# Name

filt_median - Calculate the median filtered image.

# Usage

output = filt_median(input, nxk, nyk, nzk, kernelshape = "BLOCK")

## Input

- input
- input image
- nxk, nyk, nzk
- Size of the kernel on each dimension.
- They have to be odd so that the center of kernal can be well defined.
- Note: For CIRCULAR kernel, we currently only allow circle or sphere kernel, i.e., nxk and nyk must be same for 2 dimensional image and nxk, nyk and nzk must be same for 3 dimensional image.

- kernelshape
- Shape of the kernel
- BLOCK is for block kernel (DEFAULT);
- CIRCULAR is for circular kernel;
- CROSS is for cross kernal;
- Note: For 1-dimensional image, these three kernels degenerate into the same shape.

## Output

- output
- median filtered image

# Method

# Reference

# Author / Maintainer

Pawel A. Penczek

# Keywords

- category 1
- FILTER
- category 2
- SPATIAL, NONLINEAR

# Files

filter.py

# See also

# Maturity

- stable
- works for most people, has been tested; test cases/examples available.

# Bugs

None. It is perfect.