Detection of Dead Tissues by Medical Image Using CLUSTERING?

This paper presents a new approach for image segmentation by applying k-means clustering and fuzzy c-means clustering. In image segmentation, clustering techniques are very important as they are intuitive and are also easy to implement. In This paper proposes a colour based segmentation method that uses K-means clustering and fuzzy c-means clustering technique. The k-means clustering is an instinct technique used to partition an image into k clusters. It produces accurate segmentation results only when applied to images defined by homogenous regions with respect to texture and colour since no local constraints are applied to impose spatial continuity for medical images. In others side Fuzzy clustering, which defines fuzzy techniques to cluster data and they consider that an object can be classified to more than one clusters. This type of technique leads to clustering schemes that are compatible with everyday life experience as they handle the uncertainty of real data. The most important fuzzy clustering algorithm is Fuzzy C-Means. In this clustering process, there are no predefined classes. Clustering produces initial categories in which values of a data set are classified during the classification process.