CLIJ2

Logo

GPU accelerated image processing for everyone

CLIJ2 home

generateFeatureStack

Generates a feature stack for Trainable Weka Segmentation.

Use this terminology to specifiy which stacks should be generated:

Use sigma=0 to apply a filter to the original image. Feature definitions are not case sensitive.

Example: “original gaussianBlur=1 gaussianBlur=5 laplacianOfGaussian=1 laplacianOfGaussian=7 entropy=3”

Categories: Segmentation, Machine Learning

Usage in ImageJ macro

Ext.CLIJx_generateFeatureStack(Image input, Image feature_stack_destination, String feature_definitions);

Usage in object oriented programming languages

Java
// init CLIJ and GPU
import net.haesleinhuepf.clijx.CLIJx;
import net.haesleinhuepf.clij.clearcl.ClearCLBuffer;
CLIJx clijx = CLIJx.getInstance();

// get input parameters
ClearCLBuffer input = clijx.push(inputImagePlus);
feature_stack_destination = clijx.create(input);
// Execute operation on GPU
clijx.generateFeatureStack(input, feature_stack_destination, feature_definitions);
// show result
feature_stack_destinationImagePlus = clijx.pull(feature_stack_destination);
feature_stack_destinationImagePlus.show();

// cleanup memory on GPU
clijx.release(input);
clijx.release(feature_stack_destination);
Matlab
% init CLIJ and GPU
clijx = init_clatlabx();

% get input parameters
input = clijx.pushMat(input_matrix);
feature_stack_destination = clijx.create(input);
% Execute operation on GPU
clijx.generateFeatureStack(input, feature_stack_destination, feature_definitions);
% show result
feature_stack_destination = clijx.pullMat(feature_stack_destination)

% cleanup memory on GPU
clijx.release(input);
clijx.release(feature_stack_destination);

Back to CLIJ2 reference Back to CLIJ2 documentation

Imprint