Face mask detection based on Transfer learning and PP-YOLO
Jian Wang, Lang Lin
Abstract
Taking into account the accuracy and reasoning speed of face mask detection tasks, this paper proposes a detection model PP-YOLO-Mask based on PP-YOLO through transfer learning, data augmentation and model compression methods. In a public scene, the mask detection mAP of this model is 86.69%, and the single picture recognition speed is 11.842ms. Experimental results show that compared with YOLOv3 and FasterRCNN, the model has faster accuracy and detection speed.
Topics & Concepts
Artificial intelligenceComputer scienceFace (sociological concept)Transfer of learningComputer visionFace detectionObject detectionFacial recognition systemObject-class detectionDeep learningPattern recognition (psychology)SociologySocial scienceFace recognition and analysisVideo Surveillance and Tracking MethodsAdvanced Neural Network Applications