Efficient image segmentation algorithm using SLIC superpixels and boundary-focused region merging

Abstract

An effective graph-based image segmentation using superpixel-based graph representation is introduced. The techniques of SLIC superpixels, 5-D spectral clustering, and boundary-focused region merging are adopted in the proposed algorithm. With SLIC superpixels, the original image segmentation problem is transformed into the superpixel labeling problem. It makes the proposed algorithm more efficient than pixel-based segmentation algorithms and other superpixel-based segmentation methods. With the proposed methods of 5-D spectral clustering and boundary-focused region merging, the position information is used for clustering and the threshold for region merging can be adaptive. These techniques make the segmentation result more consistent with human perception. The simulations on Berkeley segmentation database show that our proposed method outperforms state-of-the-art methods.