scholarly journals Research on Recognition of Faces with Masks Based on Improved Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Song Zhang ◽  
Jiandong Sun ◽  
Jie Kang ◽  
Shaoqiang Wang
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Target Detection ◽  
Recognition Algorithm ◽  
Feasible Method ◽  
The World

Background. At present, the new crown virus is spreading around the world, causing all people in the world to wear masks to prevent the spread of the virus. Problem. People with masks have found a lot of trouble for face recognition. Finding a feasible method to recognize faces wearing masks is a problem that needs to be solved urgently. Method. This paper proposes a mask recognition algorithm based on improved YOLO-V4 neural network and the integrated SE-Net and DenseNet network and introduces deformable convolution. Conclusion. Compared with other target detection networks, the improved YOLO-V4 neural network used in this paper improves the accuracy of face recognition and detection with masks to a certain extent.

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.

scholarly journals Research on Face Recognition Algorithm Based on Improved Residual Neural Network

2021 ◽  
Vol 9 (1) ◽  
pp. 46
Author(s):  
Tang Xiaolin ◽  
Wang Xiaogang ◽  
Hou Jin ◽  
Han Yiting ◽  
Huang Ye
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Recognition Algorithm

MCE-BASED FACE RECOGNITION

2001 ◽  
Vol 15 (08) ◽  
pp. 1311-1327 ◽  
Author(s):  
LIANG-HUA CHEN ◽  
SHAO-HUA DENG ◽  
HONG-YUAN LIAO
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Face Detection ◽  
Detection Algorithm ◽  
Recognition Algorithm ◽  
Classification Error ◽  
Complex Scenes ◽  
Minimum Classification Error ◽  
Complete Procedure ◽  
Human Faces

This paper proposes a complete procedure for the extraction and recognition of human faces in complex scenes. The morphology-based face detection algorithm can locate multiple faces oriented in any direction. The recognition algorithm is based on the minimum classification error (MCE) criterion. In our work, the minimum classification error formulation is incorporated into a multilayer perceptron neural network. Experimental results show that our system is robust to noisy images and complex background.

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.

scholarly journals Robust face recognition based on multi-task convolutional neural network

2021 ◽  
Vol 18 (5) ◽  
pp. 6638-6651
Author(s):  
Huilin Ge ◽  
◽  
Yuewei Dai ◽  
Zhiyu Zhu ◽  
Biao Wang
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Face Detection ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Recognition Algorithm ◽  
Face Images ◽  
Robust Face Recognition

<abstract> <sec><title>Purpose</title><p>Due to the lack of prior knowledge of face images, large illumination changes, and complex backgrounds, the accuracy of face recognition is low. To address this issue, we propose a face detection and recognition algorithm based on multi-task convolutional neural network (MTCNN).</p> </sec> <sec><title>Methods</title><p>In our paper, MTCNN mainly uses three cascaded networks, and adopts the idea of candidate box plus classifier to perform fast and efficient face recognition. The model is trained on a database of 50 faces we have collected, and Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measurement (SSIM), and receiver operating characteristic (ROC) curve are used to analyse MTCNN, Region-CNN (R-CNN) and Faster R-CNN.</p> </sec> <sec><title>Results</title><p>The average PSNR of this technique is 1.24 dB higher than that of R-CNN and 0.94 dB higher than that of Faster R-CNN. The average SSIM value of MTCNN is 10.3% higher than R-CNN and 8.7% higher than Faster R-CNN. The Area Under Curve (AUC) of MTCNN is 97.56%, the AUC of R-CNN is 91.24%, and the AUC of Faster R-CNN is 92.01%. MTCNN has the best comprehensive performance in face recognition. For the face images with defective features, MTCNN still has the best effect.</p> </sec> <sec><title>Conclusions</title><p>This algorithm can effectively improve face recognition to a certain extent. The accuracy rate and the reduction of the false detection rate of face detection can not only be better used in key places, ensure the safety of property and security of the people, improve safety, but also better reduce the waste of human resources and improve efficiency.</p> </sec> </abstract>

Sign in / Sign up

Export Citation Format

Share Document