MRF model based image segmentationusing hierarchical distributed genetic algorithm
Hang Joon Kim, Eun Yi Kim, Jin Wook Kim, Se Hyun Park · Electronics Letters · 1998
An unsupervised method for segmenting noisy and blurred images is proposed. A Markov random field (MRF) model is used which is robust to degradation. Since this is computationally intensive, a hierarchical distributed genetic algorithm (HDGA) is used which is unsupervised and parallel. Experimental results show that the proposed method is effective at segmenting real images.