Automatic immune clonal clustering method using manifold distance for image segmentation

There are several difficulties in using a partitional clustering algorithm to deal with image segmentation problem including choosing the correct number of clusters without any prior knowledge, measuring the image datasets with complicated manifold structures and reducing the computation time. In this paper, an automatic immune clonal clustering method using manifold distance is applied to image segmentation. This method can automatically determine the number of clusters, measure the complicated manifold dataset by using manifold distance, and less computation time by using super-pixels instead of pixels. Experimental results on four artificial data sets and four Berkeley images show that the novel method outperforms the k-means algorithm and the GCUK algorithm.