Because of the disadvantages of Multi-resolution Markov random field in wave domain for the description of the nonlinear features of the image

this paper proposes a new Multi-resolution Markov random model in morphological wavelets domain to partition the texture images. Morphological wavelets can do a nonlinear multi-resolution decomposition of images. Markov random field can model the spatial relationship of pixels in each resolution. The multi-resolution Markov random model in morphological wavelets domain combines the benefits of morphological wavelets and Markov random field. The experiments of texture images segmentation validate of our model

where the test texture images are employed from the Brodatz and Prague texture image databases.