基于帧间差分法的口罩佩戴检测算法研究

Research on Mask Wearing Detection Algorithm Based on Inter-frame Difference Method

新冠疫情防控下,针对口罩检测难识别率低的问题,提出基于帧间差分的口罩佩戴检测算法。通过对输入的图像进行预处理,利用帧间差分法提取出前景,进而对人脸进行识别,分别统计眼部区域与口部区域肤色面积,进行比较验证算法的准确性。研究得出:相比其它算法,帧间差分算法识别率更高,识别速度较快,且不需消耗太多计算机资源;在中午良好的光照条件下,识别率较高,识别速度较快,识别率和识别速度没有受到年龄的影响;在实际应用中,可应用在小区门口、火车站、校园等人流量大的场景,经过测试,已达到可用标准。

Under the control and prevention of COVID-19,a mask wearing detection algorithm based on inter frame difference is proposed to solve the problem of difficult recognition rate of mask detection. Firstly, through the preprocessing of the input image, the foreground was extracted by using the inter-frame difference method, and then the face was recognized. The skin color areas of the eye region and the mouth region were calculated respectively, and the accuracy of the algorithm was verified by comparison. The results show that inter-frame difference method has higher recognition rate and faster speed without consuming too much computer consumption compared with other algorithms. It suggests that recognition rate is higher and recognition speed is faster under the condition of good illumination at noon, and both of them are not affected by age. In the practical application, it can be applied to the scene of large traffic such as the entrance, railway station, campus and so on. After testing, it has reached the available standard.