Variance adaptive SLIC
Fei Kou, Zhengguo G. Li, Changyun Wen, Weihai Chen · 2016
Superpixel segmentation becomes more and more popular in the fields of computer vision and image processing. The simple linear iterative clustering (SLIC) is widely used due to its high segmentation accuracy and low computational complexity. In this paper, we propose a variance adaptive SLIC (VASLIC) algorithm. The compactness factor of the proposed algorithm is determined according to the image neighbourhood variance. In this way, more suitable compactness number is selected for each pixel. As a result, the proposed algorithm has higher segmentation accuracy than the SLIC and lower computational complexity. Experimental results on superpixel benchmark show that this newly proposed algorithm is indeed better than the SLIC.