This paper proposes a novel algorithm for completing rotationally symmetrical shapes under severe occlusions, based on the intuitive idea to use the existing contour, under a carefully estimated similarity transform, to fill in the missing portion of a symmetric object due to occlusions.
The authors’ algorithm exploits the invariant nature of the curvature under similarity transform and the periodicity of the curvature of a symmetric object contour. To arrive at the appropriate transform, the authors first estimated the fundamental period in the curvature. They used the fundamental period and the harmonic components to estimate the fundamental angle of rotation and the centroid of the un-occluded shape, which in turn established different modes of symmetry. By following each mode of symmetry, the authors computed the corresponding transform and selected the ones that best completed the missing portion of the contour. (Publisher abstract provided)
Downloads
Similar Publications
- Reports of Adverse Events Associated With Use of Novel Psychoactive Substances, 2013-2016: A Review
- The Application of Proteomics to Forensic Human Identification and Disease Characterization Using Hair Shafts
- Primary user emulation attack in dynamic spectrum access networks: a game-theoretic approach