Face recognition using artificial neural network group-based adaptive tolerance (GAT) trees
IEEE Transactions on Neural NetworksPublished 1 May 1996
Ming Zhang, John Fulcher
Citations59
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The artificial neural network group-based adaptive tolerance (GAT) tree model for translation-invariant face recognition, suitable for use in an airport security system, is introduced.
Abstract
Recent 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 adaptive 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 second stage identifies the individual. Face perception classification, detection of front faces with glasses and/or 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.
Keywords
Computer Science
BiometricsClassification and Regression Trees.
23,841 Citations1984Alexander Gordon, Leo Breiman +3 more
Neural NetworksMultilayer feedforward networks are universal approximators
21,248 Citations1989Kurt Hornik, Maxwell B. Stinchcombe +1 more
It is rigorously established that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available.
Mathematics of Control Signals and SystemsApproximation by superpositions of a sigmoidal function
13,684 Citations1989George Cybenko
Neural NetworksApproximation capabilities of multilayer feedforward networks
6,086 Citations1991Kurt Hornik
It is shown that standard multilayer feedforward networks with as few as a single hidden layer and arbitrary bounded and nonconstant activation function are universal approximators with respect to L p (μ) performance criteria, for arbitrary finite input environment measures μ.
A theory of the learnable
4,242 Citations1984Leslie G. Valiant
This paper regards learning as the phenomenon of knowledge acquisition in the absence of explicit programming, and gives a precise methodology for studying this phenomenon from a computational viewpoint.
Neural NetworksOn the approximate realization of continuous mappings by neural networks
4,220 Citations1989Ken-ichi Funahashi
It is proved that any continuous mapping can be approximately realized by Rumelhart-Hinton-Williams' multilayer neural networks with at least one hidden layer whose output functions are sigmoid functions.
Machine LearningThe Strength of Weak Learnability
3,293 Citations1990Robert E. Schapire
In this paper, a method is described for converting a weak learning algorithm into one that achieves arbitrarily high accuracy, and it is shown that these two notions of learnability are equivalent.
Communications of the ACMA theory of the learnable
3,268 Citations1984Leslie G. Valiant
This paper regards learning as the phenomenon of knowledge acquisition in the absence of explicit programming, and gives a precise methodology for studying this phenomenon from a computational viewpoint.
Neural ComputationHierarchical Mixtures of Experts and the EM Algorithm
2,639 Citations1994Michael I. Jordan, Robert A. Jacobs
IEEE Transactions on Pattern Analysis and Machine IntelligenceApplication of the Karhunen-Loeve procedure for the characterization of human faces
2,454 Citations1990Michael Kirby, L. Sirovich
The use of natural symmetries (mirror images) in a well-defined family of patterns (human faces) is discussed within the framework of the Karhunen-Loeve expansion, which results in an extension of the data and imposes even and odd symmetry on the eigenfunctions of the covariance matrix.
Machine LearningThe strength of weak learnability
2,434 Citations1990Robert E. Schapire
In this paper, it is shown that the two notions of learnability are equivalent, and a method is described for converting a weak learning algorithm into one that achieves arbitrarily high accuracy.
Introduction to Statistical Pattern Recognition
1,607 Citations2011Andrew R. Webb, Keith D. Copsey
IEEE Transactions on Pattern Analysis and Machine IntelligenceDecision combination in multiple classifier systems
1,511 Citations1994Tin Kam Ho, J.J. Hull +1 more
This work proposes three methods based on the highest rank, the Borda count, and logistic regression for class set reranking that have been tested in applications of degraded machine-printed characters and works from large lexicons, resulting in substantial improvement in overall correctness.
ScienceTopological Structure in Visual Perception
409 Citations1982Lan CHEN
Three experiments on tachistoscopic perception of visual stimuli demonstrate that the visual system is sensitive to global topological properties, and indicates that extraction of globalTopological properties is a basic factor in perceptual organization.
Sensor ReviewWISARD·a radical step forward in image recognition
303 Citations1984Igor Aleksander, Wischgoll Thomas +1 more
Pattern RecognitionHandwritten numerical recognition based on multiple algorithms
256 Citations1991Fumitaka Kimura, M. Shridhar
The authors combine two algorithms for application to the recognition of unconstrained isolated handwritten numerals utilizing features derived from the profile of the character in a structural configuration to recognize the numerals.
International Journal of Pattern Recognition and Artificial IntelligenceBOOSTING PERFORMANCE IN NEURAL NETWORKS
184 Citations1993Harris Drucker, Robert E. Schapire +1 more
The boosting algorithm is used to construct an ensemble of neural networks that significantly improves performance (compared to a single network) in optical character recognition (OCR) problems and improved performance significantly, and, in some cases, dramatically.
