An Assimilated Face Recognition System With effective Gender Recognition Rate

Gender Recognition in Face Recognition System has prevalent applications in the fields of demographic data collection, video surveillance, security, retail advertising and marketing and it also plays a vital role on object recognition in robot research area, which has shown an intensive attention in the past few years.However, face recognition is still a challenging task since face images are easily confused by changes of the facial factors, such as illumination, pose, the different expressions, or glasses. The goal of this paper is to improve the effectiveness of gender recognition when there are affected(blurred) images in the dataset. We applied novel descriptor based COSFIRE filters to achieve the Gender Recognition[1] in the Face Recognition System. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest on FERET training set. Extensive experiments were conducted on the GENDER-FERET dataset which contains 474 training and 472 test samples and demonstrated robustness and effectiveness of the proposed model. It also outperforms an approach that relies on handcrafted features and an ensemble of classifiers.