Open AccessFace recognition using multitasking cascading convolutional networks
Author(s) -
A G Musikhin,
S Yu Burenin
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1155/1/012057
Subject(s) - convolutional neural network , computer science , human multitasking , facial recognition system , artificial intelligence , identification (biology) , biometrics , face (sociological concept) , machine learning , face detection , process (computing) , task (project management) , upload , pattern recognition (psychology) , operating system , engineering , psychology , social science , botany , systems engineering , sociology , cognitive psychology , biology
The face recognition has many applications in such areas like intelligent security and access control, biometrics, safeguard, verification, attendance accounting, machine vision, etc. Identification of a personality by the face has a number of advantages over other methods: the person does not need to be contacted physically, which is the most acceptable way for mass applications and no complicated or expensive equipment is required. This article discusses the problem of recognition and identification of a person’s face using convolutional neural networks that process frames from a camera in real time or from a recorded video file with the subsequent entry of the identified person into the database. Multitasking Cascade Convolutional Neural Network (MTCNN) has three convolutional networks (P-Net, R-Net, and O-Net) and is capable of outperforming many face detection tests while maintaining real-time performance. The proposed method for human face recognition was developed as a software product, tested and showed the probability of correct recognition in real time 96.02%.