Abstract
In this work an image de-noising method with external bilateral filtering and wavelet domain thresholding has been proposed. In gaussian filtering fails to denoise an image at edges where the spatial variations are not smooth and cause the blurs the edges in the image. Bilateral filter overcomes this by filtering the image in both range and domain (space). Bilateral filtering is a local, nonlinear and non-iterative technique which considers both gray level (color) similarities and geometric closeness of the neighboring pixels. With bilateral filter the approximation sub-band results in loss of some image details, whereas that after each level of wavelet reconstruction flattens the gray levels cause unpleasing output image. To overcome the above issue extension of bilateral filtering with introduction of wavelets for thresholding has been proposed. Instead of direct filtering or direct wavelet domain thresholding of noisy image, the proposed method first obtains the filtered version of image using bilateral filtering and then this filtered version of image undergoes to wavelet domain thresholding using Bayes-shrink rules. In this approach the advantages of both the methods are achieved. To check the effectiveness of the proposed method in image denoising, we have compared the results with recent image denoising methods.
Recommended Citation
Parihar, Sumit Singh and Khaparkar, Shailesh
(2024)
"External Filtering and Wavelet Domain Thresholding-based Denoising Method for AWGN corrupted images,"
American Journal of Science & Engineering (AJSE): Vol. 2:
Iss.
2, Article 4.
Available at:
https://research.smartsociety.org/ajse/vol2/iss2/4