期刊
NEURAL COMPUTING & APPLICATIONS
卷 22, 期 3-4, 页码 427-433出版社
SPRINGER LONDON LTD
DOI: 10.1007/s00521-012-0892-7
关键词
Extreme learning machines; Geometrical topology hypothesis; Optimal cognition principle; Dipole topology
资金
- Natural Science Foundation of P.R. China [41176076]
- National High Technology Research and Development Program of P.R. China [2006AA09Z231]
- Science and Technology Development Program of Shandong Province [2008GG1055011, BS2009HZ006]
- Science and Technology Development Program of Qingdao [103413jch]
In this paper, one geometrical topology hypothesis is present based on the optimal cognition principle, and the single-hidden layer feedforward neural network with extreme learning machine (ELM) is used for 3D object recognition. It is shown that the proposed approach can identify the inherent distribution and the dependence structure for each 3D object along multiple view angles by evaluating the local topological segments with a dipole topology model and developing the relevant mathematical criterion with ELM algorithm. The ELM ensemble is then used to combine the individual single-hidden layer feedforward neural network of each 3D object for performance improvements. The simulation results have shown the excellent performance and the effectiveness of the developed scheme.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据