Image segmentation is an essential processing step for many image analysis applications. So far, there does not exist a general method that is suitable for all the image analysis applications. In this paper, we propose a novel pixon-based multi-resolution method for image segmentation. The key idea to our approach is that a pixon-based image model is combined with a MRF model under a Bayesian framework. In our method, we put forward a new pixon definition scheme that is more suitable for image segmentation than the "fuzzy" pixon scheme. Experimental results demonstrate that our algorithm performs fairly well and the computational cost decreased sharply compared to the traditional MRF-based algorithm.
展开▼