Design of a Face Recognition Technique Based MTCNN and ArcFace

Dang Thai Viet, Phan Van Thien, Nguyen Huu Tu, Hoang Gia Minh, Ngoc Tam Bui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The current trend of automation and data sharing in manufacturing technologies and daily living is the 4th Industrial Revolution. Computer vision technology has permeated our daily lives as a result of advancements in artificial intelligence and processing capacity. We propose using the ArcFace model, which blends deep neural networks with multi-tasking convolutional neural networks (MTCNN). The coding procedure of the agglomeration neural network facilitates the dimension-appropriate encoding of images. Techniques aimed at enhancing face recognition’s most distinctive characteristics. For the face recognition model to operate at peak efficiency, the facial recognition feature must integrate with finger gestures to control smart home activities, communicate with data, and link effortlessly to smart devices via IoT technology. We construct a facial recognition model utilizing an embedded Jetson Nano computer, a fingerprint scanning module, and a Raspberry Pi camera. The IoT smart home utilizes an embedded Raspberry Pi 3B + computer. The results indicate an approximate precision of 96% and a processing speed of 16 FPS. The interface of an Internet of Things (IoT) smart house illustrates the successful execution of real-time functionalities.

Original languageEnglish
Title of host publicationProceedings of the 3rd Annual International Conference on Material, Machines and Methods for Sustainable Development (MMMS2022) - Volume 3
Subtitle of host publicationSustainable Approaches in Machine Design, Life Cycle Engineering, and Energy Management for Manufacturing Processes
EditorsBanh Tien Long, Kozo Ishizaki, Hyung Sun Kim, Yun-Hae Kim, Nguyen Duc Toan, Nguyen Thi Hong Minh, Pham Duc An
PublisherSpringer Science and Business Media Deutschland GmbH
Pages71-78
Number of pages8
ISBN (Print)9783031574597
DOIs
Publication statusPublished - 2024
Event3rd Annual International Conference on Material, Machines and Methods for Sustainable Development, MMMS 2022 - Can Tho, Viet Nam
Duration: 2022 Nov 102022 Nov 13

Publication series

NameLecture Notes in Mechanical Engineering
ISSN (Print)2195-4356
ISSN (Electronic)2195-4364

Conference

Conference3rd Annual International Conference on Material, Machines and Methods for Sustainable Development, MMMS 2022
Country/TerritoryViet Nam
CityCan Tho
Period22/11/1022/11/13

Keywords

  • Artificial intelligence (AI)
  • Computer vision
  • Face recognition
  • Gesture recognition
  • IoT
  • Smart home

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Mechanical Engineering
  • Fluid Flow and Transfer Processes

Fingerprint

Dive into the research topics of 'Design of a Face Recognition Technique Based MTCNN and ArcFace'. Together they form a unique fingerprint.

Cite this