MLS_SHORT
Section: User Commands (1)
Updated: 8th May 1985
Index
Return to Main Contents
NAME
mls_short - suppress random noise in an image (short format)
SYNOPSIS
mls_short
[bigsize [smallsize]] [-pN]
DESCRIPTION
mls_short uses maximum likelihood smoothing technique to suppress random
noise in an image.
The option bigsize is an integer which specifies the length of the side
of the window in which mls_short is computed and defaults to 3.
The option smallsize is an integer which specifies the length of the side
of the windows which make up the original window, to find the window with the
greatest concentration of the nearest neighbours. It defaults to (bigsize
+ 1) / 2.
N is an integer which specifies the percentage of the nearest
neighbours in the original window which have the closest gray levels to that
of the central pixel and it defaults to 62. The input pixel format must be
short integers.
See S.L.Hurt and A.Rosenfeld, "Noise Reduction in Three-Dimensional Digital
Images", Pattern Recognition, Vol.17, No.4, pp407-421, (1984).
SEE ALSO
mean(1), nns(1), sas(1), median(1)
AUTHOR
Peter Mowforth and Jin Zhengping - 8/5/1985
version to handle short format: Brian Tierney, LBL
Index
- NAME
-
- SYNOPSIS
-
- DESCRIPTION
-
- SEE ALSO
-
- AUTHOR
-
This document was created by
man2html,
using the manual pages.
Time: 01:45:15 GMT, December 05, 2024