Face Recognition using Bank of Gabor Filters

The biometric schemes are commonly used for the identification of human beings. Face recognition approach has been employed using different algorithms for the purpose of identification of individuals. This paper describes utilization of Gabor filters for selecting feature vectors/coefficients. It explains construction of Gabor filters, selection of peaks, feature storage and classification of faces. Standard and improved classifier schemes have been used to evaluate the developed face recognition system in terms of detection rate and speed by using 20 to 60 Gabor filters. Evaluation results have been obtained through ORL database where 200 images have been used for training and 200 images for testing (i.e. first five images of each person for training and remaining five images for testing). The results show that the improved classifier extracts 8878 feature vectors for a bank of 40 Gabor filters and provides detection rate of 92.5 % whereas a bank of 30 Gabor filters provided detection rate of 93% by extracting 8700 feature vectors. It has also been noted that training and time for a single image using 30 Gabor filters is 5.35 and 14.5 seconds respectively which is less as compared to 40 Gabor filter-based system