Labeled Faces In The Wild Research Articles

ApaNet: adversarial perturbations alleviation network for face verification.

Albeit Deep neural networks (DNNs) are widely used in computer vision, natural language processing and speech recognition, they have been discovered to be fragile to adversarial attacks. Specifically, in computer vision, an attacker can easily deceive DNNs by contaminating an input image with perturbations imperceptible to humans. As one of the important vision tasks, face verification is also subject to adversarial attack. Thus, in this paper, we focus on defending against the adversarial attack for face verification to mitigate the potential risk. We learn a network via an implementation of stacked residual blocks, namely adversarial perturbations alleviation network (ApaNet), to alleviate latent adversarial perturbations hidden in the input facial image. During the supervised learning of ApaNet, only the Labeled Faces in the Wild (LFW) is used as the training set, and the legitimate examples and corresponding adversarial examples produced by projected gradient descent algorithm compose supervision and inputs respectively. By leveraging the middle and high layer’s activation of FaceNet, the discrepancy between an image output by ApaNet and the supervision is calculated as the loss function to optimize ApaNet. Empirical experiment results on the LFW, YouTube Faces DB and CASIA-FaceV5 confirm the effectiveness of the proposed defender against some representative white-box and black-box adversarial attacks. Also, experimental results show the superiority performance of the ApaNet as comparing with several currently available techniques.

Learning Representations for Face Recognition: A Review from Holistic to Deep Learning

For decades, researchers have investigated how to recognize facial images. This study reviews the development of different face recognition (FR) methods, namely, holistic learning, handcrafted local feature learning, shallow learning, and deep learning (DL). With the development of methods, the accuracy of recognizing faces in the labeled faces in the wild (LFW) database has been increased. The accuracy of holistic learning is 60%, that of handcrafted local feature learning increases to 70%, and that of shallow learning is 86%. Finally, DL achieves human-level performance (97% accuracy). This enhanced accuracy is caused by large datasets and graphics processing units (GPUs) with massively parallel processing capabilities. Furthermore, FR challenges and current research studies are discussed to understand future research directions. The results of this study show that presently the database of labeled faces in the wild has reached 99.85% accuracy.

One-Shot Face Recognition through a Region Inception ResNet with Modified Triplet Loss

Face recognition has become a convenient method for identity verification, especially the one-shot task has much practical value. Some former works have achieved considerable results. However, they perform ill under the situation of COVID-19 with more and more people wearing a mask. This requires the extracted face features distinguishable and robust enough for classifying different masked people. It is difficult for the one-shot task with only one sample for training. To solve this problem, we designed a network called Region Inception ResNet with Modified Triplet Loss, which generates robust features. It keeps high accuracy even under masked condition. The networks are trained on the datasets of CASIA-Webface and Ms-Celeb-1M, tested on LFW (Labelled Faces in the Wild). Experiments in Section 6 show the effectiveness of our method.

Adaptive random down-sampling data augmentation and area attention pooling for low resolution face recognition

State-of-the-art face recognition method have achieved satisfactory performance on various face datasets, but limited to high-resolution (HR) faces. In real scenes, with affects from camera quality or distance etc., low quality face images are often obtained in surveillance scenes, which leads to poor performance of general face recognition approaches. In this work, we explored the reasons why low-resolution (LR) images cannot be coped with the conventional models, and proposed the optimization methods. The main contribution of this work includes two aspects: (1) We proposed an adaptive random down-sampling data augmentation method with the corresponding loss function and training strategy. For the network training, we mapped the face images with different resolutions to the same embedding space, and then explicitly separated different classes of LR and gathered the same class of HR and LR. (2) A pooling module based on attention mechanism, area attention pooling, was proposed. After pooling, the fine-grained information of the identity is retained, and the redundant information of the non-identity is removed. We conducted a series of visualization experiments to prove the effectiveness of our method. We evaluated our methods on the real-world LR face dataset Surveillance Cameras Face Database (SCface) and the public face evaluation dataset Labeled Faces in the Wild (LFW). Compared with state-of-the-art methods, the proposed method achieves satisfactory performance at LR images on SCface and LFW dataset.

