A 3D Dynamic Face Recognition Method Based on Computer Vision

2014 ◽  
Vol 556-562 ◽  
pp. 5006-5008 ◽  
Author(s):  
Bo Xia Zeng ◽  
Wen Feng Li
Keyword(s):  
Computer Vision ◽  
Face Recognition ◽  
Traditional Method ◽  
Recognition Algorithm ◽  
Facial Features ◽  
Nonlinear Mapping ◽  
Geometric Features ◽  
Feature Points ◽  
Recognition Method ◽  
2D Images

The non-rigid 3D characters recovery technology for 2D images array is affected by background diversity, motion complexity, data losing and noise of feature points, so the recognition and recovery accuracy of facial features deformation is low. Due to the high error in traditional method, the paper puts forward a 3D facial recognition algorithm based on random images array, which converts the 2D features to 3D by nonlinear mapping, and completes the recognition on foundation of 3D geometric features distance. The experimental results show that the method effectively reduces error and improves recognition effects.

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.

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.

Research on Facial Features of Major Chinese Nationalities

2014 ◽  
Vol 687-691 ◽  
pp. 837-840
Author(s):  
Zhi Jie Li ◽  
Xiao Dong Duan ◽  
Cun Rui Wang
Keyword(s):  
Face Recognition ◽  
Measurement Method ◽  
Scientific Basis ◽  
Facial Features ◽  
Geometric Features ◽  
Face Images ◽  
Similarities And Differences

This paper analyze the facial features of 6 main chinese nationalities using measurement method on face images. We select several measurement and calculation indices according to the facial geometric features of each group. It is found that Mongolia, Korean and Han nationalitis are similar in facial features, while Tibetans and Uighurs nationalities have larger differences. Analysis of the similarities and differences among groups can provide a scientific basis for face recognition of multiple nationalities.

scholarly journals Algorithm of Face Recognition by Principal Component Analysis

1970 ◽  
Vol 3 (2) ◽  
Author(s):  
Khalid A. S. Al-Khateeb and Jaiz A. Y. Johari
Keyword(s):  
Computer Vision ◽  
Principal Component Analysis ◽  
Face Recognition ◽  
Data Base ◽  
Principal Component ◽  
Component Analysis ◽  
Recognition Algorithm ◽  
Computer Vision Applications ◽  
Simplified Algorithm ◽  
Facial Images

A face recognition algorithm based on Principal Component Analysis (PCA) has been developed and tested for computer vision applications. A database of about 400 facial images was used to test the algorithm. Each image is represented by a matrix (112 x 92), The data base is divided into subsets, where each subset represents one of 10 different individuals. A 96% rate of successful detection and a 90% rate of successful recognition were obtained. Several factors had to be standardized to provide a constrained environment in order to reduce error. The analysis is based on a set of eigenvectors that defines an Eigen Face (EF). The method proved to be simple and effective. The simplified algorithm and techniques expedited the process without seriously compromising the accuracy.

Face Detection With Face Mask for COVID-19 Pandemic Using Neural Networks

2022 ◽  
pp. 210-223
Author(s):  
Nitish Devendra Warbhe ◽  
Rutuja Rajendra Patil ◽  
Tarun Rajesh Shrivastava ◽  
Nutan V. Bansode
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Face Detection ◽  
Face Mask ◽  
Detection Technique ◽  
Facial Features ◽  
Feature Points ◽  
The People ◽  
Biometric Systems ◽  
The Face

The COVID-19 virus can be spread through contact and contaminated surfaces; therefore, typical biometric systems like password and fingerprint are unsafe. Face recognition solutions are safer without any need of touching any device. During the COVID-19 situation as all of the people are advised to wear masks on their faces, the existing face detection technique is not able to identify the person with face occlusion. The fraudsters and thieves take advantage of this scenario and misuse the face mask, favoring them to be able to steal and commit various crimes without being identified. Face recognition methods fail to detect or recognize the face as half of the face is masked and the features are suppressed. Face recognition requires the visibility of major facial features for face normalization, orientation correction, and recognition. Thus, the chapter focuses on the facial recognition based on the feature points surrounding the eye region rather than taking the whole face as a parameter.

scholarly journals A Novel Face Recognition Algorithm Using Gabor - based KPCA

2018 ◽  
Vol 7 (2) ◽  
pp. 124
Author(s):  
Umasankar Ch ◽  
D. Naresh Kumar ◽  
Md. Abdul Rawoof ◽  
D. Khalandar Basha ◽  
N. Madhu
Keyword(s):  
Face Recognition ◽  
Structural Characteristics ◽  
Feature Space ◽  
Facial Feature ◽  
Input Image ◽  
Recognition Algorithm ◽  
Nonlinear Mapping ◽  
Kernel Pca ◽  
Face Images ◽  
The Face

