A Optimally Enhanced Fuzzy K-C Means (Oefkcm) For Clustering Algorithm Medical Image Segmentation

Abstract: Medical image segmentation is worth concepts in the fields of Biomedical and Anatomical information. The biomedical images obtained by the diagnostic equipment’s are erroneous due to inception of the noise in wide band frequency. The brightness of the image is non uniform and the contrast is inhomogeneous. Hence the image thus obtained needs refinement and removal of noise and an attempt is made to enhance the region of interest by applying the image segmentation techniques. Many studies have improved more efficiency as far as subject is concerned. Numerous methods are proposed for medical image segmentation such as Clustering techniques, Thresholding technique, Classifier, Region Growing, Deformable Model, Markov Random Model, k-means, etc. Previously proposed mechanism is fuzzy k-c means in this mechanism number of cluster is lesser so the selection of number of iterations and convergence at the wrong minima. In proposed work we find out the no. of cluster by using an optimization technique of PSO and Cuckoo search technique using a Hybrid method to increase the cluster. It showed to be superior when compared to the other techniques.

Keywords: Clustering algorithm, Fuzzy K-C means algorithm, PSO, Cuckoo search, Segmentation.