Enhancement of the Face Recognition Using a Modified Fourier-Gabor Filter

A modified Fourier-Gabor filter is used to enhance the classificationrate of the face recognition. To verify the effectiveness of the proposedmethod, five well known methods are applied to four datasets; themethods are implemented without and with the suggested filter. Thedatasets consist of varying lighting conditions, different facialexpressions, configuration, orientations and emotions. The experimentsshow that using the suggested Fourier-Gabor filter enhances theclassification rates for all methods, all datasets and all training/testingpercentage. The highest classification rates are obtained by usingFourier-Gabor filter with batch linear discriminant analysis (FGBatch-ILDA), where the average classification rate over the fourdatasets is 93.8, the next is 93.77 by using Fourier-Gabor filter withlinear discriminant analysis (FG-LDA) and 90.85 by using Fourier-Gabor filter with support vector machine (FG-SVM).