Rapid face detection in complex environments based on the improved RetinaFace

Abstract

Now the epidemic prevention and control has been continuing, frequent removal and wearing of masks in railway stations, subway stations and places such as commuting to and from work are prone to the spread of the virus, and face detection is an important part of the face recognition system. Aiming at the complex environmental factors such as partial occlusion, angle change, light intensity and face blur in face detection in these places, This paper improves the detection accuracy by improving the RetinaFace algorithm. Firstly, the lightweight GhostNet network is introduced to substitute the former MobileNet0.25 backbone network of RetinaFace, and a lightweight model improved version of RetinaFace is obtained, which not only ensures that the model is smaller but also ensures the speed of face detection; In addition, The efficient ECA channel attention mechanism is fused in the enhanced feature extraction network of the model to further enhance the detection performance of small face samples in complex environments. Finally, the simulation conclusion show that compared with the former RetinaFace algorithm, the detection performance of this method in the verification set of different levels of the reconstructed WIDER FACE dataset reaches 93.4% (Easy), 90.8% (Medium) and 77.1% (Hard), which is improved by 2.7 percentage points, 2.2 percentage points and 5 percentage points, respectively. It can be seen that after the introduction of GhostNet network and ECA attention mechanism, the recognition accuracy of faces in complex environments is further improved and network performance is improved.