AffectiveHMD is a facial expression recognition technology inside of Head Mounted Display (HMD) by photo reflective sensors and machine learning. HMDs allow people to enjoy an immersive Virtual Reality (VR) experience. However, the major problem of wearing an HMD is that a large portion of the user’s face is occluded, making facial recognition difficult in an HMD-based virtual environment. To overcome this problem, we propose a facial expression recognition technology using photo reflective sensors. The sensors attached inside the HMD measures the distance between the sensors and the user’s face as reflection intensity. By learning the sensor values of basic facial expressions, our system can recognize the user’s facial expression. Our system can also reproduce facial expression change through an avatar in the virtual environment.
In this exhibition, we demonstrate facial expression recognition technology inside the head mounted display (HMD) using photo reflective sensor and machine learning. By acquiring reflection intensity information with a large number of optical sensors embedded in HMD and training a machine learning system, our system is able to recognize basic facial expressions. Furthermore, by compositing the basic facial expressions, the user’s facial expressions are reflected to the avatar in the virtual environment.