» Today: 29/03/2024
Technology
AI system recognizes faces in a second
The system manufactured by a research group of Hanoi University of Science and Technology in collaboration with enterprises can recognize faces with 99.7% accuracy.


Associate Professor Thuan (middle) guided students to research the system. Photo: NX.

The idea of designing an entrance control system was conceived by Ngo Huu Son, a fourth-year student at the Institute of Information and Communication Technology, Hanoi Polytechnic University, as he watched teachers take time to take attendance everyday or students are waiting in long lines to register their parking tickets, so they are late for class. At the end of 2019, with the guidance of Assoc.Prof.Dr. Do Phan Thuan, Lecturer at the Institute, Son and three final-year students, Nguyen Van Tien, Hoang Quoc Hao, and Nguyen Van Long, plan to bring face recognition technology with artificial intelligence (AI) and computer vision technology to build door control system.

This idea is also supported by a business to develop commercialized products. The enterprise provides smart software, hardware including identification camera, lane gate, automatic barrier. The research team is responsible for making the system identification and control software. Associate Professor Thuan said that all hardware is connected to the system, the algorithm of the image processor and the controller, for fast and accurate facial recognition up to 99.7%.

High-quality images (up to 4K) of the camera are processed in real time at 30 frames per second. When detecting someone in front of the camera, the computing device will assist in selecting the best quality face on the central processor for recognition by algorithms.

If a pre-declared user is found in the system, the central processor analyzes and sends a signal to the device to activate the gate opening, signal on or sound notification. Content attendance is included in CMS content management system, reports can be extracted. The whole process of identifying and giving feedback of the system takes less than a second.

ntptuong
Follow vnexpress.net
Print  
Top
© Copyright 2010, Information and Documentation Center under Can Tho Science and Technology Department
Address: 118/3 Tran Phu street, Cai Khe ward, Ninh Kieu district, Can Tho city Tel: 0710 3824031 - Fax: 0710 3812352 Email: tttlcantho@cantho.gov.vn License No. 200/GP-TTÐT dated November 11st, 2011 by Agency for Radio, Television and Electronic Information under Minister of Information and Communication