Abstract: Main objective of clustering an image is dominant colors extraction from the images. By extracting the information from images such as texture, color, shape and structure, the image segmentation can be very important to simplify. Because of the information extraction in any images, the segmentation has been used in many fields such as Enhancing the image, compression, retrieval systems i.e., search engines, object detection, and medical image processing.  From the past decades, there are so many approaches developed for the image segmentation. Among those, Fuzzy c-means (FCM) is a well-known method and very popular clustering scheme, which will segment the image into several parts based on the membership function.  After FCM, the K-means algorithm has been proposed to reduce the computational complexity of FCM. Because of its ability to cluster huge data points very quickly, K-means has been widely used in many applications. Later years the Hierarchical clustering is also widely applied for image segmentation. Then after, Gaussian Mixture Model has been used with its variant Expectation Maximization for segmenting the images.

Keywords:  FCM (Fuzzy c-mean), Fuzzy K Means, Segmentation, MRI

| DOI: 10.17148/IJIREEICE.2018.687