Texture image segmentation: a local spectral mapping approach

A new scheme is developed for the extraction of local texture features. This scheme, defined as the local spectral mapping (LSM), transforms a textured image into a gray-level one. The power spectrum of a local region is divided into a number of rings and wedges, and local spectral vectors are formed by summing the energy in these rings or wedges as vector elements. Two new texture measures, the linear radial feature enhancement measure (LRFE) and the linear angular feature enhancement measure (LAEF), are designed. A segmentation algorithm is implemented and applied to a set of textured images. Good results are achieved, with more than 92% of the pixel population being correctly classified for each of the test images