Note: A new GRASS GIS stable version has been released: GRASS GIS 7. Go directly to the new manual page here

NAME

KEYWORDS

SYNOPSIS

Flags:

-q

Quiet

-a

Angular Second Moment

-c

Contrast

-k

Correlation

-v

Variance

-i

Inverse Diff Moment

-s

Sum Average

-w

Sum Variance

-x

Sum Entropy

-e

Entropy

-d

Difference Variance

-p

Difference Entropy

-m

Measure of Correlation-1

-n

Measure of Correlation-2

-o

Max Correlation Coeff

--overwrite

Allow output files to overwrite existing files

--verbose

Verbose module output

--quiet

Quiet module output

Parameters:

input=name

Name of input raster map

prefix=string

Prefix for output raster map(s)

size=value

The size of sliding window (odd and >= 3)

Default: 3

distance=value

The distance between two samples (>= 1)

Default: 1

DESCRIPTION

r.texture assumes grey levels ranging from 0 to 255 as input. The input has to be rescaled to 0 to 255 beforehand if the input map range is outside of this range by using r.rescale.

In general, several variables constitute texture: differences in grey level values, coarseness as scale of grey level differences, presence or lack of directionality and regular patterns. A texture can be characterized by tone (grey level intensity properties) and structure (spatial relationships). Since textures are highly scale dependent, hierarchical textures may occur.

r.texture reads a GRASS raster map as input and calculates textural features based on spatial dependence matrices for north-south, east-west, northwest, and southwest directions using a side by side neighborhood (i.e., a distance of 1). The user should be sure to carefully set the resolution (using g.region) before running this program, or the computer may run out of memory. The output consists into four images for each textural feature, one for every direction.

A commonly used texture model is based on the so-called grey level co-occurrence matrix. This matrix is a two-dimensional histogram of grey levels for a pair of pixels which are separated by a fixed spatial relationship. The matrix approximates the joint probability distribution of a pair of pixels. Several texture measures are directly computed from the grey level co-occurrence matrix.

The following part offers brief explanations of texture measures (after Jensen 1996).

First-order statistics in the spatial domain

• Sum Average (SA)
• Entropy (ENT): This measure analyses the randomness. It is high when the values of the moving window have similar values. It is low when the values are close to either 0 or 1 (i.e. when the pixels in the local window are uniform).
• Difference Entropy (DE)
• Sum Entropy (SE)
• Variance (VAR): A measure of gray tone variance within the moving window (second-order moment about the mean)
• Difference Variance (DV)
• Sum Variance (SV)

Second-order statistics in the spatial domain

• Angular Second Moment (ASM, also called Uniformity): This is a measure of local homogeneity and the opposite of Entropy. High values of ASM occur when the pixels in the moving window are very similar.
  Note: The square root of the ASM is sometimes used as a texture measure, and is called Energy.
• Inverse Difference Moment (IDM, also called Homogeneity): This measure relates inversely to the contrast measure. It is a direct measure of the local homogeneity of a digital image. Low values are associated with low homogeneity and vice versa.
• Contrast (CON): This measure analyses the image contrast (locally gray-level variations) as the linear dependency of grey levels of neighboring pixels (similarity). Typically high, when the scale of local texture is larger than the distance.
• Correlation (COR): This measure analyses the linear dependency of grey levels of neighboring pixels. Typically high, when the scale of local texture is larger than the distance.
• Information Measures of Correlation (MOC)
• Maximal Correlation Coefficient (MCC)

NOTES

EXAMPLE

g.region rast=ortho_2001_t792_1m -p
r.texture -a ortho_2001_t792_1m prefix=ortho_texture

# display
g.region n=221461 s=221094 w=638279 e=638694
d.shadedmap drape=ortho_texture_ASM_0 rel=ortho_2001_t792_1m

BUGS

- The method for finding the maximal correlation coefficient, which requires finding the second largest eigenvalue of a matrix Q, does not always converge. This is a known issue with this measure in general.

REFERENCES

The code was taken by permission from pgmtexture, part of PBMPLUS (Copyright 1991, Jef Poskanser and Texas Agricultural Experiment Station, employer for hire of James Darrell McCauley). Manual page of pgmtexture.

• Haralick, R.M., K. Shanmugam, and I. Dinstein (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6):610-621.
• Bouman, C. A., Shapiro, M. (1994). A Multiscale Random Field Model for Bayesian Image Segmentation, IEEE Trans. on Image Processing, vol. 3, no. 2.
• Jensen, J.R. (1996). Introductory digital image processing. Prentice Hall. ISBN 0-13-205840-5
• Haralick, R. (May 1979). Statistical and structural approaches to texture, Proceedings of the IEEE, vol. 67, No.5, pp. 786-804
• Hall-Beyer, M. (2007). The GLCM Tutorial Home Page (Grey-Level Co-occurrence Matrix texture measurements). University of Calgary, Canada

SEE ALSO

AUTHORS

Last changed: $Date: 2011-11-27 06:07:24 -0800 (Sun, 27 Nov 2011) $

Main index - raster index - Full index

© 2003-2016 GRASS Development Team