Abstract
A significant advantage of a HONN over other neural net paradigms is that geometric invariance can be designed into the network thereby avoiding the need for the network to develop its internal representations over hundreds or thousands of training iterations through a much larger training set. With a HONN, only one view of each object is required for learning, clearly making it a much more attractive architecture.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
P.W. Hallinan, “Recognizng human eyes”, Proc. SPIE: Geometric Methods in Computational Vision, Vol.1570, pp.214–226, 1991.
T. Kanade, Computer Recognition of Human Faces. Basel and Stuttgart: Birkhauser, 1977.
Y. Kaya, K. Kobayashi, “A basic study on human face recognition,” Frontiers of Pattern Recognition, S. Watanabe, Ed. New York: Academic Press, pp.265–289, 1972.
D. Reisfeld and Y. Yeshurun, “Robust Detection of facial features by generalized symmetry”, Proc. 11th Intl. Conf. on Pattern Recognition, pp.117–120, 1992.
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). Conclusions & Contributions. 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_7
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4092-2_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6832-8
Online ISBN: 978-1-4615-4092-2
eBook Packages: Springer Book Archive