An active contour method based on regularized kernel fuzzy c-means clustering

This research presents hybrid level set evolution for complex and inhomogeneous image segmentation. Firstly, we develop an adaptive force with level set evolution, which is driven by region information. Adaptive force is produced by consolidating local and global force terms in an altered fashion. Besides, to avoid local fitting terms being stuck into a local minimum, we use the swap function to interchange the fitting terms so that fitting values inside the object are always higher. Later for the elimination of the costly contour initialization that existed in previous level set based evolutions, we integrate kernel based fuzzy c-means clustering and intensity-based thresholding framework with the proposed framework to automate the proposed strategy. Finally, for the level set function regularization and the for the elimination of its re- initialization we have used the Gaussian function in the level set evolution. We demonstrate the results on some complex images to show the strong and exact segmentation results that are conceivable with this new class of adaptive active contour model. We have additionally performed statistical analysis on real images and BRATS dataset using Dice index, accuracy, sensitivity, specificity and Jaccard index metrics. Results show that the proposed method gets high Dice index, accuracy, sensitivity, specificity and Jaccard index values compared to the previous state of art methods.