Title :
Optimal Multilevel Thresholding using Improved Gravitational Search Algorithm for Image Segmentation
Author :
Yan Sun ; Zhenmin Tang ; Jianfeng Lu ; Pengzhen Du
Author_Institution :
Coll. of Comput. Sci. & Eng., Nanjing Univ. of Sci. & Technol., Nanjing, China
Abstract :
In the view of the characteristics of multilevel threholding selection problems, this paper proposed a new method that Optimal Multilevel Thresholding using Improved Gravitational Search Algorithm for Image Segmentation (MTIGSA). In this paper, two strategies are proposed. One is a new gravity coefficient control strategy in order to avoid redundant computation and improve the convergence speed. Another is a mutation strategy to avoid premature convergence and improve the algorithm precision. Experimental results of both solution quality and computation efficiency illustrate the effectiveness and robustness of MTIGSA.
Keywords :
image segmentation; search problems; MTIGSA; convergence speed; gravity coefficient control strategy; image segmentation; improved gravitational search algorithm; mutation strategy; optimal multilevel thresholding selection problems; premature convergence avoidance; redundant computation avodiance; Convergence; Educational institutions; Gravity; Image segmentation; Optimization; Search problems; Standards; Gravitational Search Algorithm; Kapur´s method; histogram; image segmentation; multilevel thresholding selection;
Conference_Titel :
Mechatronic Sciences, Electric Engineering and Computer (MEC), Proceedings 2013 International Conference on
Conference_Location :
Shengyang
Print_ISBN :
978-1-4799-2564-3
DOI :
10.1109/MEC.2013.6885302
