Extraction of border ownership information by Conditional Random Field model

Border ownership is a kind of information used for determining the regions that own borders in an image. This information has recently become more valuable as it began to be used in many vision problems such as figure-ground segregation, depth perception and optical flow, however the quality and quantity of current literature are not sufficient yet. In this study, a Conditional Random Field model is developed for the enhancement of border ownership labelings, which are extracted with the help of some spatial cues at the beginning.