Extraction of facial features for the real-time human gender classification

Automatic gender detection through facial features has become a critical component in the new domain of computer human observation and computer human interaction (HCI). Automatic gender detection has numerous applications in the area of recommender systems, focused advertising, security and surveillance. Detection of gender by using the facial features is done by many methods such as Gabor wavelets, artificial neural networks and support vector machine. In this work, we have used the facial global feature distance measure as a pre-cursor to perform the support vector machine based classification technique to improve the performance results. The proposed approach seems to be promising with the test performed on the front pose images of GTAV database of AT&T by using the mat lab. The proposed method can be further evaluated in future by using different databases with various poses other than the frontal pose.