Network For Face Recognition Research Articles

Survey on the Loss Function of Deep Learning in Face Recognition

With the continuous development of face recognition network, the selection of loss function plays an increasingly important role in improving accuracy. The loss function of face recognition network needs to minimize the intra-class distance while expanding the inter-class distance. So far, one of our mainstream loss function optimization methods is to add penalty terms, such as orthogonal loss, to further constrain the original loss function. The other is to optimize using the loss based on angular/cosine margin. The last is Triplet loss and a new type of joint optimization based on HST Loss and ACT Loss. In this paper, based on the three methods with good practical performance and the joint optimization method, various loss functions are thoroughly reviewed.

Domain Alignment Embedding Network for Sketch Face Recognition

Sketch face recognition refers to the process of matching sketches to photos. Recently, there has been a growing interest in using deep learning to learn discriminative features for sketch face recognition. However, the success of deep learning relies on the large-scale paired images to counteract effects such as over-fitting, since the amount of the paired training data is relatively small, the discriminative power of the deeply learned features will inevitably be reduced. This paper proposes a novel deep metric learning method termed domain alignment embedding network for sketch face recognition. Specifically, a training episode strategy is designed to alleviate the small sample problem, and a domain alignment embedding loss is proposed to guide the feature embedding network to learn discriminative features. Extensive experimental results on the UoM-SGFSv2 and PRIP-VSGC datasets are verified to show the effectiveness of the proposed method.

Adversarial Reconstruction CNN for Illumination-Robust Frontal Face Image Recovery and Recognition

This article proposes an adversarial reconstruction convolution neural network (ARCNN) for non-uniform illumination frontal face image recovery and recognition. The proposed ARCNN includes a reconstruction network and a discriminative network. The authors employ GAN framework to learn the reconstruction network in an adversarial manner. This article integrates gradient loss and perceptual loss terms, which are able to preserve the detailed and spatial structure image information, into the overall reconstruction loss function to constraint the reconstruction procedure. Experiments are conducted on the typical illumination-sensitive dataset, extended YaleB dataset. The reconstructed results demonstrate that the proposed ARCNN approach can remove the illumination and shadow information and recover natural uniform illuminated face image from non-uniform illuminated ones. Face recognition results on the extended YaleB dataset demonstrate that the proposed ARCNN reconstruction procedure can also preserve the discriminative information of face image for classification task.

WITHDRAWN: Contactless attendance system using Siamese neural network based face recognition

Abstract One of the most important and fast growing biometrical technological advancement is face recognition, used for identification of the person without any human intervention. In the proposed work, one shot learning has been used on Siamese convolution neural network (SCNN) for face recognition and attendance of the employee is entered in the MySQL database. Application Programmable interface used for uploading database is APACHE Web Server. The advantage of one shot learning algorithm is that it requires single training set for similarity measure. Get well soon message is send to absent employees through Gmail using send mail transfer protocol. Twelve images have been successfully tested and the system observed state-of –art performance with all face recognized correctly.

Parallel Multi-Path Age Distinguish Network for Cross-Age Face Recognition

Cross Age Face Recognition (CAFR) is a challenging task in the field of face recognition. There still exist some limitations in mainstream CAFR methods. On one hand, some methods need synthesizing multiple groups of features and fusing the results under different ages, where the similarity score in some age groups may affect final classification results. On the other hand, many other methods takes a facial image as a linear combination of identity information and age information, which treats age factor as a value independent of identity information, but may be inconsistent with the aging pattern of many individuals. And these methods require both age labels and identity labels in training, which is limited by the scale of existing CAFR datasets. To address the above limitations, this work proposes the Parallel Multi-path Age Distinguish Network (PMADN) model. Specifically, our model consists of two cascading networks, an Age Distinguish Mapping Network (ADMN) and a Cross-Age Feature Recombination Network (CFRN). Firstly, the face features are mapped into different age groups by parallel multi-path full connected layers in ADMN, which can better extract the identity features in a small age span. Secondly, CFRN nonlinearly recombines the mapped features to extract the age robust features that are beneficial to identity classification, which can avoid the simple linear combination of identity factor and age factor in the existing methods. What's more, our algorithm is combined with transfer learning and only uses the age label and a pre-trained ordinary face recognition network for training, which can make use of a larger aging face dataset for training. Extensive CAFR experiments performed on the benchmark MORPH Album2, CACD-VS and Cross Age LFW databases demonstrate the effectiveness and superiority of our method.

