Jaccard index compensation for object segmentation evaluation

Abstract

In this paper, we propose an objective metric for quality evaluation of individual object segmentation in images. Using the Jaccard Index as a base, additional compensation terms are integrated into our metric. These terms not only allow our metric to combine region-based and boundary-based methods, they also describe human visual tolerance and saturation. This metric can also can adaptively adjust “perception function” under different image sizes. The experiment on our subjective object segmentation quality assessment database demonstrates that the proposed metric performs well in matching subjective ratings.