K-Means Clustering Dialog Box (Image Tool)
Perform image segmentation using
K-Means clustering based on regional statistical measures of the mean, mode, minimum, maximum, range, and/or value of the image pixels.
Region Seeds—A list of selected pixel elements from the image. These are used as the seed points with which individual clusters are identified. Click on the image to select region seeds.
Edit Value—Edit a selected region seed.
Fill Values—An array of values greater than 0 and less than or equal to the number of cluster seeds which are used to fill the clusters.
Edit Value—Edit a selected fill value.
Delete Selected Item—Delete a selected item from the Region Seeds or Fill Values list.
Clear List—Clear the Region Seeds and Fill Values lists.
Redraw—Redraws the selected seed points on the displayed image.
Max Iterations—The maximum iterations to use in the clustering algorithm. (Default: 30)
Fill with Cluster Mean—If set, clusters are filled with the mean value of the image pixels in that cluster.
Statistical Measures
Mean—If selected, clusters are filled with the mean value of the image pixels in that cluster.
Mode—If selected, the mode of each window in the image is used as a statistic for the clustering algorithm.
Min—If selected, the minimum of each window in the image is used as a statistic for the clustering algorithm.
Max—If selected, the maximum of each window in the image is used as a statistic for the clustering algorithm.
Range—If selected, the range of each window in the image is used as a statistic for the clustering algorithm.
Pixel Value—If selected, the pixel values in the image are used as a statistic for the clustering algorithm.
Create New Image—If this option is selected, the processed data is used to create a new image. Enter a suffix for the new image variable name in the text field provided.
Overwrite Image—If this option is selected, the current image is overwritten by the processed data.
Window Width—The window width used for computing the image statistics. (Default: 3)
Window Height—The window height used for computing the image statistics. (Default: 3)
Variable Suffix—If the Create New Image option is selected, enter a suffix for the new image variable name. This suffix is added to the original variable name.
OK—Perform clustering and exit the dialog box.
Apply—Perform clustering, but do not exit the dialog box.
Cancel—Dismiss the dialog box without taking any action.
Help—Display online Help on the dialog box.