Redundancy Removing Aggregation Network With Distance Calibration for Video Face Recognition

Attention-based techniques have been successfully used for rating image quality, and have been widely employed for set-based face recognition. Nevertheless, for video face recognition, where the base convolutional neural network (CNN) trained on large-scale data already provides discriminative features, fusing features with only predicted quality scores to generate representation are likely to cause duplicate sample dominant problem, and degrade performance correspondingly. To resolve the problem mentioned above, we propose a redundancy removing aggregation network (RRAN) for video face recognition. Compared with other quality-aware aggregation schemes, RRAN can take advantage of similarity information to tackle the noise introduced by redundant video frames. By leveraging metric learning, RRAN introduces a distance calibration scheme to align distance distributions of negative pairs of different video representations, which improves the accuracy under a uniform threshold. A series of experiments is conducted on multiple realistic data sets to evaluate the performance of RRAN, including YouTube Faces, IJB-A, and IJB-C. In comprehensive experiments, we demonstrate that our method can diminish the overall influence of poor quality components with large proportion in the video and further improve the overall recognition performance with individual difference. Specifically, RRAN achieves a 96.84% accuracy on YouTube Face, outperforming all existing aggregation schemes.

Improved crossover firefly algorithm based deep Beleif network for low-resolution face recognition

Face detection by low-resolution image (LR) is one of the key aspects of Human-Computer Interaction(HCI). Due to the LR image, which has changes in pose, lighting, and illumination, the performance of face recognition is reduced. In this work, we propose the Deep Belief Network-Crossover based Firefly (DBN-CROFF) method for face recognition from low-resolution images. The Histogram of Gradient (HOG) and 2-Dimensional Discrete Wavelet Transform (2D-DWT) to extract facial width, size of the cheeks, skin tone, nose, and lip shape features from facial data. The Kernel Principle Component Analysis (k-PCA) is used to successfully reduce the dimension of the feature. The experimental performance of the proposed method is evaluated using four datasets namely LFW, Multi-PIE, Extended Yale-B, and FERET with conventional techniques. Finally, the proposed DBN-CROFF solution surpasses the other conventional facial recognition approaches by giving a higher accuracy of recognization.

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.

Deep-learning based descriptors in application to aging problem in face recognition

Nowadays, “aging” becomes a challenging problem for face recognition systems. The challenge is particularly due to age-related biological changes, which can lead to significant variations in facial characteristics between two images taken at different ages of the same person. As the face is the most heavily part affected by aging, there is a growing need to extracting robust face features for age-invariant face recognition, particularly, in the presence of large age differences of the same person face images. The aim of this paper is to examine effectiveness of deep-learning based methods as features extraction tool for age-invariant face recognition. In this study, we evaluate five popular pre-trained deep-convolutional neural network (CNN) models that are AlexNet, GoogleNet, Inception V3, ResNet50 and SqueezeNet, on a widely used face-aging database, namely FG-NET, using K-nearest neighbors (K-NN), discriminant analysis, and support vector machines (SVM) classifiers. Further, a statistical analysis test is performed to confirm the statistical significance of the obtained results. Experimental results on this database show the promise of using Convolutional Neural Networks(CNN) for face recognition across age progression. Also the AlexNet model appears to be most promising for age-invariant face recognition, as highest mean accuracy rate is always achieved with feature extraction using the AlexNet model. These results are more significant, according to a 95% confidence level hypothesis test.

Hybrid features and exponential moth-flame optimization based deep belief network for face recognition

ABSTRACT Face recognition finds its application in various areas, like biometrics, person identification through their identity cards, Closed-Circuit Television (CCTV) cameras, and so on. Among various biometrics, such as fingerprint, palm print, iris, etc., face plays an important role. Hence, a face recognition technology was developed in the previous papers, with contributions in the feature extraction and classification phases. In this paper, an approach is developed for face recognition using the proposed Exponential Moth-flame Optimisation (Exponential MFO) based Deep Belief Network (DBN). Initially, the images in the database undergo feature extraction, where the features, such as K-SIFT, m-Co-HOG, along with Active Appearance Models (AAM) features are extracted from the image. Then, the classification is done using the proposed EMFO-DBN. The proposed EMFO-DBN is designed by integrating the Exponential Weighted Moving Average (EWMA) into the update process of the Moth flame optimisation (MFO) algorithm. The experimentation of the proposed method has been done using the CVL database, and the proposed method outclassed other state of the art techniques with the values of 0.98, 0.0073, and 0.0083, respectively, for accuracy, FAR, and FRR, respectively.

