An analysis of co-occurrence texture statistics as a function of grey level quantization

TLDR

The study investigates how grey level quantization affects the classification performance of co‑occurrence probability statistics for natural textures. The authors use correlation analysis, Fisher linear discriminant classification, and a Fisher separability index, testing on Brodatz textures and two SAR sea‑ice datasets to evaluate co‑occurrence statistics. Classification accuracy generally declines with more grey levels for most statistics, though a preferred subset (contrast, correlation, entropy) outperforms single or full sets; when limited to one statistic, contrast, dissimilarity, inverse difference normalized, or inverse difference moment normalized are recommended, and look‑direction or all‑orientation averaging is preferred.

Abstract

In this paper, the effect of grey level quantization on the ability of co-occurrence probability statistics to classify natural textures is studied. Generally, as a function of increasing grey levels, many of the statistics demonstrate a decrease in classification ability while a few maintain constant classification accuracy. None of the individual statistics show increasing classification accuracy throughout all grey levels. Correlation analysis is used to rationalize a preferred subset of statistics. The preferred statistics set (contrast, correlation, and entropy) is demonstrated to be an improvement over using single statistics or using the entire set of statistics. If the feature space dimension only allows for a single statistic, one of contrast, dissimilarity, inverse difference normalized, or inverse difference moment normalized, is recommended. Testing that compares (using all orientations separately), the average of all orientations and look direction averaging, when determining the co-occurrence features, indicates that the look direction or all orientations is preferred. The Fisher linear discriminant method is used for all classification testing. The Fisher criterion is used as a separability index to provide insight into the classification results. Testing is performed on Brodatz imagery as well as two separate SAR sea-ice data sets.