mia-2dsegment-fuzzyw

Sysnopis:

mia-2dsegment-fuzzyw {-i io} [ options ...]

Description:

This program is a implementation of a fuzzy c-means segmentation algorithm

Options:

File I/O

-i, --in-file=(input, required); io

image to be segmented. For supported file types see Plugin type: 2dimage/io

-c, --cls-file=(output); io

class probability images, the image type must support multiple images and floating point values. For supported file types see Plugin type: 2dimage/io

-o, --out-file=(output); io

B-field corrected image. For supported file types see Plugin type: 2dimage/io

-g, --gain-log-file=(output); io

Logarithmic gain field, the image type must support floating point values. For supported file types see Plugin type: 2dimage/io

Help & Info

-V, --verbose=warning; dict

verbosity of output, print messages of given level and higher priorities. Supported priorities starting at lowest level are:

info:Low level messages
trace:Function call trace
fail:Report test failures
warning:Warnings
error:Report errors
debug:Debug output
message:Normal messages
fatal:Report only fatal errors
--copyright=(); bool

print copyright information

-h, --help=(); bool

print this help

-?, --usage=(); bool

print a short help

--version=(); bool

print the version number and exit

Processing

--threads=-1; int

Maxiumum number of threads to use for processing,This number should be lower or equal to the number of logical processor cores in the machine. (-1: automatic estimation).

Segmentation parameters

-n, --no-of-classes=3; uint

number of classes to segment

-C, --class-centres=

initial class centers

-N, --neighborhood=shmean:shape=8n; factory

neighborhood filter for B-field correction. For supported plug-ins see Plugin type: 2dimage/filter

-a, --alpha=0.7; float

weight of neighborhood filter for B-field correction

-p, --fuzziness=2; float

parameter describing the fuzzyness of mattar distinction

-e, --epsilon=0.01; float

Stopping criterion for class center estimation.

Example:

Run a 5-class segmentation over inpt image input.v and store the class probability images in cls.v.

mia-2dsegment-fuzzyw -i input.v -a 5 -o cls.v

Author(s):

Gert Wollny