Abstract
Calculating the number of people is often necessary and repeated in real life. As the number of people increases, the calculation is time-consuming. Efficiently calculating the number of people is helpful to human life. In this article, we propose a valuable app to quickly calculate the number of people in a photo by a convolutional neural network (CNN). Initially, suspected face areas are segmented into micro-blocks. The segmented blocks are then confirmed through the CNN by rejecting the segmented micro-blocks without the human face to ensure the detection accuracy of the face area. The experimental results reveal that the proposed app can efficiently calculate the number of people. The world is now seriously threatened by the COVID-19 epidemic. The proposed app can help quickly calculate the number of people, avoid crowd gathering, and cause the risk of group infections.
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference25 articles.
1. A novel facial image recognition method based on perceptual hash using quintet triple binary pattern
2. Image set-based face recognition using pose estimation with facial landmarks
3. Cascaded asymmetric local pattern: a novel descriptor for unconstrained facial image recognition and retrieval
4. New approach to face recognition using co-occurrence matrix and Bayesian neural networks;Hssayni;Proceedings of the IEEE International Conference on Optimization and Applications 2020,2020
5. Rapid object detection using a boosted cascade of simple features;Viola;Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2001,2001
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献