Comparison of Combined Shape Descriptors for Irregular Objects

This paper focuses on recognition powers and computational efforts of three different shape coding techniques, namely the chain code histogram (CCH), the pairwise geometric histogram (PGH), and the combination of simple shape descriptors, for characterization of irregular objects. In recognizing irregular objects the essential task is to design efficient measures based on relatively small prior knowledge on geometrical constraints of possible target objects. Three rather different approaches are evaluated and discussed by the means of the self-organizing map (SOM). A database retrieval problem is also assumed to further test their discriminatory powers. As a case study, natural irregular objects have been used. Grouping of these objects based on their visual similarity is the main topic in this paper. The combination of simple shape descriptors is shown to have good recognition capabilities and low computation costs.