A novel image segmentation approach using fcm and whale optimization algorithm

The segmentation of images is considered a significant step in the processing of images. Due to its simplicity and efficiency, Fuzzy c-means (FCM) is most commonly employed clustering approach for image segmentation. FCM, however, has the drawbacks of sensitiveness to the prior values and local optimum solution and also, it is very sensitive to the effect of noises. In the literature survey, several optimization-based fuzzy clustering approaches were proposed to counter these drawbacks. Whale Optimization Algorithm (WOA) has a strong capability for global optimization and a combination of FCM and WOA has enhanced efficiency over conventional FCM clustering. A new approach to segmentation of image which is based on the WOA and FCM Algorithm is proposed in this paper along with the noise detection and reduction mechanism. Since exploration and exploitation phases are performed in nearly equal numbers of iterations separately, the WOA simultaneously shows better avoidance from local optima and superior convergence speed. In our experiment, we have used synthetic images and Medical Resonance Imaging (MRI) Images to validate the performance of the proposed system by taking various types of noise and the findings indicate that the proposed method is more efficient and effectively reduce the impact of noise. We compared the proposed method with other existing clustering-based segmentation techniques and then measured their efficiency using different evaluation indices, and the findings demonstrate the efficacy of the methodology proposed.