Brain Image Segmentation Using Artificial Bee Colony Optimization And Markovian Potts Model

In this paper, we propose a segmentation model using MRF (Markov Random Fields) and a global optimization method based on ABC (Artificial Bee Colony) algorithm. As a Markovian algorithm, ICM (Iterated Conditional Modes) is an iterative method which takes into account the neighboring labels of the pixel in calculating the energy function that need to be minimized to obtain the best segmentation. To improve this local method in term of energy function optimization, ABC is so introduced knowing its robustness especially in discrete multivariable optimization problems. The contribution of this work is to propose MRF-ABC algorithm that consists of using ABC to optimize a Potts energy function, after an ICM initialization, in order to improve image segmentation quality. The whole algorithm is evaluated on MRI (Magnetic Resonance Images) and experimental results show the efficiency of the proposed approach.