Segmentation is an essential part of the detection and classification series. The best result of brain MRI detection was followed by the best segmentation process. Supporting brain MRI detection accurately, one of the ways could be used by increasing segmentation. This paper utilizes one of the segmentation methods which is called clustering. We propose a clustering approach using K-Means. K-Means has advantages easy to understand, fast process, and guarantees convergence. But it has drawbacks which are initialization cluster center randomly, sometimes it is given good results but sometimes it is not. Therefore, this research proposes to optimize the weak side of K-Means using a grey wolf optimizer. Initialization cluster center was chosen based on fitness value. The fitness value of this paper is Sum Square Error (SSE), we purpose to minimize the SSE of the population and searching new positions depend on Gray Wolf Optimization (GWO)’s rule. The final position of GWO would be initialized by K-Means. The series of our research steps are acquisition image, grayscaling, resizing, segmentation, and analysis performance based on MSE and PSNR. The best result of the purposed method is k=17 which PSNR (16.09) and MSE (15.99). GWO K-Means were given the best outcome segmentation brain MRI based on measuring error value and PSNR.
Elindra Ambar Pambudi, Abid Yanuar Badharudin, Agung Purwo Wicaksono
Presidency College, India
Gray Wolf Optimization, K-Means, MRI Segmentation, Sum Square Error | Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 11 , Issue: 3 )
Date of Publication :
April 2021
|