Abstract
Object recognition systems needs of image segmentation processes that relate image regions to world objects. These methods present often three problems: the generation of a large number of small regions, under-segmentation (different objects are associated to the same image region) and over-segmentation (a scene object is segmented in various regions). In order to overcome these problems, we propose an image segmentation method that combines depth information and object surface properties obtained from a pair of stereo images. The system work under the standard assumption that 3D objects have planar faces and regular shapes. First, a region growing segmentation process is applied to both images generating two labeled images. Then, depth information of the region frontiers is obtained by matching the labeled segments from left and right image rows. Finding a path through a 2D search plane whose axes are the left and right-segmented lines solves the stereo matching problem. Original image regions are then merged based on their size, surface information and frontier depth information. In this way, image regions are associated to surfaces that are contiguous in the 3D space, and they present a common property (as gray level, color or texture).