Share Email Print
cover

Proceedings Paper

Optimized linear combination of multiple neural networks on object recognition
Author(s): Huilin Jiang; Huamin Yang; Zhengang Jiang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Neural networks have pretty adaptability on the multifarious features ofrecognized objects, which can fulfill the multi-feature information fusion by combining multiple neural networks linearly and enhance the performance of recognition system. For the linear combination, it can't select the best dynamically to regulate the contribution of individual subnets because it combines the static weights ofthe output in subnets, which has limited the whole network performance. This paper puts forward an optimized linear combined method on multiple neural networks. This method determines the optimized combination weight by constructing estimate function ofthe whole network performance, gives the computable mathematical model for this optimized combination weight estimated method, and discusses the robust in the multiple neural networks system by optimized linear combination. From the simulation experience, this method is used on object recognition by multi-feature information fusion and gains more satisfying result than general multi-neural network linear combined method.

Paper Details

Date Published: 30 August 2002
PDF: 4 pages
Proc. SPIE 4925, Electronic Imaging and Multimedia Technology III, (30 August 2002); doi: 10.1117/12.481615
Show Author Affiliations
Huilin Jiang, Changchun Univ. of Science and Technology (China)
Huamin Yang, Changchun Univ. of Science and Technology (China)
Zhengang Jiang, Changchun Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 4925:
Electronic Imaging and Multimedia Technology III
LiWei Zhou; Chung-Sheng Li; Yoshiji Suzuki, Editor(s)

© SPIE. Terms of Use
Back to Top