In this paper, a scale and orientation invariant feature representation for 2.5D objects is introduced, which may be used to classify, detect and recognize objects even under the cases of cluttering and/or occlusion. With this representation a 2.5D object is defined by an attributed graph structure, in which the nodes are the pit and peak regions on the surface. The attributes of the graph are the scales, positions and the normals of these pits and peaks. In order to detect these regions a "peakness" (or pitness) measure is defined based on Gaussian curvature calculation, which is performed at various scales on the surface. Finally a "position vs. scale" feature volume is obtained and the graph nodes are extracted from this feature space by volume segmentation techniques.