The representation and matching of categorical shape

• Published in: Computer vision and image understanding Vol. 103; no. 2; pp. 139 - 154
• Main Authors: Shokoufandeh, Ali, Bretzner, Lars, Macrini, Diego, Fatih Demirci, M., Jönsson, Clas, Dickinson, Sven
• Format: Journal Article
• Language: English
• Published: San Diego, CA Elsevier Inc 01.08.2006; Elsevier
• Subjects: Applied sciences; Artificial intelligence; attention; Computer science; control theory; systems; curved objects; earth movers distance; Exact sciences and technology; Generic object recognition; good algorithm; Graph matching; Pattern recognition. Digital image processing. Computational geometry; recognition; Scale-spaces; Shape categorization; spectra; Spectral graph theory; subtree problem; Scale-spaces; Generic object recognition; Spectral graph theory; Shape categorization; Graph matching; Semantic relation; Geometrical shape; Computer vision; Scale space; Similarity; Image processing; Topological graph; Pattern recognition; Object recognition; Categorization; Pattern matching; Directed graph
• ISSN: 1077-3142; 1090-235X; 1090-235X
• DOI: 10.1016/j.cviu.2006.05.001

We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated parts of an object at appropriate scales. These parts, in turn, map to nodes in a directed acyclic graph, in which edges encode both semantic relations (parent/child) as well as geometric relations. Given two image descriptions, each represented as a directed acyclic graph, we draw on spectral graph theory to derive a new algorithm for computing node correspondence in the presence of noise and occlusion. In computing correspondence, the similarity of two nodes is a function of their topological (graph) contexts, their geometric (relational) contexts, and their node contents. We demonstrate the approach on the domain of view-based 3-D object recognition.