The face recognition demo shows person facial feature training via a single photo and subsequent face matching on the live video stream, using VisionLabs’ library integrated onto the H22 System on a Module (SoM).

2D face recognition is an extensively studied, but still evolving subject of research. Various strategies including statistical approaches, hidden Markov models, neural networks, template based and feature based matching have been proposed. Here we briefly present our implementation which is based on past research and achieves state-of-the-art recognition performance on considerably low resolution input facial images.
Our approach can be divided into three independent phases: Facial landmarks library construction (offline), Building of facial descriptor (once per novel image) and Facial descriptors matching.