Contribution of Interesting Facial Parts on Gender Recognition System Performance

Abstract

Recently, the gender recognition system is very important for interaction applications such as consultation questions, legal gender access. There are many research works which used facial information to detect the gender type. One of the most interesting research works is Azzopardi work who used bank of Gabor filters to segment randomly-chosen sub faces. In this research, his proposed model is evaluated on manually-chosen interesting sub-faces such as eye, eyebrow, nose, mouth and mixture of all sub-faces. The observed results showed enhancement in classification accuracy that achieved 95.10% by selecting all the interesting parts of facial image.