KMeansClassification
Brief Description
Unsupervised KMeans image classification
Tags
Segmentation,Learning
Long Description
Performs unsupervised KMeans image classification.
Parameters
[param] -in
<string> Input image to classify.. Mandatory: True. Default Value: ""
[param] -out
<string> Output image containing the class indexes.. Mandatory: True. Default Value: ""
[param] -ram
<int32> Available memory for processing (in MB). Mandatory: False. Default Value: "128"
[param] -vm
<string> Validity mask. Only non-zero pixels will be used to estimate KMeans modes.. Mandatory: False. Default Value: ""
[param] -ts
<int32> Size of the training set (in pixels).. Mandatory: False. Default Value: "100"
[param] -nc
<int32> Number of modes, which will be used to generate class membership.. Mandatory: True. Default Value: "5"
[param] -maxit
<int32> Maximum number of iterations for the learning step.. Mandatory: False. Default Value: "1000"
[param] -ct
<float> Convergence threshold for class centroid (L2 distance, by default 0.0001).. Mandatory: False. Default Value: "0.0001"
[param] -outmeans
<string> Output text file containing centroid positions. Mandatory: False. Default Value: ""
[param] -rand
<int32> Set specific seed. with integer value.. Mandatory: False. Default Value: "0"
[param] -inxml
<string> Load otb application from xml file. Mandatory: False. Default Value: ""
[param] -outxml
<string> Save otb application to xml file. Mandatory: False. Default Value: ""
Limitations
None
Authors
OTB-Team
See Also
Example of use
in: QB_1_ortho.tif
ts: 1000
nc: 5
maxit: 1000
ct: 0.0001
out: ClassificationFilterOutput.tif