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.

By:

De Leon, Christian Noel U

Contributor(s):

Material type: Text

TextManila : Technological University of the Philippines, 2022Description: x, 100 pages : illustrations ; 28 cm. + 1 CD-ROM (4 3/4 in.)Content type:

text

Media type:

unmediated

Carrier type:

volume

Subject(s):

Facemasks -- Detection. Facemasks -- Recognition

LOC classification:

BTH QA 76 D45 2022

Dissertation note: College of Science -- Bachelor of Science in Computer Science, Technological University of the Philippines, 2022. Abstract: 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

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Notes	Date due	Barcode
Bachelor's Thesis COS	TUP Manila Library	Thesis Section-2nd floor	BTH QA 76 D45 2022 (Browse shelf(Opens below))	c.1	Not for loan	For Room Use Only		BTH0003254

Thesis (Undergraduate)

College of Science -- Bachelor of Science in Computer Science, Technological University of the Philippines, 2022.

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

There are no comments on this title.

to post a comment.