Stochastic permutation ordering watershed

International audience ; The stochastic watershed is a morphological approach to segmentation that repeats the application of a seeded watershed from series of uniform random markers. The obtained watershed boundaries are combined to construct a probability density function. We propose an alternative approach called stochastic permutation ordering watershed. Our approach relies on the construction of several permutation orderings of the pixels of an image, starting from a random pixel and using a dedicated Hamiltonian path construction on a graph. From the permutation orderings, several seeded watersheds are applied and averaged. In contrast to the stochastic watershed, our approach enables to take into account any features associated to pixels, such as patches, of prime important to segment textured images. Experimental results show the benefit of the approach.