A Hybrid Approach towards Segmentation of Range Images

This paper presents a technique for the segmentation of range images. It tends to be a hybrid approach that combines edge detection and region growing techniques toward accomplishing the task of segmentation. The surface coherency property of range data provided an important attribute, .;rhich enabled the improvision of extrinsic knowledge regarding the types of surface primitives existing within an image. The cross-breeding approach produces a segmentation map and an edge map. Edges detected by such a method possessed good localisation property. The incorporation of region growing process eliminates internal micro edges and produces a segmentation map. These two maps would undoubtedly be of great value to the higher level recognition process.