Skip to Main Content
There are many interference noise in industrial site, it affect the image quality of industry seriously. In view of these question, this paper demonstrate a wavelet image denoising algorithm based on local Wiener filtering with directional windows to replace the traditional denoising methods. Consider the direction of each wavelet sub-band, this algorithm use different shapes of the neighborhood window in different sub-band to estimated the variance of wavelet coefficients, the algorithm is applied to the detection of the blast furnace's looking-fire-hole image. Experimental results show that the proposed method obtain good results in both the Gaussian image denoising and keep the details of image.