00501715

00501715 - IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 7 ,...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 7, NO. 3, MAY 1996 555 Face Recognition Using Artificial Neural Network Group-Based Adaptive Tolerance (GAT) Trees Ming Zhang, Senior Member, IEEE, and John Fulcher, Member, IEEE Abstructaecent artificial neural network research has focused on simple models, but such models have not been very successful in describing complex systems (such as face recognition). This paper introduces the artificial neural network group-based adap- tive tolerance (GAT) tree model for translation-invariant face recognition, suitable for use in an airport security system. GAT trees use a two-stage divide-and-conquer tree type approach. The first stage determines general properties of the input, such as whether the facial image contains glasses or a beard. The sec- ond stage identifies the individual. Face perception classification, detection of front faces with glasses andlor beards, and face recognition results using GAT trees under laboratory conditions are presented. We conclude that the neural network group-based model offers significant improvement over conventional neural- network trees for this task. I. INTRODUCTION A. Automated Face Recognition HE application of interest in the present study is the T automatic recognition of human faces-it is within this context we develop the artificial neural network group-based adaptive tolerance (GAT) tree model. Hundreds of papers exist in the scientific literature involving human face recognition, but only a few deal with the automatic recognition of faces using computers. Early (conventional) approaches included distance measures [27], algebraic extrac- tion or principal component analysis [21], [28], and isodensity lines [30], [26]. More recently, custom VLSI (very large scale integration) image correlator techniques have been applied Artificial neural network approaches include unsupervised networks [ 101, multilayer perceptrons (MLP’s) hackpropaga- tion [29], and self-organizing maps [5]. Specialized architec- tures such as WISARD [ 11 and dynamic link architectures [22] have also been applied to this problem. We now consider briefly two of the more successful attempts at automatic face recognition in recent times. Bouattour et al. [3] developed a human face recognition sys- tem using MLP’s. Their database consisted of 650 grey scale images, with approximately 70 images per person. Bouattour’s system, subsequently manufactured by the French MIMETICS Manuscript received June 25,1994; revised January 30,1995 and September 9, 1995. This work was supported by a research grant from SITA (Societe Internationale de Telecommunications Aeronautiques) at the Center For In- formation Technology Research, University of Wollongong, Australia. M. Zhang is with the Department of Computing and Infomation Systems, Faculty of Business and Technology, University of Western Sydney, NSW 2560, Australia.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This document was uploaded on 10/23/2010.

Page1 / 13

00501715 - IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 7 ,...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online