A mask recognition algorithm based on improved YOLO-V4 neural network (Preprint)

2021 ◽  
Author(s):  
Song Zhang ◽  
Shaoqiang Wang ◽  
Shaoqiang Wang
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Target Detection ◽  
Network Model ◽  
Neural Network Model ◽  
Prevention And Control ◽  
Preventive Measures ◽  
Recognition Algorithm ◽  
Facial Features ◽  
And Control

BACKGROUND With the spread of the new crown virus, the wearing of masks as one of the effective preventive measures is getting more and more attention, and the behavior of not wearing a mask is likely to cause the spread of the virus, which is not conducive to the prevention and control of the epidemic. OBJECTIVE In this paper, a new neural network model is used to better recognize the facial features of people with exit masks. METHODS This paper proposes a mask recognition algorithm based on improved YOLO-V4 neural network that can solve this problem well. This paper integrates SE-Net and DenseNet network as the reference neural network of YOLO-V4 and introduces deformable convolution. RESULTS Compared with other target detection networks, the improved YOLO-V4 neural network used in this paper improves the accuracy of mask detection to a certain extent. CONCLUSIONS The improved YOLO-V4 network proposed in this article has verified its feasibility and accuracy through experiments and has great value in use. Improving the YOLO-V4 network can help better respond to face recognition with masks in the epidemic. However, the model studied in this article focuses on accuracy and is slightly lacking in speed. The next step is to increase its speed based on ensuring accuracy and consider actual deployment and use.

Intelligent Computing Based on Neural Network Model in Problems of Kinematics and Control of Parallel Robot

2018 ◽  
Author(s):  
Sergey Yuriyevich Khalapyan ◽  
Anton Igorevich Glushchenko ◽  
Larisa Alexandrovna Rybak ◽  
Elena Vladimirovna Gaponenko ◽  
Dmitry Ivanovich Malyshev
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Parallel Robot ◽  
Intelligent Computing ◽  
And Control

scholarly journals Neural Network Model for Face Recognition from Dynamic Vision Sensor

2020 ◽  
pp. short17-1-short17-8
Author(s):  
Fedor Shvetsov ◽  
Anton Konushin ◽  
Anna Sokolova
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Network Model ◽  
Neural Network Model ◽  
Synthetic Data ◽  
Simulated Data ◽  
Fine Tuning ◽  
Vision Sensor ◽  
Dynamic Vision ◽  
The Face

In this work, we consider the applicability of the face recognition algorithms to the data obtained from a dynamic vision sensor. A basic method using a neural network model comprised of reconstruction, detection, and recognition is proposed that solves this problem. Various modifications of this algorithm and their influence on the quality of the model are considered. A small test dataset recorded on a DVS sensor is collected. The relevance of using simulated data and different approaches for its creation for training a model was investigated. The portability of the algorithm trained on synthetic data to the data obtained from the sensor with the help of fine-tuning was considered. All mentioned variations are compared to one another and also compared with conventional face recognition from RGB images on different datasets. The results showed that it is possible to use DVS data to perform face recognition with quality similar to that of RGB data.

scholarly journals Critical Features for Face Recognition

2018 ◽  
Author(s):  
Naphtali Abudarham ◽  
Lior Shkiller ◽  
Galit Yovel
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Deep Neural Network ◽  
Recognition Algorithm ◽  
Facial Features ◽  
Perceptual Representation ◽  
Familiar Face ◽  
Perceptual Representations ◽  
Unfamiliar Faces ◽  
New Framework

Face recognition is a computationally challenging task that humans perform effortlessly. Nonetheless, this remarkable ability is limited to familiar faces and does not generalize to unfamiliar faces. To account for humans’ superior ability to recognize familiar faces, current theories suggest that familiar and unfamiliar faces have different perceptual representations. In the current study, we applied a reverse engineering approach to reveal which facial features are critical for familiar face recognition. In contrast to current views, we discovered that the same subset of features that are used for matching unfamiliar faces, are also used for matching as well as recognition of familiar faces. We further show that these features are also used by a deep neural network face recognition algorithm. We therefore propose a new framework that assumes similar perceptual representation for all faces and integrates cognition and perception to account for humans’ superior recognition of familiar faces.

Prediction of Airport Energy Consumption Using a Hybrid Grey Neural Network Model

2012 ◽  
Vol 608-609 ◽  
pp. 1252-1256 ◽  
Author(s):  
Jing Jie Chen ◽  
Chen Xiao ◽  
Wen Gao Qian
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Civil Aviation ◽  
Aviation Industry ◽  
Consumption Data ◽  
Prediction And Control ◽  
And Control

Prediction and control of airport energy consumption plays an important role in promoting energy saving and emission reduction in the civil aviation industry. In view of the complexity and nonlinearity of energy consumption system, as well as a small number of airport energy consumption data, this study develops a hybrid grey neural network model, which organically combines GM (1, 1) model and BP neural network in parallel and series connections, on the basis of analysis of main prediction methods. With energy consumption data from one Chinese airport for the whole year 2010, this study analyzes and compares different prediction results using different models through matlab. It shows that the hybrid model has a better accurate prediction, and its prediction accuracy can be controlled within 7%.

scholarly journals A Deep Convolution Neural Network Model for Vehicle Recognition and Face Recognition

2017 ◽  
Vol 107 ◽  
pp. 715-720 ◽  
Author(s):  
Xingcheng Luo ◽  
Ruihan Shen ◽  
Jian Hu ◽  
Jianhua Deng ◽  
Linji Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Network Model ◽  
Neural Network Model ◽  
Convolution Neural Network ◽  
Vehicle Recognition ◽  
Deep Convolution Neural Network

Hydrodynamic and Control Analysis of a Self-Controllable Underwater Towed Vehicle

2006 ◽  
Author(s):  
Jiaming Wu ◽  
Xiaohui Xiong
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Control System ◽  
Network Model ◽  
Neural Network Model ◽  
Trajectory Control ◽  
Control Analysis ◽  
Time Step ◽  
Neural Network Controller ◽  
And Control

The hydrodynamic and control performances of a self-stable controllable underwater towed vehicle developed by South China University of Technology under different depth trajectory control operations are analyzed by means of a proposed hydrodynamic numerical model. The model is established based on LMBP algorithm of neural network theory. Training samples for the neural network model are provided from the experimental data of the vehicle prototype towing experiments conducted in a large-scale ship model towing tank under the manipulation of a depressing wing installed in the vehicle. After the LMBP model is established, a depth trajectory control system for the towed vehicle is designed in order to accomplish vehicle trajectory control. This system is mainly composed of tow parts: a neural network identifier based on genetic algorithm and a fuzzy neural network controller based on genetic algorithm simulated annealing. Hydrodynamic performances of the vehicle under various control operations can then be numerically simulated with the proposed LMBP model and the depth trajectory control system of the towed vehicle. In numerical simulation of trajectory control to the towed vehicle, deflection of the vehicle’s depressing wing is adjusted at every time step by the proposed control system to match the trajectory of the vehicle with a pre-designated one. The value of the deflection is taken as input parameter for the LMBP neural network model, trajectory and attitude behavior of the towed vehicle under the control manipulations can then be predicted by the LMBP model.

Sign in / Sign up

Export Citation Format

Share Document