Joint Demographic Features Extraction for Gender, Age and Race Classification based on CNN

Abstract

Automatic verification and identification of face from facial image to obtain good accuracy with huge dataset of training and testing to using face attributes from images is still challengeable. Hence proposing efficient and accurate facial image identification and classification based of facial attributes is important task. The prediction from human face image is much complex. The proposed research work for automatic gender, age and race classification is based on facial features and Convolutional Neural Network (CNN). The proposed study uses the physical appearance of human face to predict age, gender and race. The proposed methodology consists of three sub systems, Gender, Ageing and Race. Therefore different feature are extracted for every sub system. These features are extracted by using Primary, Secondary features, Face Angle, Wrinkle Analysis, LBP and WLD. The accuracy of classification is based on these features. CNN used to classify by using these features. The proposed study has been evaluated and tested on large database MORPH II and UTKF. The performance of proposed system is compared with state of art techniques.