Low-resolution face recognition based on feature-mapping face hallucination

The image recognition approaches based on Convolutional Neural Network (CNN) have already achieved tremendous performance on super-resolution face images. However, there exist several challenges in face recognition field. For example, in very low-resolution face recognition (LRFR) environments, the accuracy will drop drastically. To address the issue, this paper proposes a novel face hallucination and recognition model for low resolution face images ground on feature-mapping. In the proposed model, a new loss function named identity-aware loss is also proposed. The proposed loss function is combined with the feature loss and image-content loss to jointly train models. The proposed model is evaluated on Labeled Faces in the Wild (LFW) dataset, which compared to progressive competing models. A large number of experimental results indicate that this model observably enhances the performance of recognition particularly when face images are very low-resolution. In addition, our model can perform high resolution face image reconstruction which is comparable to advanced approaches based on super-resolution in the field of visual quality, and achieve identity preservation of corresponding low resolution probe image.

Mask Wearing Detection Based on Inceptionv4 and Multi-Scale Retinex Image Enhancement Algorithm

The novel coronavirus is a contagious virus with a high mortality rate, and the international health emergency due to COVID-19 has never stopped since the outbreak, due to this situation, wearing masks has become a basic recommended public epidemic prevention approach for many countries. In the current shortage of medical human resources, we urgently need a non-artificial mask-wearing detection method. In this paper, the multi-scale Retinex algorithm is involved as the preprocessing step of the input image. The mask-wearing detection is based on the InceptionV4 convolutional neural network model. During the experiment, we compared and verified the superiority of the Inception part of the InceptionV4 model compared with the Stem structure of the GoogLenet model, and from LFW (Labeled Faces in the Wild), RMFD (Real-World-Masked-Face-Dataset) more than 10,000 samples were selected from the public datasets for model training. Finally, the precise rate reaches 97.3 %.

Face Recognition and Gender Detection Using SIFT Feature Extraction, LBPH, and SVM

Face recognition and name and gender identification are challenging processes, especially when identifying perpetrators and suspects or when used in authentication systems. Machine learning and computer vision technologies are used in many fields, including security, and play an important role in face recognition and gender detection, offering valuable information to officials to rectify a situation in less time. This study used a few machine learning methods in the Labelled Faces in the Wild (LFW) database to examine their facial recognition and gender detection capacities. The LFW dataset was used to train and evaluate the Scale Invariant Feature Transform (SIFT) feature extraction method along with the Support Vector Machine (SVM) classifier and the Local Binary Pattern Histogram (LBPH) method. The result comparison from the current and other studies showed that the proposed LBPH method had higher accuracy in face recognition, while its accuracy in gender detection was very close to the ones of other, relevant studies.

Face Verification Based on Deep Learning for Person Tracking in Hazardous Goods Factories

Person tracking in hazardous goods factories can provide a significant improvement in security and safety. This article proposes a face verification model which can be used to record travel paths for staff or related persons in the factory. As face images are captured from the dynamic crowd at entrance–exit gates of workshops, face verification is challenged by polymorphic faces, poor illumination and changing of a person’s pose. To adapt to this situation, a new face verification model is proposed, which is composed of two advanced deep learning neural network models. Firstly, MTCNN (Multi-Task Cascaded Convolutional Neural Network) is used to construct a face detector. Based on the SphereFace-20 network model, we have reconstructed a convolutional network architecture with the embedded Batch Normalization elements and the optimized network parameters. The new model, which is called the MDCNN, is used to extract efficient face features. A set of specific processing algorithms is used in the model to process polymorphic face images. The multi-view faces and various types of face images are used to train the models. The experimental results have demonstrated that the proposed model outperforms most existing methods on benchmark datasets such as the Labeled Faces in the Wild (LFW) and YouTube Face (YTF) datasets without multi-view (accuracy is 99.38% and 94.30%, respectively) and the CNBC/FERET datasets with multi-view (accuracy is 94.69%).

