To improve the performance of the adaptive filter, a new algorithm has been developed that adds to the basic one the advantage of operating, when necessary, with a smaller window, near and in the presence of small detail areas that, by doing increasing the local variance increases the ratio with the noise variance, beyond a certain threshold (supplied to the filter as an argument).
If the ratio between the variances exceeds this threshold, the algorithm tries to check whether by decreasing the filter size, for that point, the ratio drops back below the threshold and, in this case, applies the basic formula. Otherwise the filter dimensions will continue to decrease until the minimum size (3x3) is reached. It then proceeds to check the value of the ratio of the variances and, if it is greater than 1, always applies the basic formula, replacing, otherwise, the value of the current pixel with the average of the 3x3 around it.
The results obtained with the described procedure are remarkable in terms of image cleanliness and respect for details.
Citation pour cette source
Antonello Meloni (2024). imadvfilter2 (https://www.mathworks.com/matlabcentral/fileexchange/71716-imadvfilter2), MATLAB Central File Exchange. Récupéré le .
Compatibilité avec les versions de MATLAB
Plateformes compatibles
Windows macOS LinuxCatégories
- Image Processing and Computer Vision > Image Processing Toolbox > Image Filtering and Enhancement > Image Filtering >
Tags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Découvrir Live Editor
Créez des scripts avec du code, des résultats et du texte formaté dans un même document exécutable.
Version | Publié le | Notes de version | |
---|---|---|---|
1.1.2 | Debug |
||
1.1.1 | Updated function "stima" for RGB images |
||
1.1.0 |