Man page or keyword search:   man All Sections 1 - General Commands 2 - System Calls 3 - Subroutines, Functions 4 - Special Files 5 - File Formats 6 - Games and Screensavers 7 - Macros and Conventions 8 - Maintenence Commands 9 - Kernel Interface New Commands Server 4.4BSD AIX Alpinelinux Archlinux Aros BSDOS BSDi Bifrost CentOS Cygwin Darwin Debian DigitalUNIX DragonFly ElementaryOS Fedora FreeBSD Gentoo GhostBSD HP-UX Haiku Hurd IRIX Inferno JazzOS Kali Knoppix LinuxMint MacOSX Mageia Mandriva Manjaro Minix MirBSD NeXTSTEP NetBSD OPENSTEP OSF1 OpenBSD OpenDarwin OpenIndiana OpenMandriva OpenServer OpenSuSE OpenVMS Oracle PC-BSD Peanut Pidora Plan9 QNX Raspbian RedHat Scientific Slackware SmartOS Solaris SuSE SunOS Syllable Tru64 UNIXv7 Ubuntu Ultrix UnixWare Xenix YellowDog aLinux   8420 pages apropos Keyword Search (all sections) Output format html ascii pdf view pdf save postscript

Pgmtexture User Manual(0)			     Pgmtexture User Manual(0)

NAME
       pgmtexture - calculate textural features on a PGM image

SYNOPSIS
       pgmtexture

       [-d d]

       [pgmfile]

DESCRIPTION
       This program is part of Netpbm(1).

       pgmtexture  reads a PGM image as input and calculates textural features
       based on spatial dependence matrices at 0, 45, 90, and 135 degrees  for
       a distance d (default = 1).

       Textural features include:

       ·      Angular Second Moment

       ·      Contrast

       ·      Correlation

       ·      Variance

       ·      Inverse Difference Moment

       ·      Sum Average

       ·      Sum Variance

       ·      Sum Entropy

       ·      Entropy

       ·      Difference Variance

       ·      Difference Entropy

       ·      Information Measures of Correlation

       ·      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.

LIMITATIONS
       The  program can run incredibly slow for large images (larger than 64 x
       64) and command line options are limited.  The method for  finding  the
       Maximal	Correlation  Coefficient,  which  requires  finding the second
       largest eigenvalue of a matrix Q, does not always converge.

SEE ALSO
       pgm(1), pamsharpness(1), pamsharpmap(1), pgmedge(1), pgmminkowski(1)

AUTHOR
       Copyright (C) 1991 by Texas Agricultural Experiment  Station,  employer
       for hire of James Darrell McCauley.

netpbm documentation		  22 Aug 1991	     Pgmtexture User Manual(0)

Vote for polarhome