Facial emotion recognition is identifying human emotion from facial expressions. As the concept is gaining wide popularity with time, researchers are trying to expand the horizon by providing efficient techniques to extract more knowledge from facial features. Hence, this paper presents a multiple face detection system, which is capable of analyzing human facial features for predicting human emotion, pose, gender and age. To the best of our knowledge, no single paper presents a system capable of detecting all these features together in a single frame. Haar cascades and deep convolutional neural networks form the backbone of the entire work. A support of a Web application using flask is also provided, which will enable one to implement the work on another computer, in the same network, via a Web browser. The experimental results of the system provide an accuracy of 68.33%.
CITATION STYLE
Virmani, D., Sharma, T., & Garg, M. (2021). GAPER: Gender, Age, Pose and Emotion Recognition Using Deep Neural Networks. In Lecture Notes in Mechanical Engineering (pp. 287–297). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-5463-6_26
Mendeley helps you to discover research relevant for your work.