Recognition of Facial Images with Low Resolution Using a Hopfield Memory Model

Ying Dai and Yasuaki Nakano

Pattern Recognition, Vol. 31, pp. 159-167 (1998)

Abstract

In this paper, a new method to recognize facial image with low resolution by utilizing the Hopfield model is presented.
In this method, a Hopfield memory model for the facial images is organized and the optimal procedure of the unlearning is determined. Based on the composed Hopfield memory model, the relation between the reliability of the recalls and the number o f faces memorized in the Hopfield memory is analyzed. Finally, the method for the face recognition using the Hopfield memory model combined with the pattern matching is proposed. The experimental results for face recognition are also represented and analyzed.

[顔画像認識][中野の研究紹介][中野の目次]

mail address: ← お手数ですが打ち込んで下さい

First Written Before June 17, 1998
Transplanted to KSU Before May 16, 2003
Transplanted to So-net May 3, 2005
Last Update April 11, 2007

© Yasuaki Nakano 1998-2007