The Gabor wavelets are used to extract facial features, and then a doubly nonlinear mapping kernel PCA (DKPCA) is proposed to perform feature transformation and face recognition. The conventional kernel PCA nonlinearly maps an input image into a high-dimensional feature space in order to make the mapped features linearly separable. However, this method does not consider the structural characteristics of the face images, and it is difficult to determine which nonlinear mapping is more effective for face recognition. In this work, a new method of nonlinear mapping, which is performed in the original feature space, is defined. The proposed nonlinear mapping not only considers the statistical properties of the input features, but also adopts an Eigen mask to emphasize those important facial feature points The proposed algorithm is evaluated based on the Yale database, the AR database, the ORL database and the YaleB database.

scholarly journals Face Recognition Based on Wavelet Kernel Non-Negative Matrix Factorization

2014 ◽  
Vol 14 (3) ◽  
pp. 37-45 ◽  
Author(s):  
Lin Bai, ◽  
Yanbo Li ◽  
Meng Hui
Keyword(s):  
Face Recognition ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Recognition Algorithm ◽  
Recognition Method ◽  
Rbf Network ◽  
Multi Resolution Analysis ◽  
Resolution Analysis ◽  
Non Negative Matrix Factorization

Abstract In this paper a novel face recognition algorithm, based on wavelet kernel non-negative matrix factorization (WKNMF), is proposed. By utilizing features from multi-resolution analysis, the nonlinear mapping capability of kernel nonnegative matrix factorization could be improved by the method proposed. The proposed face recognition method combines wavelet kernel non-negative matrix factorization and RBF network. Extensive experimental results on ORL and YALE face database show that the suggested method possesses much stronger analysis capability than the comparative methods. Compared with PCA, non-negative matrix factorization, kernel PCA and independent component analysis, the proposed face recognition method with WKNMF and RBF achieves over 10 % improvement in recognition accuracy.

Based on Fractional Brownian Motion and Fourier Descriptors of the Side Face Recognition Algorithm

2014 ◽  
Vol 596 ◽  
pp. 427-432
Author(s):  
Hong Wu ◽  
Gui Xin Tang ◽  
Tao Han ◽  
Bai Hao Jie
Keyword(s):  
Brownian Motion ◽  
Face Recognition ◽  
Fractional Brownian Motion ◽  
Recognition Algorithm ◽  
Fourier Descriptors ◽  
Feature Points ◽  
The Face ◽  
Side Face ◽  
Algorithm Base ◽  
The Impact

This paper proposes a kind of the side face recognition algorithm base on Fractional Brownian motion and Fourier descriptors. This method is mainly innovating for feature extraction and making up for a shortage of the side face recognition algorithm. Firstly, by Fractional Brownian motion of Hurst index will get silhouette extracted. Then we through Fourier descriptors to obtain the desired feature points. Further study of this algorithm can solve the side of the face recognition rotation, scaling, and translation transform the impact. Comparative characteristics will make distance classifier and BP neural network classifier. This article also processes the analysis of the algorithm and the future development.

scholarly journals 3D Face Recognition Based on an Attention Mechanism and Sparse Loss Function

Electronics ◽  
2021 ◽  
Vol 10 (20) ◽  
pp. 2539
Author(s):  
Hongyan Zou ◽  
Xinyan Sun
Keyword(s):  
Face Recognition ◽  
Loss Function ◽  
Point Cloud ◽  
Recognition Algorithm ◽  
Attention Mechanism ◽  
Depth Information ◽  
Facial Features ◽  
3D Face Recognition ◽  
Face Features ◽  
The Face

Face recognition is one of the essential applications in computer vision, while current face recognition technology is mainly based on 2D images without depth information, which are easily affected by illumination and facial expressions. This paper presents a fast face recognition algorithm combining 3D point cloud face data with deep learning, focusing on key part of face for recognition with an attention mechanism, and reducing the coding space by the sparse loss function. First, an attention mechanism-based convolutional neural network was constructed to extract facial features to avoid expressions and illumination interference. Second, a Siamese network was trained with a sparse loss function to minimize the face coding space and enhance the separability of the face features. With the FRGC face dataset, the experimental results show that the proposed method could achieve the recognition accuracy of 95.33%.

Sign in / Sign up

Export Citation Format

Share Document