An illumination, expression, and noise invariant gender classifier using two-directional 2DPCA on real Gabor space

This work investigates a framework for gender classification which is invariant to illumination, expression, and noise. It utilizes 2D Gabor filter along with two-directional 2DPCA. Gabor filter gives the real Gabor space which contains crucial face information and prohibits the illumination, expression, and deformation to a certain extent. The real Gabor space is high dimensional to represent face images. To select the most discriminate feature set from the real Gabor space, 2DPCA in horizontal and vertical directions is used. The proposed scheme is evaluated through a number of well-known face image databases. The system yields classification rate of 98.18%, 96.61%, 96.15%, 93.33%, and 88.34% for FERET, FIE A, AR, Indian Face, and LFW, respectively. In the presence of illumination, expression, and noise, the system gives more than 90% accuracy for all databases except LFW. The system does so with reduced features which make it suitable for real life applications.