Texture Analysis using Local Property Maps

Morphological granulometry has been shown to be effective in a range of texture analysis applications. We describe an extension to the standard approach which allows truly local properties of the texture to be measured at each pixel. The result is a set of texture features which are analogous to those which could be measured for individual texture primitives, if they could be isolated. We demonstrate the ability of the method to estimate the known properties of the primitives in synthetic texture images and show that reasonably accurate results can be obtained over a range of practically useful conditions. We describe the application of the method to a difficult texture analysis problem grading the degree of osteoporosis in radiographs of the femoral neck and show that better results can be obtained than with either Laws' texture features or conventional granulometry.