Chef cap and mask wearing detection method based on deep learning

Abstract

The invention provides a chef hat and mask wearing detection method based on deep learning. The chef hat and mask wearing detection method comprises the steps: collecting head images in a kitchen scene; preprocessing the human head image, and constructing a human head detection data set; putting the training set into a convolution feature device to extract features related to the chef cap and themask, generating a predicted human head bounding box by generating the Anchor box number through a K-means clustering method, and taking the intersection ratio of a candidate box and a real box as anevaluation standard; inputting the training set data into a YOLOv3 network for repeated training to obtain a weight value and an offset value of a convolutional layer, and outputting a loss function value of the training set data; and compressing the trained model to meet real-time detection conditions, detecting the model, detecting the head image according to the trained model, and respectivelyoutputting results including prediction bounding boxes and categories of the chef cap and the mask.

Description

technical field [0001] The present invention mainly relates to the field of image processing, in particular to a detection method for wearing a chef hat and a mask based on deep learning. Background technique [0002] Mask is a commonly used daily necessities, which can effectively prevent dust, harmful gas, saliva droplets, etc. from entering and exiting the nose. In health places such as hospitals, wearing a mask can not only protect yourself from the hazards of infectious diseases; in areas with large dust in working environments such as construction sites and factories, you should wear a mask to prevent yourself from inhaling dust and causing harm to your health. In addition, in some key monitoring places, such as ATM cash machines, suspicious elements will deliberately cover their faces with masks in order to avoid being captured by cameras. For these places that need to identify whether to wear masks, there is currently no method that can quickly and automatically det...

AI Technical Summary

Problems solved by technology

[0007] To sum up, the current methods for hats and masks mainly have the following shortcomings: first, the application scenario is single and unstable; second, the target is simple and the process is complicated; third, it is not possible to extract features for the target; fourth, Slow speed; fifth, low accuracy; sixth, large memory usage; seventh, low scalability

Images