Improved Viola-Jones face detection algorithm based on HoloLens

The current face detectionin Microsoft HoloLens can only be achieved by remote call of face detectioninterface algorithm which is, however, restricted by network, resulting in slow detection and failing to meet real-time detection demand. This paper proposes an improved Viola-Jones algorithm of face detectionbased on HoloLens upgrading classical Viola-Jones face detectionalgorithm relying on Haar-like rectangle feature expansion to enhance detection efficiency, and accelerating detection building on two-dimensional convolution separation and image re-sampling technique. The detection efficiency of improved face detectionalgorithm is 12% on average higher than that of existing face detectioninterface algorithm, and its detection speed is four-folded. Moreover, HoloLens depth camera enables 3D face detectionand location, and its unique gaze, voice, and gesture interacting techniquesfree the hands, thereby realizing easier and less-burdened man-computer interaction. HoloLens furnished with real-time video face detectionalgorithm as detailed in this paper can be applied in such fields as social contact, public security, and business management.