Some examples

Notes:
1. Shift-reload if any image is missing.
2. Compressed (tar.gz) source code and images. See readme


(a)

(b)

(c)

(d)

(e)

(f)
Figure 1: Example of adaptive Gaussian filtering. (a) A pine cone image corrupted with Gaussian noise, $sigma =40$. (b) Local scale map. (c) The output of 50 iterations of anisotropic diffusion, k=10. (d) The output of 80 iterations of anisotropic diffusion with k=10. (e) A chain of $sigma $-filters, see text for parameters. (f) The adaptive Gaussian filter.

 
 

(a)

(b)

(c)

(d)

(e)

(f)
Figure 2: Example of adaptive Gaussian filtering. (a) Lenna corrupted with Gaussian noise, $sigma =40$. (b) Local scale map. (c) The output of 60 iterations of anisotropic diffusion with k=10. (d) The output of 80 iterations of anisotropic diffusion with k=10. (e) A chain of $sigma $-filters, see text for parameters. (f) The adaptive Gaussian filter.

 
 

(a)

(b)

(c)

(d)

(e)

(f)
Figure 3: Example of adaptive Gaussian filtering. (a) A human colon image corrupted with Gaussian noise, $sigma =30$. (b) Local scale map. (c) The output of 100 iterations of anisotropic diffusion with k=10. (d) The output of 120 iterations of anisotropic diffusion with k=10. (e) A chain of $sigma $-filters, see text for parameters. (f) The adaptive Gaussian filter.

(a)

(b)

(c)

(d)

(e)

(f)
Figure 4: Example of adaptive Gaussian filtering. (a) A human colon image corrupted with Gaussian noise, $sigma =30$. (b) Local scale map. (c) The output of 100 iterations of anisotropic diffusion with k=10. (d) The output of 120 iterations of anisotropic diffusion with k=10. (e) A chain of $sigma $-filters, see text for parameters. (f) The adaptive Gaussian filter.