Texture classification using features derived from random field models

Authors:
R. L. Kashyap;R. Chellappa;A. Khotanzad
Affiliations:
School of Electrical Engineering, Purdue University, West Lafayette, IN 47907, U.S.A.;Dept. of Electrical Engineering-Systems and Image Processing Institute, University of Southern California, Los Angeles, CA, U.S.A.;School of Electrical Engineering, Purdue University, West Lafayette, IN 47907, U.S.A.
Venue:
Pattern Recognition Letters
Year:
1982

Citing 4
Cited 0

Decorrelation Methods of Texture Feature Extraction

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Theoretical Comparison of Texture Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Maximum Likelihood Approach to Texture Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Empirical Evaluation of Generalized Cooccurrence Matrices

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper presents a new feature extraction method for classifying a texture image into one of the l possible classes C"i, i=1,...,l. It is assumed that the given M x M image characterized by a set of intensity levels, {y(s"1,S"2), 0@?s"s,s"2@?M-1}, is a realization of an underlying random field model, known as the Simultaneous Autoregressive Model (SAR). This model is characterized by a set of parameters @f whose probability density function p"i(@f), depends on the class to which the image belongs. First it is shown that the maximum likelihood estimate (M.L.E.) @f^*, of @f is an appropriate feature vector for classification purposes. The optimum Bayes classifier which minimizes the average probability of classification error, is then designed using @f^*. Finally the efficiency of the feature vector is demonstrated through experimental results obtained with some natural texture data and a simpler quadratic mean classifier.