YOLO-FaceNet Fusion: Innovative System for Facial Recognition and Feature Extraction
- Version
- Download 61
- File Size 698.09 KB
- File Count 1
- Create Date 24 May 2024
- Last Updated 24 May 2024
YOLO-FaceNet Fusion: Innovative System for Facial Recognition and Feature Extraction
Mr. Mukesh Kumar[1], Aman Kumar[2], Ankush Gupta[3], Gaurav Kapoor[4], Vineet Vashishtha [5]
Assistant Professor[1], student[1], student[2], student[3], student[4]
(Department of Computer Science and Engineering: Internet of Things)
Meerut Institute of Engineering and Technology, Meerut
mukesh.cs@miet.ac.in[1], aman.kumar.cseiot.2020@miet.ac.in[2], ankush.gupta.cseiot.2020@miet.ac.in[3],
gaurav.kapoor.cseiot.2020@miet.ac.in[4], vineet.vashishtha.cseiot.2020@miet.ac.in[5]
Abstract:
Facial verification is vital in domains like Heathcare, Identity verification, etc. study presents a sophisticated facial verifying system utilizing state-of-the-art technologies: ArcFace is utilized for the edification of the model, while FaceNet is employed for the elicitation of facial characteristics. Initially, YOLO is deployed to discern and extricate visages from the input effigies. Subsequently, FaceNet is utilized to derive high-caliber facial attributes. In the final stage, ArcFace is employed for the model's edification, thus augmenting its robustness and precision. The apparatus gauges facial resemblance employing the Euclidean distance metric and is appraised through measures such as recall, accuracy, and precision. This approach yields a dependable and accurate facial verification system, thereby enhancing operational efficiency in practical applications..
Keywords – You Only Look Once (YOLO), ArcFace, Convolutional Neural Network (CNN), FaceNet, Machine Learning, Deep Learning, Euclidean Distance.
Download