NAME

i.texture - calculate textural features on a raster file
(GRASS Image Processing Program)

SYNOPSIS

i.texture
i.texture help
i.texture rast=name

DESCRIPTION

Reads a GRASS raster map as input. Calculates textural features based on spatial dependence matrices for north-south, east-west, northwest, and southwest directions using a 3x3 neighborhood (i.e., a distance of 1). Writes to standard output. Be sure to carefully set your resolution (using g.region) before running this program, or else your computer could run out of memory. Also, make sure that your raster map has no more than 255 categories.

OPTIONS

Parameter:

rast=name
Raster map name.

NOTES

Textural features include:
  1. Angular Second Moment,
  2. Contrast,
  3. Correlation,
  4. Variance,
  5. Inverse Difference Moment,
  6. Sum Average,
  7. Sum Variance,
  8. Sum Entropy,
  9. Entropy,
  10. Difference Variance,
  11. Difference Entropy,
  12. Information Measure of Correlation,
  13. Another Information Measure of Correlation, and
  14. Maximal Correlation Coefficient.
Algorithm taken from:
Haralick, R.M., K. Shanmugam, and I. Dinstein. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybertinetics, SMC-3(6):610-621.

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).

BUGS

The program can run incredibly slow for large raster files (larger than 64 x 64) and command line options are limited.

The method for finding (14) the maximal correlation coefficient, which requires finding the second largest eigenvalue of a matrix Q, does not always converge.

It would be interesting to write raster files to map features for neighborhoods, with some sort of quantization to record category values. This may be useful for image classification schemes, but this exercise is left to the reader (the changes would be fairly trivial).

REFERENCES

IEEE Transactions on Systems, Man, and Cybertinetics, SMC-3(6):610-621.

SEE ALSO

g.region
r.reclass

AUTHOR

James Darrell McCauley, Agricultural Engineering, Purdue University