Two-dimensional gray-scale clustering for texture analysis

To develop a new quantitative method for the visual discrimination of image texture.

Two kinds of image phantoms were prepared, one for evaluating the effects of change in size and gray values of individual pixels (primitives) on perceived coarseness and the other for evaluating changes in groups of pixels (clusters) on perceived heterogeneity. The phantom images were displayed on a CRT and presented to 11 observers who assessed heterogeneity and coarseness on a 10-point scale between -5 and +5. On the basis of the observers' results, a new texture analysis method termed two-dimensional gray-scale clustering analysis was developed and applied to measure quantitatively the texture of the phantoms. The results obtained were then compared with those of the visual evaluation.

The size of the primitives and the clusters greatly affected the visual evaluation of heterogeneity and coarseness. Changes in the gray value had only a slight effect. The intra-observer variation for heterogeneity was significantly larger than that for coarseness. Two-dimensional gray-scale clustering analysis could differentiate heterogeneity from coarseness. A high correlation was obtained between the visual evaluation and the quantitative data.

Quantitative two-dimensional gray-scale clustering analysis appears to be a useful means of texture analysis.