scholarly journals Analysis of Feature Extraction and Anti-Interference of Face Image under Deep Reconstruction Network Algorithm

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Jin Yang ◽  
Yuxuan Zhao ◽  
Shihao Yang ◽  
Xinxin Kang ◽  
Xinyan Cao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Bayesian Method ◽  
Feature Matching ◽  
Facial Feature ◽  
Face Image ◽  
Feature Representation ◽  
Image Feature ◽  
Training Time ◽  
Network Algorithm

In face recognition systems, highly robust facial feature representation and good classification algorithm performance can affect the effect of face recognition under unrestricted conditions. To explore the anti-interference performance of convolutional neural network (CNN) reconstructed by deep learning (DL) framework in face image feature extraction (FE) and recognition, in the paper, first, the inception structure in the GoogleNet network and the residual error in the ResNet network structure are combined to construct a new deep reconstruction network algorithm, with the random gradient descent (SGD) and triplet loss functions as the model optimizer and classifier, respectively, and it is applied to the face recognition in Labeled Faces in the Wild (LFW) face database. Then, the portrait pyramid segmentation and local feature point segmentation are applied to extract the features of face images, and the matching of face feature points is achieved using Euclidean distance and joint Bayesian method. Finally, Matlab software is used to simulate the algorithm proposed in this paper and compare it with other algorithms. The results show that the proposed algorithm has the best face recognition effect when the learning rate is 0.0004, the attenuation coefficient is 0.0001, the training method is SGD, and dropout is 0.1 (accuracy: 99.03%, loss: 0.0047, training time: 352 s, and overfitting rate: 1.006), and the algorithm proposed in this paper has the largest mean average precision compared to other CNN algorithms. The correct rate of face feature matching of the algorithm proposed in this paper is 84.72%, which is higher than LetNet-5, VGG-16, and VGG-19 algorithms, the correct rates of which are 6.94%, 2.5%, and 1.11%, respectively, but lower than GoogleNet, AlexNet, and ResNet algorithms. At the same time, the algorithm proposed in this paper has a faster matching time (206.44 s) and a higher correct matching rate (88.75%) than the joint Bayesian method, indicating that the deep reconstruction network algorithm proposed in this paper can be used in face image recognition, FE, and matching, and it has strong anti-interference.

scholarly journals Face Detection and Recognition using Open CV Based on Fisher Faces Algorithm

2020 ◽  
Vol 8 (5) ◽  
pp. 1204-1208
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Face Detection ◽  
Face Image ◽  
Image Feature ◽  
Learning Stage ◽  
Identity Recognition ◽  
Video Frames ◽  
Testing Stage ◽  
The Face

Facial Recognition represents the event of a system which may determine the person with the assistance of a face using Computer Vision (Open CV). Face recognition is employed within the fields of Identity Recognition, police investigation and enforcement. It's a method of characteristic someone supported facial expression. This method is enforced in 2 stages. They're the training stage and therefore the testing stage. This study primarily consists of 3 elements, specifically face detection from the image, feature extraction and storing many reminder images, and recognition. Face finding rule is employed to detect the face from the given image. The foremost helpful and distinctive options of the face image are extracted within the feature extraction part. Face Detection may be challenging because of pictures and video frames will contain advanced background, completely different head poses and occlusion like carrying glasses or scarf. It presents a rule for finding face recognition downside and concatenated into one feature vector that is employed to coach the system to recognise among the prevailing photos with it. Within the testing stage the system takes the face of the image of someone for recognition. Image acquisition, preprocessing, image filtering, feature extraction is just like the learning stage. For classification the options are fed to the trained system. The algorithms can determine the face image from the content and acknowledges it.

scholarly journals Does My Face FIT?: A Face Image Task Reveals Structure and Distortions of Facial Feature Representation

PLoS ONE ◽  
2013 ◽  
Vol 8 (10) ◽  
pp. e76805 ◽  
Author(s):  
Christina T. Fuentes ◽  
Catarina Runa ◽  
Xenxo Alvarez Blanco ◽  
Verónica Orvalho ◽  
Patrick Haggard
Keyword(s):  
Facial Feature ◽  
Face Image ◽  
Feature Representation

Matrix Based Feature Measurement and Extraction for Face Recognition

2015 ◽  
Vol 738-739 ◽  
pp. 643-647
Author(s):  
Qi Zhu ◽  
Jin Rong Cui ◽  
Zi Zhu Fan
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Face Recognition ◽  
Measurement Method ◽  
Principal Component ◽  
Component Analysis ◽  
High Accuracy ◽  
Face Image ◽  
Two Dimensional ◽  
The Matrix

In this paper, a matrix based feature extraction and measurement method, i.e.: multi-column principle component analysis (MCPCA) is used to directly and effectively extract features from the matrix. We analyze the advantages of MCPCA over the conventional principal component analysis (PCA) and two-dimensional PCA (2DPCA), and we have successfully applied it into face image recognition. Extensive face recognition experiments illustrate that the proposed method obtains high accuracy, and it is more robust than previous conventional face recognition methods.

UNCORRELATED PROJECTION DISCRIMINANT ANALYSIS AND ITS APPLICATION TO FACE IMAGE FEATURE EXTRACTION

2003 ◽  
Vol 17 (08) ◽  
pp. 1325-1347 ◽  
Author(s):  
JIAN YANG ◽  
JING-YU YANG ◽  
ALEJANDRO F. FRANGI ◽  
DAVID ZHANG
Keyword(s):  
Feature Extraction ◽  
Discriminant Analysis ◽  
Face Image ◽  
Desirable Property ◽  
Experimental Results ◽  
Image Feature ◽  
Analysis Method ◽  
Two Stage ◽  
Image Feature Extraction ◽  
Projection Analysis

In this paper, a novel image projection analysis method (UIPDA) is first developed for image feature extraction. In contrast to Liu's projection discriminant method, UIPDA has the desirable property that the projected feature vectors are mutually uncorrelated. Also, a new LDA technique called EULDA is presented for further feature extraction. The proposed methods are tested on the ORL and the NUST603 face databases. The experimental results demonstrate that: (i) UIPDA is superior to Liu's projection discriminant method and more efficient than Eigenfaces and Fisherfaces; (ii) EULDA outperforms the existing PCA plus LDA strategy; (iii) UIPDA plus EULDA is a very effective two-stage strategy for image feature extraction.

Sign in / Sign up

Export Citation Format

Share Document