Leaves

摘要

Image denoising is one of the most basic and important tasks in image processing when computer is used for quality inspection of flue-cured tobacco leaves. The Contourlet transform has the advantages of multiresolution, anisotropy. and sparsity. Wavelet denoising, median filter, mean filter, gaussian filter and wiener filter are used to conduct comparative experiments on tobacco leaf images so as to verify the denoising effect of Contourlet transform. It is showed that the image denoising method based on the Contourlet transform has the advantages of high signal-to-noise ratio and good visual effect when applied to tobacco image denoising, which is effective and feasible for image denoising of flue-cured tobacco.