Performance improvement in face recognition system using optimized Gabor filters

A biometric method for identifying people is face recognition. In the face recognition process, the key step is to extract the distinctive features of each person’s image. One of the most widely used tools for this purpose is the Gabor filter bank. A Gabor filter bank can extract powerful distinguishing features from a face image, but the disadvantage is that it imposes a high computational complexity on the face recognition system. The present paper introduces two new Gabor filter banks, i.e., the Optimal Gabor Filter Bank (OGFB) and the Personal Gabor Filter Bank (PGFB), which can reduce the computational complexity of a face recognition system by more than 7.5 and 30 times, respectively. It also introduces a new feature called Square Region of Face (SRoF) which is as easy to implement as global features, while taking into account the geometric position of facial features, including eyes, nose, and lips. This new feature is resistant to changes of hairstyle, eyebrows shape, and their color, as well as to the covered part of faces especially by different types of Islamic veils. Experiments on benchmark datasets of Caltech, Yale, Feret, and CsetM show that the proposed methods achieve better or competitive classification accuracy compared to several recent face recognition systems.