Analysis of Wavelet Families for Face Recognition
F.P. Ferreira, Tiago Buarque Assunção de Carvalho · 2017
Over the last years, the problem of facial recognition has become an important research topic because of its applications in biometrics and security. In this paper, we consider the Wavelet decomposition technique for facial feature extraction combined with Eigenfaces and Fisherfaces. We evaluate seven different Wavelet functions in five face databases, using the Nearest Neighbors (1-NN), Naive Bayes and Support Vector Machine (SVM) classifiers. The experimental results show that the highest mean recognition rate is always achieved with feature extraction using the Symlets 2 or Haar Wavelets. In some cases, these accuracies are significantly higher, for a 95% confidence level.