What is it about?
In view of the low accuracy of mask wearing recognition caused by factors such as multiple and small target recognition, extreme lighting conditions and low definition, this paper proposes a fusion algorithm that integrates the attention mechanism FcaNet and dense convolution blocks into YOLOv5s. The fusion algorithm is used to address the issue including small target identification and low-resolution facial image recognition. This paper obtains data from opensource datasets RMFD (Real-World Masked Face Dataset) and celebA, uses fusion algorithm for feature extraction, and finally uses FaceNet and support vector machine (SVM) for face mask wearing recognition. After experimental comparison, the fusion algorithm can achieve 97.55% accuracy of face mask wearing recognition under different complex environments, and the average frame rate is 30.3FPS. The algorithm model improves the recognition rate of mask wearing under occlusion conditions and with different clarity, has higher recognition performance, and can be used for mask wearing recognition when entering public places.
Featured Image
Perspectives
This paper proposes a face mask wearing recognition model that incorporates FcaNet and dense convolution blocks into YOLOv5 fused FaceNet, based on the YOLOv5s network, and integrates the advantages of dense convolution blocks for feature retention and feature processing, so that the picture has more features. The points are retained, which improves the accuracy of face detection and recognition, and also makes up for the difficulty of YOLOv5s in small target detection. Experiments show that, in terms of recognition rate, compared with traditional FaceNet and YOLOv5s+FaceNet, the fusion algorithm in this paper has a higher recognition rate on the test data set, and can process face pictures of different clarity, with good performance. Generalization performance. In the next step, the author will consider how to improve the face recognition frame rate and model optimization, and try to test occlusion-type face recognition on more datasets.
Qi Yan
吉利学院
Read the Original
This page is a summary of: Mask Wearing Recognition Based on Fusion Algorithm, June 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3546632.3546879.
You can read the full text:
Contributors
The following have contributed to this page