Criminal Persons Recognition Using Improved Feature Extraction Based Local Phase Quantization

Facial recognition is a trending technology that can identify or verify an individual from a video frame or digital image from any source. A major concern of facial recognition is achieving the accuracy on classification, precision, recall and F1-Score. Traditionally, numerous techniques involved in the working principle of facial recognition, as like Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), Subspace Decomposition Method, Eigen Feature extraction Method and all are characterized as instable, poor generalization which leads to poor classification. But the simplified method is feature extraction by comparing the particular facial features of the images from the collected dataset namely Labeled faces in the wild (LFW) and Olivetti Research Laboratory (ORL) dataset. In this paper, the feature extraction is based on local phase quantization with directional graph features for an effective optimal path and the geometric features. Further, Person Identification based deep neural network (PI-DNN) has proposed are expected to provide a high recognition rate. Various performance metrics, such as recognition rate, classification accuracy, accuracy, precision, recall, F1-score is evaluated. The proposed method achieves high-performance values when it is compared with other existing methods. The novelty of this paper explains in understanding the various features of different types of classifiers used. It is mainly developed to recognize the human faces in the crowd, and it is also deployed for criminal identification.

Optimizing Few-Shot Learning Based on Variational Autoencoders.

Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations on the Labeled Faces in the Wild (LFW) dataset. The purpose of our research is to increase the size of the training dataset using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training dataset, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. The face generation method based on VAEs with perceptual loss can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets.

Analysis of Feature Extraction and Anti-Interference of Face Image under Deep Reconstruction 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.

Multi-Block Color-Binarized Statistical Images for Single-Sample Face Recognition.

Single-Sample Face Recognition (SSFR) is a computer vision challenge. In this scenario, there is only one example from each individual on which to train the system, making it difficult to identify persons in unconstrained environments, mainly when dealing with changes in facial expression, posture, lighting, and occlusion. This paper discusses the relevance of an original method for SSFR, called Multi-Block Color-Binarized Statistical Image Features (MB-C-BSIF), which exploits several kinds of features, namely, local, regional, global, and textured-color characteristics. First, the MB-C-BSIF method decomposes a facial image into three channels (e.g., red, green, and blue), then it divides each channel into equal non-overlapping blocks to select the local facial characteristics that are consequently employed in the classification phase. Finally, the identity is determined by calculating the similarities among the characteristic vectors adopting a distance measurement of the K-nearest neighbors (K-NN) classifier. Extensive experiments on several subsets of the unconstrained Alex and Robert (AR) and Labeled Faces in the Wild (LFW) databases show that the MB-C-BSIF achieves superior and competitive results in unconstrained situations when compared to current state-of-the-art methods, especially when dealing with changes in facial expression, lighting, and occlusion. The average classification accuracies are 96.17% and 99% for the AR database with two specific protocols (i.e., Protocols I and II, respectively), and 38.01% for the challenging LFW database. These performances are clearly superior to those obtained by state-of-the-art methods. Furthermore, the proposed method uses algorithms based only on simple and elementary image processing operations that do not imply higher computational costs as in holistic, sparse or deep learning methods, making it ideal for real-time identification.

Improving face recognition performance using TeCS2dictionary

• Combining visual cues with face recognition algorithm to improve performance. • Visual queues such as color, shape, texture and symmetry help in understanding faces. • Extensive experiments show the effectiveness of the proposed framework. • Proposed approach outperforms our previous work and other state of art approaches. Human mind processes the different primitive components of image signals such as color, shape, texture, and symmetry in a parallel and complex fashion. Deep neural networks aim to learn all these components from the image in an unsupervised manner. However, learning the primitive features is not formally assured in a deep learning formulation, and, adding these features explicitly would improve the performance. Especially in face recognition, humans intuitively and implicitly employ the usage of primitive features such as color, shape, texture, and symmetry of faces. Inspired by this observation, this paper presents a novel approach in building a learning based TeCS 2 space. This space consists of meta-level features obtained from dictionary learning and combining it with task specific deep learning classifiers (such as DenseNet) for face recognition. Confidence based fusion mechanism is presented to supplement the task specific deep learning classifier with the proposed TeCS 2 features. The effectiveness of the proposed framework is evaluated on four benchmark face recognition datasets: (i) Disguised Faces in the Wild (DFW), (ii) Labeled faces in the wild (LFW), (iii) IIITD Plastic Surgery dataset, and (iv) Point and Shoot Challenge (PaSC).

Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons

Face detection by electronic systems has been leveraged by private and government establishments to enhance the effectiveness of a wide range of applications in our day to day activities, security, and businesses. Most face detection algorithms that can reduce the problems posed by constrained and unconstrained environmental conditions such as unbalanced illumination, weather condition, distance from the camera, and background variations, are highly computationally intensive. Therefore, they are primarily unemployable in real-time applications. This paper developed face detectors by utilizing selected Haar-like and local binary pattern features, based on their number of uses at each stage of training using MATLAB’s trainCascadeObjectDetector function. We used 2577 positive face samples and 37,206 negative samples to train Haar-like and LBP face detectors for a range of False Alarm Rate (FAR) values (i.e., 0.01, 0.05, and 0.1). However, the study shows that the Haar cascade face detector at a low stage (i.e., at six stages) for 0.1 FAR value is the most efficient when tested on a set of classroom images dataset with 100% True Positive Rate (TPR) face detection accuracy. Though, deep learning ResNet101 and ResNet50 outperformed the average performance of Haar cascade by 9.09% and 0.76% based on TPR, respectively. The simplicity and relatively low computational time used by our approach (i.e., 1.09 s) gives it an edge over deep learning (139.5 s), in online classroom applications. The TPR of the proposed algorithm is 92.71% when tested on images in the synthetic Labeled Faces in the Wild (LFW) dataset and 98.55% for images in MUCT face dataset “a”, resulting in a little improvement in average TPR over the conventional face identification system.

Application of Face Recognition Method Under Deep Learning Algorithm in Embedded Systems

The Convolutional Neural Network (CNN) based on deep learning is introduced to propose two deep face detection algorithms and design an embedded face recognition system, in an effort to apply the deep learning algorithm to face detection and explore the embedded face recognition system. First, an optimized Multi-task Cascaded Convolutional Network (MTCNN) algorithm is proposed for the simulation transformation and crop preprocessing of the face image, denoted as OMTCNN. Second, a lightweight face recognition algorithm based on CNN is proposed to reduce the computational complexity of face recognition in the embedded system, denoted as LCNN. Finally, OMTCNN and LCNN are combined to construct the multi-core embedded face recognition system. Results demonstrate that OMTCNN shows good performance in determining face identity, and its training accuracy can reach 95.78%, significantly better than the unimproved MTCNN algorithm. On the Labeled Faces in the Wild (LFW) dataset, LCNN provides a correct rate of 98.13%, and the reduction in the complexity of the model itself increases the computational speed by as much as 6.4 times. The test results suggest that the designed face recognition system has good applicability on the embedded platform. The increase in the accuracy of the face recognition module and the introduction of the calculation acceleration module have significantly improved the face detection and recognition performance of the embedded system. The embedded face recognition system based on deep learning has practical application value.

Gabor and Maximum Response Filters with Random Forest Classifier for Face Recognition in the Wild

Research on face recognition has been evolving for decades. There are numerous approaches developed with highly desirable outcomes in constrained environments. In contrast, approaches to face recognition in an unconstrained environment where varied facial posing, occlusion, aging, and image quality still pose vast challenges. Thus, face recognition in the unconstrained environment still an unresolved problem. Many current techniques are not performed well when experimented in unconstrained databases. Additionally, most of the real-world application needs a good face recognition performance in the unconstrained environment. This paper presents a comprehensive process aimed to enhance the performance of face recognition in an unconstrained environment. This paper presents a face recognition system in an unconstrained environment. The fusion between Gabor filters and Maximum Response (MR) filters with Random Forest classifier is implemented in the proposed system. Gabor filters are a hybrid of Gabor magnitude filters and Oriented Gabor Phase Congruency (OGPC) filters. Gabor magnitude filters produce the magnitude response while the OGPC filters produce the phase response of Gabor filters. The MR filters contain the edge- and bar-anisotropic filter responses and isotropic filter responses. In the face features selection process, Monte Carlo Uninformative Variable Elimination Partial Least Squares Regression (MC-UVE-PLSR) is used to select the optimal face features in order to minimize the computational costs without compromising the accuracy of face recognition. Random Forests is used in the classification of the generated feature vectors. The algorithm performance is evaluated using two unconstrained facial image databases: Labelled Faces in the Wild (LFW) and Unconstrained Facial Images (UFI). The proposed technique used produces encouraging results in these evaluated databases in which it recorded face recognition rates that are comparable with other state-of-the-art algorithms.

