KmsGC: An Unsupervised Color Image Segmentation Algorithm Based on -Means Clustering and Graph Cut
Figure 5
(a), (b), (c), and (d) are the cluster number determination of the images (a), (b), (c), and (d) of Figure 4, respectively. In each graph, -axis represents the number of clusters, whereas -axis shows the values of the compactness criterion, and ; the compactness criterion reaches the minimum value at the optimal cluster number. According to these results, the optimal cluster numbers are obtained as showed below each graph.