Conference paper
Modular dynamic RBF neural network for face recognition
Proceedings of the 2012 IEEE Conference on Open Systems (ICOS), Vol.1, pp.133-138
IEEE Conference on Open Systems (ICOS), 2012 (Kuala Lumpur, Malaysia, 21-Oct-2012–24-Oct-2012)
Institute of Electrical and Electronics Engineers
2012
Abstract
Over the years, we have seen an increase in the use of RBF neural networks for the task of face recognition. However, the use of second order algorithms as the learning algorithm for all the adjustable parameters in such networks are rare due to the high computational complexity of the calculation of the Jacobian and Hessian matrix. Hence, in this paper, we propose a modular structural training architecture to adapt the Levenberg-Marquardt based RBF neural network for the application of face recognition. In addition to the proposal of the modular structural training architecture, we have also investigated the use of different front-end processors to reduce the dimension size of the feature vectors prior to its application to the LM-based RBF neural network. The investigative study was done on three standard face databases; ORL, Yale and AR databases.
Details
- Title
- Modular dynamic RBF neural network for face recognition
- Authors
- Sue Inn Ch'ng (Author) - Sunway UniversityKah Phooi Seng (Author) - Sunway UniversityLi-Minn Ang (Author) - Edith Cowan University
- Publication details
- Proceedings of the 2012 IEEE Conference on Open Systems (ICOS), Vol.1, pp.133-138
- Conference details
- IEEE Conference on Open Systems (ICOS), 2012 (Kuala Lumpur, Malaysia, 21-Oct-2012–24-Oct-2012)
- Publisher
- Institute of Electrical and Electronics Engineers
- Date published
- 2012
- DOI
- 10.1109/ICOS.2012.6417629; 10.1109/ICOS.2012
- ISBN
- 9781467310468
- Organisation Unit
- University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
- Language
- English
- Record Identifier
- 99513796302621
- Output Type
- Conference paper
Metrics
12 Record Views