Deep Face Rectification for 360° Dual-Fisheye Cameras.

Rectilinear face recognition models suffer from severe performance degradation when applied to fisheye images captured by 360° back-to-back dual fisheye cameras. We propose a novel face rectification method to combat the effect of fisheye image distortion on face recognition. The method consists of a classification network and a restoration network specifically designed to handle the non-linear property of fisheye projection. The classification network classifies an input fisheye image according to its distortion level. The restoration network takes a distorted image as input and restores the rectilinear geometric structure of the face. The performance of the proposed method is tested on an end-to-end face recognition system constructed by integrating the proposed rectification method with a conventional rectilinear face recognition system. The face verification accuracy of the integrated system is 99.18% when tested on images in the synthetic Labeled Faces in the Wild (LFW) dataset and 95.70% for images in a real image dataset, resulting in an average accuracy improvement of 6.57% over the conventional face recognition system. For face identification, the average improvement over the conventional face recognition system is 4.51%.

Unconstrained Face Identification Based on 3D Face Frontalization and Support Vector Guided Dictionary Learning

Face identification aims at putting a label on an unknown face with respect to some training set. Unconstrained face identification is a challenging problem because of the possible variations in face pose, illumination, occlusion, and facial expression. This paper presents an unconstrained face identification method based on face frontalization and learning-based data representation. Firstly, the frontal views of unconstrained face images are automatically generated by using a single, unchanged 3D face model. Then, we crop the face relevant regions of the frontal views to segment faces from the backgrounds. At last, to enhance the discriminative capability of the coding vectors, a support vector-guided dictionary learning (SVGDL) model is applied to adaptively assign different weights to different pairs of coding vectors. The performance of the proposed method FSVGDL (frontalization-based support vector guided dictionary learning) is evaluated on the Labeled Faces in the wild (LFW) database. After decision fusion, the identification accuracy yields 97.17% when using 7 images per individual for training and 3 images per individual for testing with 158 classes in total.

Recognizing Very Small Face Images Using Convolution Neural Networks

Face recognition can be installed in a surveillance system so that it can be used for monitoring, tracking and access control. An excellent, intelligent surveillance system should be sensitive to the objects far away from the camera. Unfortunately, due to the long-distance, objects like human faces captured by the camera are too small to identify. As to enhance the subtle color differences in the face image, in this paper we first improve the resolution of the captured image using deep convolution neural networks (DCNNs). Then the efficient features are extracted and used to do classification. As for verifying the effectiveness of the proposed method, we used three databases including AR face database, Georgia Tech face database (GT) database, and Labelled Faces in the Wild (LFW) database, altogether, to conduct the training and testing. Compared to the existing approaches, experimental results show that the identification accuracy of the proposed method outperforms any existing approaches.

Lightweight and Resource-Constrained Learning Network for Face Recognition with Performance Optimization.

Despite considerable progress in face recognition technology in recent years, deep learning (DL) and convolutional neural networks (CNN) have revealed commendable recognition effects with the advent of artificial intelligence and big data. FaceNet was presented in 2015 and is able to significantly improve the accuracy of face recognition, while also being powerfully built to counteract several common issues, such as occlusion, blur, illumination change, and different angles of head pose. However, not all hardware can sustain the heavy computing load in the execution of the FaceNet model. In applications in the security industry, lightweight and efficient face recognition are two key points for facilitating the deployment of DL and CNN models directly in field devices, due to their limited edge computing capability and low equipment cost. To this end, this paper provides a lightweight learning network improved from FaceNet, which is called FN13, to break through the hardware limitation of constrained computational resources. The proposed FN13 takes the advantage of center loss to reduce the variations of the between-class features and enlarge the difference of the within-class features, instead of the triplet loss by using FaceNet. The resulting model reduces the number of parameters and maintains a high degree of accuracy, only requiring few grayscale reference images per subject. The validity of FN13 is demonstrated by conducting experiments on the Labeled Faces in the Wild (LFW) dataset, as well as an analytical discussion regarding specific disguise problems.