Improved Face Gender Identification Using Fusion of Global Thepade’s SBTC and Local OTSU Thresholding Features

In Image Processing, the face gender classification in the real time applications is an interesting area having important significance. Human can recognize the gender easily but machines find it difficult to recognize the gender from facial images. Many researchers are working in order to fill this gap. The recognition of gender is important for the human computer interaction. The goal of this paper is to propose machine learning based face image gender recognition using global Thepade's SBTC and local Otsu's thresholding features which will help to recognize gender. The experimentations performed on Faces94 dataset and face gender recognition accuracy have shown the proposed method has given better face gender recognition capability with feature fusion across considered machine leaning classifiers.