A Method of Face Recognition Based on Fuzzy c-Means Clustering and Associated Sub-NNs
Authors:
- 2 January 2007
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 18 (1) , 150-160
Abstract
The face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. In this paper, we present a method for face recognition based on parallel neural networks. Neural networks (NNs) have been widely used in various fields. However, the computing efficiency decreases rapidly if the scale of the NN increases. In this paper, a new method of face recognition based on fuzzy clustering and parallel NNs is proposed. The face patterns are divided into several small-scale neural networks based on fuzzy clustering and they are combined to obtain the recognition result. In particular, the proposed method achieved a 98.75% recognition accuracy for 240 patterns of 20 registrants and a 99.58% rejection rate for 240 patterns of 20 nonregistrants. Experimental results show that the performance of our new face-recognition method is better than those of the backpropagation NN (BPNN) system, the hard c-means (HCM) and parallel NNs system, and the pattern-matching systemKeywords
This publication has 27 references indexed in Scilit:
- Multi-FNN identification based on HCM clustering and evolutionary fuzzy granulationSimulation Modelling Practice and Theory, 2003
- Implementation of an rbf neural network on embedded systems: real-time face tracking and identity verificationIEEE Transactions on Neural Networks, 2003
- Eigenface-domain super-resolution for face recognitionIEEE Transactions on Image Processing, 2003
- Face recognition using kernel direct discriminant analysis algorithmsIEEE Transactions on Neural Networks, 2003
- Face recognition with radial basis function (RBF) neural networksIEEE Transactions on Neural Networks, 2002
- Dynamic fuzzy neural networks-a novel approach to function approximationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2000
- Conditional fuzzy clustering in the design of radial basis function neural networksIEEE Transactions on Neural Networks, 1998
- Neural-network design for small training sets of high dimensionIEEE Transactions on Neural Networks, 1998
- Corner detection by a cost minimization approachPattern Recognition, 1993
- A Convergence Theorem for the Fuzzy ISODATA Clustering AlgorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1980