A Comparative Study of Feedforward Neural Network and Simplified Fuzzy ARTMAP in the Context of Face Recognition

Abstract

AbstractFace recognition has become one of the most active research areas of pattern recognition since the early 1990s. In this paper, a comparative study of two face recognition methods is discussed. One method is based on PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis) and Feedforward Neural Network (FFNN) and the second method is based on PCA, LDA and Simplified Fuzzy ARTMAP(SFAM). Combination of PCA and LDA is used for improving the capability of LDA and PCA when used alone. Neural classifier (FFNN or SFAM) is used to reduce the number of misclassifications. Experiment is conducted on ORL database and results demonstrate SFAM as more efficient recognizer, both in terms of recognition rate and time complexity, when compared to FFNN. SFAM has the added advantage that the network is adaptive, that is, during testing phase if the network comes across a new face that it is not trained for; the network identifies this to be a new face and also learns this new face. Thus SFAM can be used in applications where database needs to be updated frequently.KeywordsFace recognitionPrincipal Component AnalysisLinear Discriminant AnalysisFeedforward Neural NetworkSimplified Fuzzy ARTMAP