Comparisons of 3D Shape Clustering with Different Face Area Definitions
ICDHM '09 Proceedings of the 2nd International Conference on Digital Human Modeling: Held as Part of HCI International 2009
| Hi-index | 0.00 |
The 3D scans of human bodies contain over hundreds of thousand grid points. To be used effectively for analysis, indexing, searching, clustering and retrieval, these human bodies requires a compact shape representation. We have developed compact representations based on human body shape based on lengths mostly between joints of single large bones and in the second method silhouettes of the human body are created and then encoded as Fourier shape descriptors. We also have developed two such compact representations based on human head shape by applying Principal Component Analysis on the facial surface and in the second method the whole head is transformed to a spherical coordinate system expanded in a basis of Spherical Harmonics.