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

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings of the 3rd Annual International Conference on Material, Machines and Methods for Sustainable Development (MMMS2022) - Volume 3
ホスト出版物のサブタイトルSustainable Approaches in Machine Design, Life Cycle Engineering, and Energy Management for Manufacturing Processes
編集者Banh Tien Long, Kozo Ishizaki, Hyung Sun Kim, Yun-Hae Kim, Nguyen Duc Toan, Nguyen Thi Hong Minh, Pham Duc An
出版社Springer Science and Business Media Deutschland GmbH
ページ71-78
ページ数8
ISBN(印刷版)9783031574597
DOI
出版ステータスPublished - 2024
イベント3rd Annual International Conference on Material, Machines and Methods for Sustainable Development, MMMS 2022 - Can Tho, Viet Nam
継続期間: 2022 11月 102022 11月 13

出版物シリーズ

名前Lecture Notes in Mechanical Engineering
ISSN(印刷版)2195-4356
ISSN(電子版)2195-4364

Conference

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

ASJC Scopus subject areas

  • 自動車工学
  • 航空宇宙工学
  • 機械工学
  • 流体および伝熱

フィンガープリント

「Design of a Face Recognition Technique Based MTCNN and ArcFace」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル