Texture

From Eigenvector Research Documentation Wiki
Revision as of 20:15, 29 September 2009 by imported>Scott (→‎Inputs)
Jump to navigation Jump to search

Purpose

Run texture analysis on an image or group of images.

Synopsis

[y,varargout]= texture(img, method, options, varargin)

Description

TEXTURE will perform an analysis on any 2 dimensional (m x n pixels) layer of an image or group of images. It loops through input 'img' where mode 3 is considered the variables (slabs of an image) mode and mode 4 is considered the images mode. Any additional inputs to the chosen 'method' must be added after the options input.

Outputs are 'y' a dataset with each row corresponding to an image and varargout containing any secondary output from the selected method. Outputs for a 'method' must be designated by the user with options.numout. Outputs will be appended together forming one row vector per image. E.G. for 'anglemt' if options.numout = [2 1] then the y{2} and y{1} outputs of 'anglemt' will be concatenated to form the row. Only the first output of a function is used. If there is a second output of a function it is assigned to varargout.

Aggregation can be performed across variables (slabs/layers) and or across images. For example, setting options.varmode = 'sum' will sum the layer of an image into one layer.

Inputs

  • img = image data (matrix or DataSet). The first two modes must be pixels, the third mode must be variables, and the fourth mode must be images.
  • method = texture method ('anglemt' 'autocor_img' 'svd_texture' 'fft_texture' 'semivar').

Optional Inputs

  • varargin = additional input needed for selected 'method'.

Outputs

  • firstout = first output is this.
  • y = dataset where each row (spectra) corresponds to an image.
  • varargout = second ouput of a function (e.g. for anglemt this would be 's', the distance scales). Will transform into row vector of cells.

Options

options = a structure array with the following fields:

  • numout: [{1}] 1xK vector. Number and order of outputs from selected 'method' to use.
  • imgmode: [ {'none'} | 'sum' | 'mean' ] aggregation across images.
  • varmode: [ {'none'} | 'sum' | 'mean' ] aggregation across variables.

TEXTURE FUNCTION SUB-STRUCTURES These options can be assigned in their nested form. See the particular function for a full description of available options. For example:

options.anglemt.xscale = [1:100];

See Also

anglemt, autocor_img, detrend_img, fft_texture, semivar, svd_texture