PTK: A novel depth buffer-based shape descriptor for three-dimensional object retrieval

The increase in availability and use of digital three-dimensional (3D) synthetic or scanned objects, makes the availability of basic database operations, such as retrieval, necessary. Retrieval methods are based on the extraction of a compact shape descriptor; the challenge is to design a shape descriptor that describes the original object in sufficient detail to make accurate 3D object retrieval possible. Building on previous work, this paper proposes a novel depth buffer-based shape descriptor (called PTK) that encompasses symmetry, eigenvalue-related weighting and an object thickness related measure to provide an accuracy surpassing previous state-of-the-art methods. An evaluation of the novel method's parameters and a direct comparison to other approaches are carried out using publicly available and widely used databases.