Attribute-based Face Recognition and Application in Safety Detection of Intelligent Factory
Xiangfeng Chen, Wenbai Chen, Peichao Xu, Mengyao Lv · 2018
In order to meet intelligent factory safety requirements, a safety monitoring system based on multi-attribute face recognition is introduced in this paper. The multi-attribute face recognition model is obtained by fine-tuning Resnet-50, which is applied in the mobile robot platform. When the target appears in the field of monitoring area, the multiple attributes of the target can be detected by the model. Then, the system makes the appropriate decision according to the predicted result. The experiments show that the multiple attributes of the target face can be recognized by the model. In particular, whether the target wears a helmet or not can be detected by the monitoring system. Further, the safety of intelligent factory would be improved, reducing the reliance on labor force.