**Name**

**mschannel** Build a multi-scales multi-channels decomposition of an image

**Command Synopsis**

**mschannel** [-N *N*] [-S *S*] [-W *W*] [-p *p*] *in* *mov*

-NN: # images per channel, default 1 (for local scale value)

-SS: standard deviation of the smoothing filter, default 1

-WW: pixel weight for the smoothing filter, default 1

-pp: scalar distance: ABS (p=1) or Quadratic (p=2,default)

in: input Fimage

mov: output Fmovie

**Function Summary**

void mschannel (N , S , W , p , in , mov )

int *N , *W , *S , *p ;

Fimage in ;

Fmovie mov ;

**Description**

This module build a multi-scales multi-channels representation of an image.

The aim of the algorithm is to create channels so as they can be used with *msegct* module in order to find the segmentation. We consider three kind of channels. Each channel correponds to a direction of a quadratic difference if *p* is set to 2 (default) or a simple difference in absolute value if *(p=1)*. More over we consider different scale for each channel.

Let *e* the local scale, and *N* the number of channels per direction that the user wants to reach. So for each local scale we have three channels.
Let *I*_{m, n} the value of the original image's pixel (input Fimage).
From the original image we calculate the channels (Fimage) associated with the value of the local scale :

For *e* = 1 we have :

Horizontal Channel :
*H*_{m, n}^{(e=1)} = (*abs*(*I*_{m+1, n} - *I*_{m, n})^{p} + *abs*(*I*_{m-1, n} - *I*_{m, n})^{p})/2

Vertical Channel :*V*_{m, n}^{(e=1)} = (*abs*(*I*_{m, n+1} - *I*_{m, n})^{p} + *abs*(*I*_{m, n-1} - *I*_{m, n})^{p})/2

Diagonal Channel :*V*_{m, n}^{(e=1)} = (*abs*(*I*_{m+1, n+1} - *I*_{m, n})^{p} + *abs*(*I*_{m-1, n-1} - *I*_{m, n})^{p})/2

Those three channels correspond to the 3 images of the fmovie associeted with the first local scale Vertical Channel :

Diagonal Channel :

Horizontal Channel :
*H*_{m, n}^{(e > 1)} = (*abs*( - )^{p} + *abs*( - )^{p})/2

Vertical Channel :*V*_{m, n}^{(e > 1)} = (*abs*( - )^{p} + *abs*( - )^{p})/2

Diagonal Channel :*V*_{m, n}^{(e > 1)} = (*abs*( - )^{p} + *abs*( - )^{p})/2

is the original fimage convolved with splitable blur filter of size Vertical Channel :

Diagonal Channel :

At least, all the channels are smoothed with a type of binomial filter. For that reason, the user needs to enter the standard deviation

**See Also**

**Version 1.3**

Last Modification date : Thu Nov 29 20:23:56 2001

**Author**

Yann Guyonvarc'h