Object segmentation algorithm for use in recognizing 3-D partially occluded objects

In this paper, an object segmentation algorithm is presented to extract partially occluded objects from a scene. The visual scene is composed of a group of 3-D overlapping objects which can be represented by straight-line drawings projected on 2-D image plane. The goal is to decompose the visual scene into several 3-D objects by extracting line drawing from partially occluded scene. The criteria used for segmenting a visual scene into composing objects include junction type interpretation and region homogeneity. The segmented result can be used as a basis for partial matching in recognizing partially occluded objects.