IEEE Transactions on ComputersGrowing and pruning neural tree networks
129 Citations1993A. Sakar, Richard J. Mammone
It is shown that this method has better performance in terms of minimizing the number of classification errors than the squared error minimization method used in backpropagation.
IEEE Transactions on Neural NetworksA tree-structured adaptive network for function approximation in high-dimensional spaces
129 Citations1991Terence D. Sanger
The author proposes a technique based on the idea that for most of the data, only a few dimensions of the input may be necessary to compute the desired output function, and it can be used to reduce the number of required measurements in situations where there is a cost associated with sensing.
Pattern RecognitionIdentification of human faces based on isodensity maps
107 Citations1991Osamu Nakamura, Shailendra Mathur +1 more
The feasibility of using isodensity lines for human face identification system is presented through experimental investigation and shows a 100% accuracy in matching same persons and a 100%" accuracy in discriminating different persons (including persons with spectacles).
Neural NetworksA fast dynamic link matching algorithm for invariant pattern recognition
99 Citations1994Wolfgang Konen, Thomas Maurer +1 more
A flexible neural mechanism for invariant recognition based on correlated neuronal activity and the self-organization of dynamic links is proposed which allows an unsupervised decision of whether a given input pattern matches with a stored model pattern.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEEye Spacing Measurement for Facial Recognition
97 Citations1985Mark Nixon
Measurement of spacing has been made by application of the Hough transform technique to detect the instance of a circular shape and an ellipsoidal shape which approximate the perimeter of the iris and both the perimeter the sclera and the shape of the region below the eyebrows respectively.
IEEE Transactions on Systems Man and CyberneticsAdaptation Algorithms for Binary Tree Networks
58 Citations1979William W. Armstrong, J. Gecsei
The automatic synthesis of Boolean switching functions by adaptive tree networks is discussed and applications to pattern recognition and optical character recognition problems are described.
A real-time face recognition system using custom VLSI hardware
37 Citations2002James M. Gilbert, Weizhao Yang
A real-time face recognition system has been implemented on an IBM compatible personal computer with a video camera, image digitizer, and custom VLSI image correlator chip that achieves a very conservative 88% recognition rate using cross-validation on the moderately varied database.
Communication in Statistics- Theory and MethodsThe table look-up rule
34 Citations1976Robert M. Haralick
A quickly implementable table look-up rule based on Ashby’s representation of sets in his constraint analysis that is comparable to the optimum Bayes rule on simulated Gaussian Data.
Pattern RecognitionSolving of optimization and identification problems by the committee methods
30 Citations1987Вл. Д. Мазуров, А. И. Кривоногов +1 more
Some applications of the committee technique in regard to economics, sociology, biology and medicine are discussed and the existence theorem for a discriminating committee, consisting of affine functions, is presented.
Comparisons between human and computer recognition of faces
23 Citations2002Vicki Bruce, Peter Hancock +1 more
The characteristics of human face recognition that should be reflected in any psychologically plausible computational model of face recognition are reviewed and the coding of image sequences by humans and computers are discussed.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Recognition in face space</title>
14 Citations1991Matthew Turk, Alexander P. Pentland
The construction of face space and its use in the detection and identification of faces is explained in the context of a working face recognition system and the effects of illumination changes scale orientation and the image background are discussed.
Neural nets for human face recognition
13 Citations2003Hazem Bouattour, Françoise Fogelman Soulié +1 more
A neural network (NN) architecture based on a multilayer perceptron with shared weights allows direct gray-level image processing and lets the NN learn to extract image features in its hidden layers, which allow fast classification of face images.
Unsupervised learning for neural trees
11 Citations1991Lide Fang, A. Jennings +3 more
A self-organizing neural tree is studied and it is indicated that the vectors represented by the nodes of the tree tend to approximate the probability of the sample distribution.
International Journal of Pattern Recognition and Artificial IntelligenceCOMBINING IMAGE PROCESSING OPERATORS AND NEURAL NETWORKS IN A FACE RECOGNITION SYSTEM
7 Citations1992Paola Flocchini, F. Gardin +3 more
A system able to recognize human faces from different perspectives, and which have different expressions, shows a high generalization capability and allows the recognition of images with different kinds of noise better than what each single network can do, as confirmed by a preliminary experimental evaluation.
Facial recognition for police purposes using computer graphics and neural networks
6 Citations1990Richard Starkey, Igor Aleksander
A program was written in lightspeed Pascal on a Macintosh II personal computer to simulate a WISARD neural network and a target face from the photograph collection was chosen at random and the net was trained to recognise it.