Adaptive tuning of SLIC parameter K

The well-known simple linear iterative clustering (SLIC) is the most effective among the existing algorithms for superpixel segmentation, which requires manual tuning of the number of superpixels K . The optimal value of the parameter K of the SLIC algorithm for a given image is yet an open issue. In this work, we present granulometry and quality metrics based methods for adaptive tuning of the parameter K . The proposed granulometric method exploits the weighted average of the image pattern spectrum for the adaptive tuning of the parameter K . In the quality metrics method, we use majority voting scheme based on information, texture and ground truth independent quality metrics. The experimental results demonstrate that the K SLIC superpixels from the proposed methods achieved good boundary adherence of the ground truth for the images with high value of the compactness.