Table Of Contents

Extract Texture Feature (G Dataflow)

Last Modified: October 26, 2017

Extracts texture features from the image.

Features are extracted by computing the wavelet bands from the image and then computing co-occurrence Haralick features from the extracted bands. The features are extracted within a specified window and the window is moved across the image from the top-left to the right-bottom corner.

connector_pane_image
datatype_icon

ROI descriptor

Region of the image in which to extract the texture features.

datatype_icon

global rectangle

Coordinates of the bounding rectangle.

datatype_icon

contours

Individual shapes that define an ROI.

datatype_icon

ID

Object specifying if contour is the external or internal edge of an ROI.

datatype_icon

Type

Shape type of the contour.

datatype_icon

Coordinates

Relative position of the contour.

datatype_icon

image in

Reference to the source image.

datatype_icon

window options

Options for the window from which features are extracted and specifies how the window is moved across the image.

datatype_icon

sizeX

Size of the window in the x dimension.

The size must be at least 3 and cannot be larger than the width of image in.

datatype_icon

sizeY

Size of the window in the y dimension.

The size must be at least 3 and cannot be larger than the height of image in.

datatype_icon

step size

Amount by which the window is moved across the image in the horizontal and vertical direction.

If the value is 0, the window is moved across the image with no overlap.

datatype_icon

wavelet options

Input that specifies how the node extracts the wavelet bands used to compute texture features.

datatype_icon

type

Wavelet type to use for the discrete wavelet analysis.

The options include two types of wavelets, orthogonal and biorthogonal. The following table describes the wavelet types and provides information for selecting a wavelet type.

Type Name Abbreviation Notes
Orthogonal Wavelets Haar - Orthogonal wavelets are not redundant and are suitable for image denoising and compression.
Daubechies dbxx
Coiflets coifx
Symmlets symx
Biorthogonal Wavelets -
x indicates the order of the wavelet. A higher order indicates a smoother, more regular, wavelet.

Default: db02

datatype_icon

wavelet bands to use

Wavelet bands to use for feature extraction.

If no band is selected, all bands are used. The following wavelet bands are available:

  • Low Low
  • Low High
  • High Low
  • High High
  • Low Low Low
  • Low Low High
  • Low High Low
  • Low High High
datatype_icon

min energy level

Minimum amount of energy that should be present in the wavelet bands that are used.

If this control is set to 100, all bands are used. This control is ignored if a wavelet band is selected using wavelet bands to use.

datatype_icon

co-occurrence options

Options for computing the co-occurrence matrix of each window in the image.

The Haralick features are then extracted from the co-occurrence matrix.

datatype_icon

level

Number of gray levels the image is quantized to before the co-occurrence matrix is computed.

The larger this value, the longer the node will take to compute the matrix.

datatype_icon

displacement vector

Distance of the neighboring pixels to consider when computing the co-occurrence matrix.

datatype_icon

xDelta

Distance in the horizontal direction.

datatype_icon

yDelta

Distance in the vertical direction.

datatype_icon

error in

Error conditions that occur before this node runs.

The node responds to this input according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error error in contains an error
If no error occurred before the node runs, the node begins execution normally.

If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.

If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Default: No error

datatype_icon

use window

Output that, if true, ignores window options and treats the entire image as one region.

datatype_icon

image out

Reference to the source image.

datatype_icon

texture feature

2D array that contains the extracted feature.

The number of rows in the array corresponds to the number of windows used in the image.

datatype_icon

wavelet bands used

Wavelet bands used to compute the features.

datatype_icon

error out

Error information.

The node produces this output according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error error in contains an error
If no error occurred before the node runs, the node begins execution normally.

If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.

If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Where This Node Can Run:

Desktop OS: Windows

FPGA: Not supported

Web Server: Not supported in VIs that run in a web application


Recently Viewed Topics