Face mask wearing condition detection method based on deep learning

Abstract

The invention belongs to the field of deep learning, and particularly relates to a face mask wearing condition detection method based on deep learning. The method comprises the following steps: obtaining the data of a to-be-detected image in real time, inputting the to-be-detected image into a trained mask detection network model, and obtaining a detection result; marking the to-be-detected image according to a detection result; the mask detection network model comprises a backbone feature extraction network model, a Neck network module and a Prediction network; the CSPDarkNet-X module is used in the backbone feature extraction network in the mask detection model, so that the feature extraction capability of the model can be enhanced, the parameter quantity of the model can be reduced, the structure of the backbone network of the model is simplified, and the feature learning capability of the model is improved.

Description

technical field [0001] The invention belongs to the field of deep learning, and in particular relates to a method for detecting the wearing condition of a face mask based on deep learning. Background technique [0002] Respiratory tract infectious disease viruses, toxic and harmful gases, dust and other harmful substances to the human body can enter the body through the human respiratory and circulatory system, thereby causing damage to the human body, and even life-threatening in severe cases. Regular wearing of masks can effectively prevent viruses, dust, and toxic and harmful gases from entering lungs, nerves and other vital tissues, and reduce the risk of personnel being infected, as a source of transmission, and poisoning damage. The face mask wearing mask detection algorithm can be applied to community access control, airports, campuses, streets, hospitals and other public places. The algorithm analyzes the characteristics of the face wearing a mask to determine whethe...

AI Technical Summary

Problems solved by technology

[0003] At present, there are few related studies on face mask recognition. The key is: first locate the position of the face in the image; then identify whether the face given by the data set is wearing a mask and whether it is wearing the mask correctly

However, there are few existing mask datasets and there are problems such as insufficient category, environment, and scale information.

Complex environments can usually be face occlusion, variable face scale, unbalanced illumination, dense, etc. These problems are the main reasons that affect the performance of the detection algorithm. At the same time, such problems can easily lead to poor generalization ability of the model and redundant information. surplus, low precision, poor real-time performance, etc.

[0004] At present, the problems of target detection algorithms based on deep learning are: poor real-time performance, large model size, poor detection effect of small targets, poor robustness, poor adaptability, weak generalization ability, etc.

At the same time, when the algorithm is used in the actual complex environment, due to the external interference of the target such as occlusion and multi-scale, there are still some shortcomings in directly using the current mainstream target detection algorithm for face mask detection.

Its main manifestations are: there are still problems such as insufficient shallow feature extraction for multi-scale targets; in actual use, the model has a lot of redundant information, which makes the model have more operating costs in reasoning; the model There are problems such as high training cost, high computing consumption, and the model is too complex to deploy

Images