Patch Growing: Object segmentation using spatial coherence of local patches

Object segmentation is a challenging and important problem in computer vision. The difficulties to obtain accurate segmentations using only the traditional Topdown or Bottom-up approaches have introduced new proposals based on the idea of combining them in order to obtain better results. In this paper we present a novel approach for object segmentation based on the following two steps: 1) oversegment the image in homogeneous regions using a Region Growing algorithm (Bottomup), and 2) use prior knowledge about the object appearence (local patches and spatial coherence) from annotated images to validate and merge the regions that belong to the object (Top-down). Our experiments using different object classes from the well-known TUD and the Weizmann databases show that we are able to obtain good object segmentations from a generalistic segmentation method.