Using artificial neural network for human age estimation based on facial images

Facial image analysis has received a great deal of attention from many researcher because it leads to very important knowledge that help in improving the human-machine interaction. Recently human age estimation by face images arise as a challenging research topic. In this paper, the application of neural networks to estimate human ages was explored. The uniqueness about our research project is that we consider fine tuned age ranges than most of the previous research work do and apply our experiment to real human face image. After collecting real face images, facial features was extracted and used as inputs to learn Multi-layer perceptron neural networks (MLP). The results show that MLP network has minimum estimation error and can be considered as a good method to model accurate age estimator that could be used in many useful applications like age-based access control and age adaptive human machine interaction.