Distslct img

From Eigenvector Research Documentation Wiki
Revision as of 10:30, 29 September 2009 by imported>Scott (New page: ===Purpose=== Selects samples on outside of data space for images. ===Synopsis=== :isel = distslct_img(varargin) :isel = distslct_img(x,nosamps,flag) ===Description=== This is an image-rea...)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Purpose

Selects samples on outside of data space for images.

Synopsis

isel = distslct_img(varargin)
isel = distslct_img(x,nosamps,flag)

Description

This is an image-ready version of the DISTSLCT function. It is called exactly as the basic function except that an image can be passed into it and image-formatted output is returned. Inputs are the X by Y by N image matrix (x) (class "double") and the number of samples to select (nosamps). If nosamps<N then STDSLCT selects all samples otherwise a distance measure is used to get the remaining samples. Optional input (flag) indicates how many samples STDSSLCT should select (when nosamps>=N): flag = 1: STDSSLCT selects N-1 flag = 2: STDSSLCT selects N {default} Output of this function is a two column array (isel) representing the x and y indices of the selected pixel(s). Note that if (x) is an image dataset, it could alternatively be passed to the standard distslct version as-is. The result will be the single-element index into the unfolded image. This may be more useful in some circumstances.

See Also

distslct