A comprehensive database for border ownership

Border ownership is a problem of identifying which visual region the borders of a visual image belong. It has valuable and essential information for visual systems. Existing computational approaches either use artificial or limited type and number of images. In this study, we propose a new comprehensive database, which contains border ownership information from the edges and segments of 500 indoor and 500 outdoor images determined by hand-labeling of human participants and a couple of analyses carried on this database for the purpose of developing better computational models as well as making better comparisons of developed border ownership models. Images in the database are labeled by 4 participants, whose age ranged between 24 and 34.