An Efficient Classification and Segmentation of Brain Tumor Images Using Fuzzy Approach with Optimization Technique

摘要

In numerous uses of image processing and computer vision, it is image segmentation that is generally utilized. A given image is divided to distinctive areas by utilizing the division procedure taking into account some decisive factors. The investigation of the Computed Tomography (CT) images considers image division a critical and imperative part in recognizing the various types of tumor. The tumor's grouping and the non-tumor images took after by the segmentation of tumor locale in CT images is finished by the proposed methodology. The process of classifying is carried out by Adaptive Neuro-Fuzzy Inference System (ANFIS) classifier. It combines the explicit knowledge representation of an FIS and the learning power of the artificial neural networks. After the classification segmented the tumor part of the image, here fuzzy, c means clustering (FCM) technique with centroid optimization. As regards the centroid optimization Gray Wolf Optimizer (GWO) are used to increase the accuracy of the proposed approach. An accuracy rate of 99.24% in the analysis of the segmentation process is obtained Using GWO technique and Proposed FCM approach compared to existing technique the accuracy is 57.7%. It is in the working platform of MATLAB that this proposed methodology is implemented.