Abstract
The current simulator reads in two isolevel images at a time - one for each training subject - therefore the other 3 pairs of images have to be sequentially processed before the system can reach a classification decision. It would be far more convenient to be able to read and process all four pairs simultaneously in a single command. This can be achieved with the appropriate modifications to the software, however there was insufficient time to effect these changes. In order to make the system run at a reasonable (near real-time) speed, faster multiprocessor machines with much more memory (to minimize disk paging) and CPUs optimized for floating point calculations would be needed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
R. Brunelli, T. Poggio, “Face Recognition: Features versus Templates,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.15, No.10, pp.1042–1052, October 1993.
L. Spirkovska, M.B. Reid, “Coarse-Coded Higher-Order Neural Networks for PSRI Object Recognition”, IEEE Trans. on Neural Networks, Vol.4,No.2 pp276–283, March 1993.
M. Turk, A. Pentland, “Eigenfaces for Recognition”, Journal of Cognitive Neuroscience, Vol.3, No.l, pp.71–86, 1991.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Uwechue, O.A., Pandya, A.S. (1997). Future Work. In: Human Face Recognition Using Third-Order Synthetic Neural Networks. The Springer International Series in Engineering and Computer Science, vol 410. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4092-2_8
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4092-2_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6832-8
Online ISBN: 978-1-4615-4092-2
eBook Packages: Springer Book Archive