Adaptive segmentation of textures using mathematical morphology

The authors define a recursive morphological decomposition algorithm using a group of structuring elements of different sizes. The algorithm decomposes a texture image into a series of images according to their primitive sizes and gray levels. In order to segment accurately the boundaries of adjacent regions, an adaptive technique is proposed based on Bayes error estimation to determine the size of the window over which texture features are extracted. Thus, window size varies according to its position in image and to the textures to be segmented. Experimental results are given