Abstract: Image Segmentation is a fundamental and challenging problem in computer vision and medical image analysis. In spite of several decades of research and many key advances and several challenges still remain in this area. The evolution of contour is governed by three types of information (i) appearance (ii) boundary edgeness and (iii) shape each of which is incorporated as clique potential into MAP-MRF problem. The evolution of the contour is performed by iteratively solving a MAP-MRF labeling problems described by the non linear function. Then a genetic algorithm is used to find the result without converting non linear to linear function. The proposed method is a new model for segmentation contour explicitly as a chain of control point is implemented of medical image segmentation in non contrast computed tomography data.
Keywords: Markov random fields, active contour, genetic algorithm.
Title: MRF Based Contour Evolution of Non-Contrast Medical Image by Genetic Segmentation Algorithm
Author: M. Sahayini Derancy, R.L. Bhargavi
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Research Publish Journals
