Title :
Cubical singular simplex model for 3D objects and fast computation of homology groups
Author :
Chao, Jinhui ; Nakayama, Jyouji
Author_Institution :
Dept. of Electr. & Electron. Eng., Chuo Univ., Tokyo, Japan
Abstract :
This paper proposes a new simplex model for 3D objects: a cubical singular simplex model instead of the traditional triangularization simplex model. An extended Kohonen mapping is then presented as an efficient learning rule of the model. Based on this model, one can derive a pyramid structure for multi-resolution hierarchy, which is not possible for triangularization simplex. Besides, a fast algorithm is shown to calculate the homology groups of the objects as topological invariants from the proposed model
Keywords :
image representation; self-organising feature maps; stereo image processing; topology; unsupervised learning; 3D object representation; cubical singular simplex model; extended Kohonen mapping; homology groups; multiple resolution hierarchy; pyramid structure; topological invariants; unsupervised learning rule; Chaos; Feature extraction; Flexible structures; Image coding; Image recognition; Image restoration; Network topology; Shape; Smoothing methods; Vector quantization;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547259
