Information-Theoretical Technique for Optimizing Segmentation Quality

In this paper, a problem of image segmentation quality is considered. The problem of segmentation quality is viewed as selecting the best segmentation from a set of images generated by segmentation algorithm at different parameter values. A technique for selecting the best segmented image is proposed. Information redundancy measure is used as a criterion for optimizing segmentation quality. It is shown that proposed method for constructing the redundancy measure gives the extremal properties. Computing experiment confirmed that the segmented image corresponding to a minimum of redundancy measure produces the suitable dissimilarity when compared with the original image. The segmented image which was selected using the proposed criterion, gives the highest similarity with the ground-truth segmentations, available in the database.The research was supported in part by the Russian Foundation for Basic Research (grants No 15-07-09324 and No 15-0104671)