Abstract
In this paper, a new method for recognizing the facial images with low resolution by utilizing the Hopfield model is presented.
In this method, according to the Markov random field (MRF) model, the Hopfield memory model with recall capability is constructed. Based on the composed Hopfield memory model, the relation between the reliability of the recalls and the number of faces which are memorized in the Hopfield memory is analyzed, and the scheme for the face recognition combined with the pattern matching is presented.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
M. Kosugi, ”Human-Face Recognition Using Mosaic Pattern and Neural Networks”, Trans. of IEICE D-II, J73-D-II, pp.1132–1139(1993) (in Japanese)
J.J. Hopfield, ”Neural Networks and Physical Systems with Emergent Collective Abilities”, Proc. Natl. Acad. Sci. U.S.A, 79, pp. 2554–2558 (1982)
Y. Dai, et al. ”A Study of Face Recognition with Low Quality Images”, The Proceedings of ICARCV'94, pp.1442–1446(1994), Singapore.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dai, Y., Nakano, Y. (1997). Recognition of facial images with low resolution using a Hopfield memory model. In: Bigün, J., Chollet, G., Borgefors, G. (eds) Audio- and Video-based Biometric Person Authentication. AVBPA 1997. Lecture Notes in Computer Science, vol 1206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015991
Download citation
DOI: https://doi.org/10.1007/BFb0015991
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62660-2
Online ISBN: 978-3-540-68425-1
eBook Packages: Springer Book Archive