His study aims to create a robust fuzzy c-means clustering algorithm for brain pictures that is both effective and robust. A local mesh developments feature extractor is suggested for the segmentation of medical images. The size of the local variance among the center pixel and its neighbors is taken into consideration while evaluating the datasets that constitute the local region of the image. Initially, the image is divided into smaller segments, and unique objective function characteristics are taken from every available dataset. After dividing the image into blocks with relatively uniform textures, we combine similar neighboring regions using an agglomerative process until either of the two halting criteria is met. We combine the two nearby regions with the highest merger significance value at each step. The regions are merged according to merger significance, and the resulting segmented regions are used for medical picture segmentation applications. In order to test the experimental findings for medical picture segmentation, an equivalent MRI database is used. Following investigation, the suggested method’s results demonstrate an important boost in image segmentation.