DEEP LEARNING-BASED FACE MASK DETECTION USING YOLOV5 MODEL
Journal Title: Scientific Journal of Astana IT University - Year 2022, Vol 12, Issue 12
Abstract
Based on the background of rapid transmission of novel coronavirus and various pneumonia, wearing masks becomes the best solution to effectively reduce the probability of transmission. For a series of problems arising from crowded public places and collective units, where face recognition is difficult to increase target density, a deep convolutional neural network is used for real-time mask detection and recognition. This paper presents the method based on YOLOv5 model for deep learning and mask detection in image recognition as well as a live camera to label the pedestrians without masks in time. This experiment will use LabelImg software to preprocess 5003 images and make lightweight improvements based on the original YOLOv5 model to generate the final face mask recognition model. The Mosaic method is added to merge the images effectively and process the images in batch, and secondly, the GIoU loss function is selected to calculate the bounding box regression loss by comparison, which improves the localization accuracy even more. According to the experimental detection results, analogized with the original model YOLOv5, the recall and accuracy are effectively improved. In this paper, YOLOv3, SSD, Fast-R-CNN detection algorithms are used for comparison, the detection results of this model have a high mAP value which is equal to 92.9, which are higher than the detection results of other models. Real-time target recognition based on this model combined with practical applications can be applied in hospitals and crowd-gathering places to achieve effective reduction of epidemic transmission probability in a short period of time.
Authors and Affiliations
Saya Sapakova, Yelidana Yilibule
SYSTEM OF PREVENTIVE АCTION OF CONSTRUCTION ENTERPRISES ON THE BASIS OF IDENTIFICATION OF ANTICRISIS POTENTIAL
Peculiarities of formation of anti-crisis potential of construction enterprises are considered. Construction companies are rapidly adapting to the requirements of the digital economy, transforming the management struct...
MODEL DEVELOPMENT AND CALCULATIONS FOR 35/10 KV ELECTRICAL SUBSTATIONS IN TURKESTAN REGION USING RASTRWIN3 PROGRAM
The city of Turkestan, Kazakhstan is experiencing growth leading to an increased need for electricity. In order to meet this demand the city is upgrading its infrastructure specifically focusing on improving its 35/10 k...
APPLICATION OF MACHINE LEARNING FOR RECOGNIZING SURFACE WELDING DEFECTS IN VIDEO SEQUENCES
The paper offers a solution to the problem of detecting and recognizing surface defects in welded joints that appear during tungsten inert gas welding of metal edges. This problem belongs to the machine vision. Welding o...
IMPROVING THE METHOD OF SEARCHING DIGITAL ILLEGAL MEANS OBTAINING INFORMATION BASED ON CLUSTER ANALYSIS
Іn the article the possibilities of the multipositional technology of searching digital insertion devices are investigated based on clustering. Existing means of detecting radiation of digital illegal means obtaining inf...
INFORMATION-ANALYTICAL SYSTEM FOR EVALUATING THE SCIENTIFIC PERFORMANCE OF STRUCTURAL UNITS OF UNIVERSITIES AND RESEARCH INSTITUTES BASED ON THE APPROACH OF CONSTRUCTING COMPLEX INTEGRAL EVALUATION
The article discusses the creation of an information-analytical system for evaluating the scientific performance of structural units of universities and research institutes based on the approach of constructing complex...