Gender Classification Using Hybrid of Gabor Filters and Binary Features of an Image

Abstract

Face is one of the most important biometric of human and contains lots of useful information such as gender, age, race and identity. Gender classification is very easy for human but it considers a challenge for computers. Gender classification through face images has recently been considered so much. Gender recognition can be useful in interaction between human and computer like identifying individual’s identity. It is also applicable in TV networks in order to study the rate of viewers. Various algorithms have been designed for this issue and each of them has unraveled that to some extent. The last obtained rate to identify gender was through article written by Dr. Mozaffari who obtained mean rate of 83% for identification. It is the proposed method of the present study which has brought identification rate to 92.5. in this method we draw out face features based on Gabor filters and local binary patterns. These features are resistant against noise and they select proper features against bottleneck of images. In order to obtain a proper classification, we use self-organized map (SOM) (type of artificial neural network). This neural network finds the proper weights for each gender with very little error. Obtained results are compared with existing datasets and therefore, superiority of the proposed method would be evident. DOI: http://dx.doi.org/10.11591/ijece.v4i4.5926