Research on Image Technology with Application of K-Means Based on Genetic Simulated Annealing Algorithm in CT Image Segmentation

Abstract:

Aiming at the characteristic of medical images, this paper presents the improved genetic simulated annealing algorithm with K-means clustering analysis and applies in medical CT image segmentation. This improved genetic simulated annealing algorithm can be used to globally optimize k-means image segmentation functions to solve the locality and the sensitiveness of the initial condition. It can automatically adjust the parameters of genetic algorithm according to the fitness values of individuals and the decentralizing degree of individuals of the population and keep the variety of population for rapidly converging, and it can effectively avoid appearing precocity and plunging into local optimum. The example shows that the method is feasible, and better segmentation results have got to satisfy the request for 3D reconstruction, compared with k-means image segmentation and genetic algorithm based image segmentation.

• Periodical: Advanced Materials Research (Volume 1022)
• Pages: 269-272
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1022.269
• Online since: August 2014
• Authors: Ling Li Zhu*, Lan Wang
• Keywords: Genetic Simulated Annealing Algorithm, Image Segmentation, K-Means

References

[1] J.P. Marques de Sa. Pattern Recognition Concepts, Methods and Applications.

[2] H Chen, N S Flann. Parallel Simulated Annealing and Genetic Algorithms : A Space of Hybrid Methods[J]. Paralled Problem Solving from Nature 3. Springer-Verlag, 1994, 428～438.

DOI: 10.1007/3-540-58484-6_286

[3] J J Grefenstette. Incorporating Problem Specific Knowledge into Genetic Algorithms[M]. Davis L Ed. Genetic Algorithms and Simulated Annealing, Pitman, 1987, 42~60.

[4] YU Yao-jun, CHEN Jun, LI Jing. Design and Realization of On-line Examination System[J]. Computer Simulation, 2010; 27(6): 350～353.