Contour canonical form
| Autor: | Xu-Lei Wang, Hongbin Zha |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Geodesic
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Heat kernel signature Active shape model Embedding Canonical form Computer vision Artificial intelligence Principal geodesic analysis Performance improvement business Algorithm ComputingMethodologies_COMPUTERGRAPHICS Shape analysis (digital geometry) |
| Zdroj: | ICMR |
| DOI: | 10.1145/2324796.2324835 |
| Popis: | Evaluating the intrinsic similarities between non-rigid 3D shapes is of vital importance in content-based shape retrieval. In this paper, we present a novel intrinsic embedding technique, the contour canonical form, to express the isometry-invariant shape representation. The basic idea is to generate an unbent mapping shape for each subpart by aligning the geodesic contours. In details, we first extract the feature points on the non-rigid shape. Then, their canonical mapping positions are calculated, which are globally optimized under geodesic constraints defined on the shape surface. Guided by these positions, an embedding shape is finally obtained by adaptively rotating and translating the geodesic contours around the corresponding feature point. Compared with existing spectral embedding methods, our approach excels on both the preservation of geometric information and the computational efficiency. In the experiment, the contour canonical form is applied in retrieving non-rigid 3D shapes from the McGill articulated benchmark. The appealing results clearly demonstrate a significant performance improvement of our approach over state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|