Research on the Application of Object Detection and Data Collection in Recruitment System

This paper uses data collection and target identification to improve the recruitment system. The YOLOv3 neural network was used to train it, and the employee behavior recognition model under multiple postures was obtained. This model has strong adaptive ability. The behavior is analyzed preliminarily based on the method of pedestrian motion analysis and motion detection. Considering the similarity, brightness, and other attributes of the face, the depth recognition and judgment of the actions of pedestrians when going out, sleeping and playing mobile phones are carried out. Simulation results show that the proposed method can effectively solve the problem of pedestrian recognition in complex scenes.