Development of a Real-Time Facemask Detector Using YOLOv4 Object Detection Model and OpenCV /
De Leon, Christian Noel U.
Development of a Real-Time Facemask Detector Using YOLOv4 Object Detection Model and OpenCV / Christian Noel U. De Leon, Ronald Andrie G. Mutuc, Jomari L. Tagra. - x, 100 pages : illustrations ; 28 cm. + 1 CD-ROM (4 3/4 in.)
Thesis (Undergraduate)
College of Science --
Includes bibliographical references.
COVID-19 began more than 2 years ago and is still a threat to human lives today. One of the most important preventive measures that is still being implemented today is the wearing of facemasks. The general objective of the study is geared towards the development of real-time facemask detector entitled "Real-time Facemask Detector Using YOLOv4 Object Detection Model and OpenCV". The real-time facemask detector model was built using predefined weights of YOLOv4 and uncompressed version of CSPDarknet-53 with 53 convolutional layers serving as a backbone. The model will recognize whether the subject is wearing a facemask, incorrectly wearing one, or none at all. The model also used 856 images per class for training. Throughout the project development, the researchers followed the Agile methodology. While in testing, Portability and Reliability testing was performed then evaluated by different people from all age group. The result showed that the software can detect a 416x416 frame with a mean average precision of 94.60% in a class containing Correct facemasks, 60.47% in Incorrect, and 85.10% in no facemask. Furthermore, the system got an overall mean of 3.59 or "Highly Acceptable" rating from the thirty (30) respondents. The developed system is meant to provide aid to frontline workers who are in patrol implementing the basic health protocols.--Author's Abstract
Facemasks -- Detection. Facemasks -- Recognition.
BTH QA 76 / D45 2022
Development of a Real-Time Facemask Detector Using YOLOv4 Object Detection Model and OpenCV / Christian Noel U. De Leon, Ronald Andrie G. Mutuc, Jomari L. Tagra. - x, 100 pages : illustrations ; 28 cm. + 1 CD-ROM (4 3/4 in.)
Thesis (Undergraduate)
College of Science --
Includes bibliographical references.
COVID-19 began more than 2 years ago and is still a threat to human lives today. One of the most important preventive measures that is still being implemented today is the wearing of facemasks. The general objective of the study is geared towards the development of real-time facemask detector entitled "Real-time Facemask Detector Using YOLOv4 Object Detection Model and OpenCV". The real-time facemask detector model was built using predefined weights of YOLOv4 and uncompressed version of CSPDarknet-53 with 53 convolutional layers serving as a backbone. The model will recognize whether the subject is wearing a facemask, incorrectly wearing one, or none at all. The model also used 856 images per class for training. Throughout the project development, the researchers followed the Agile methodology. While in testing, Portability and Reliability testing was performed then evaluated by different people from all age group. The result showed that the software can detect a 416x416 frame with a mean average precision of 94.60% in a class containing Correct facemasks, 60.47% in Incorrect, and 85.10% in no facemask. Furthermore, the system got an overall mean of 3.59 or "Highly Acceptable" rating from the thirty (30) respondents. The developed system is meant to provide aid to frontline workers who are in patrol implementing the basic health protocols.--Author's Abstract
Facemasks -- Detection. Facemasks -- Recognition.
BTH QA 76 / D45 2022