Date of Original Version
1st International Workshop on Visual Scene Understanding, June, 2009
Abstract or Table of Contents
In this paper, we explore ways to combine boundary information and region segmentation to estimate regions corresponding to foreground objects. Boundary information is used to generate an object likelihood image which encodes the likelihood that each pixel belongs to a foreground object. This is done by combining evidence gathered from a large number of boundary fragments on training images by exploiting the relation between local boundary shape and relative location of the corresponding object region in the image. A region segmentation is used to generate a likely segmentation that is consistent with the boundary fragments out of a set of multiple segmentations. A mutual information criterion is used for selecting a segmentation from a set of multiple segmentations. Object likelihood and region segmentation are combined to yield the final proposed object region(s).