Abstract
The study of 2D shapes is a central problem in the field of computer vision. In 2D shape analysis, classification and recognition of ob jects from their observed silhouettes are extremely crucial and yet diffi- cult. It usually involves an efficient representation of 2D shape space with natural metric, so that its mathematical structure can be used for further analysis. Although significant progress has been made for the study of 2D simply-connected shapes, very few works have been done on the study of 2D ob jects with arbitrary topologies. In this work, we propose a represen- tation of general 2D domains with arbitrary topologies using conformal geometry. A natural metric can be defined on the proposed representation space, which gives a metric to measure dissimilarities between ob jects. The main idea is to map the exterior and interior of the domain confor- mally to unit disks and circle domains, using holomorphic 1-forms. A set of diffeomorphisms from the unit circle S 1 to itself can be obtained, which to- gether with the conformal modules are used to define the shape signature. We prove mathematically that our proposed signature uniquely represents shapes with arbitrary topologies. We also introduce a reconstruction algo- rithm to obtain shapes from their signatures. This completes our frame- work and allows us to move back and forth between shapes and signatures. Experiments show the efficacy of our proposed algorithm as a stable shape representation scheme.