Age, Gender And Emotion Detection

Abstract

The main reason is the development of a method to automatically estimate the age and gender of the human face. It continues to play an important role in computer vision and pattern recognition. In addition to age determination, facial emotion recognition also plays an important role in computer vision. Nonverbal communication methods such as facial expressions, eye movements, and gestures are used in many human-computer interaction applications. Much research has been done to create computer models of human age, gender, and emotions. But it is still far behind the human visual system. This project proposes a convolutional neural network (CNN) -based architecture for age and gender classification. The architecture is trained to label input images with eight ages and two genders. Our approach shows that age and gender classification is more accurate than the classifier-based method. Computer modelling of human emotions will use Deep CNN to predict human emotions and observe how facial emotional intensity changes from low to high emotional levels. A Viola-Jones pre-processing algorithm was used to extract features from the image supplied as input to the CNN. With the appropriate user interface, the prediction results will be displayed.