Human Age And Gender Classification using Convolutional Neural Network
Mohammed Kamel Benkaddour, Sara Lahlali, Maroua Trabelsi
Abstract
Pattern recognition and automatic classification are very active research areas, their main objectives are to develop intelligent systems able to achieve efficiently learning and recognizing objects. An essential section of these applications is attached to biometrics, which is used for security purposes in general. The facial modality as a fundamental biometric technology has become increasingly important in the field of research. The goal of this work is to develop a gender prediction and age estimation system based on convolutional neural networks for a face image or a real-time video. In this paper, three CNN network models were created with different architecture (the number of filters, the number of convolution layers ...) validated on IMDB and WIKI dataset, the results obtained showed that CNN networks greatly improve the performance of the system as well as the accuracy of the recognition.