Attacks on state-of-the-art face recognition using attentional adversarial attack generative network

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. Therefore, it is very important to study how face recognition networks are subject to attacks. Generating adversarial examples is an effective attack method, which misleads the face recognition system through obfuscation attack (rejecting a genuine subject) or impersonation attack (matching to an impostor). In this paper, we introduce a novel GAN, Attentional Adversarial Attack Generative Network (A3GN), to generate adversarial examples that mislead the network to identify someone as the target person not misclassify inconspicuously. For capturing the geometric and context information of the target person, this work adds a conditional variational autoencoder and attention modules to learn the instance-level correspondences between faces. Unlike traditional two-player GAN, this work introduces a face recognition network as the third player to participate in the competition between generator and discriminator which allows the attacker to impersonate the target person better. The generated faces which are hard to arouse the notice of onlookers can evade recognition by state-of-the-art networks and most of them are recognized as the target person.

Computational Method for Recognizing Situations and Objects in the Frames of a Continuous Video Stream Using Deep Neural Networks for Access Control Systems

An effective (performance- and accuracy-wise) computational method for pattern recognition in a continuous video stream using deep neural networks for access control systems is proposed. The class of recognition problems solved by the method using a sequence of video stream frames is identified: the vehicle itself and the characters on its license plate (LP), faces of people, and abnormal situations. In contrast to the known solutions, a classification with a subsequent reinforcement based on multiple frames of a video stream and with an algorithm for the automatic annotation of images is used. Neural network architectures with independent recurrent layers for classifying video fragments adapted for the problems, a dual network for face recognition, and a deep neural network for vehicle character recognition are proposed. New databases for neural network training are created. A schematic diagram of an intelligent access control system for ensuring the security of an enterprise, a distinctive feature of which is the use of a multirotor unmanned aerial vehicle with a computing unit, is proposed. Field experiments are carried out, and the accuracy and performance of the computational method in solving each problem are assessed. Software modules in the Python language for solving tasks of the intelligent access control system are developed.

KeyFrame extraction based on face quality measurement and convolutional neural network for efficient face recognition in videos

Indexing is the process of extracting a compact, significant and pertinent signature that describes the content of the data. This field has a broad spectrum of promising applications, such as the Face in Video Recognition (FiVR). Motivating the interest of researchers around the world. Since the video has a huge amount of data, the process of extracting the relevant frames becomes necessary and an essential step prior to performing face recognition. In this context, we propose a new method for extracting keyframes from videos based on face quality and deep learning for a face recognition task. The first step is the face detection using MTCNN detector, which detects five landmarks (the eyes, the two corners of the mouth and the nose). It limits face boundaries in a bounding box, and provides a confidence score. This method has two steps. The first step aims to generate the face quality score of each face in the data set prepared for the learning step. To generate quality scores, we use three face feature extractor including Gabor, LBP and HoG. The second step consist on training a deep Convolutional Neural Network in a supervised manner in order to select frames having the best face quality. The obtained results show the effectiveness of the proposed method compared to the methods of the state of the art.

Application Research of Deep Convolutional Neural Network in Computer Vision

<p>As an important research achievement in the field of brain like computing, deep convolution neural network has been widely used in many fields such as computer vision, natural language processing, information retrieval, speech recognition, semantic understanding and so on. It has set off a wave of neural network research in industry and academia and promoted the development of artificial intelligence. At present, the deep convolution neural network mainly simulates the complex hierarchical cognitive laws of the human brain by increasing the number of layers of the network, using a larger training data set, and improving the network structure or training learning algorithm of the existing neural network, so as to narrow the gap with the visual system of the human brain and enable the machine to acquire the capability of "abstract concepts". Deep convolution neural network has achieved great success in many computer vision tasks such as image classification, target detection, face recognition, pedestrian recognition, etc. Firstly, this paper reviews the development history of convolutional neural networks. Then, the working principle of the deep convolution neural network is analyzed in detail. Then, this paper mainly introduces the representative achievements of convolution neural network from the following two aspects, and shows the improvement effect of various technical methods on image classification accuracy through examples. From the aspect of adding network layers, the structures of classical convolutional neural networks such as AlexNet, ZF-Net, VGG, GoogLeNet and ResNet are discussed and analyzed. From the aspect of increasing the size of data set, the difficulties of manually adding labeled samples and the effect of using data amplification technology on improving the performance of neural network are introduced. This paper focuses on the latest research progress of convolution neural network in image classification and face recognition. Finally, the problems and challenges to be solved in future brain-like intelligence research based on deep convolution neural network are proposed.</p>

In brief

PAGE 810 Greek and Serbian researchers present a new recurrent neural network (RNN) for solving linear algebraic systems with finite-time convergence. The network can converge on a solution faster than previous methods due to inclusion of an exponential term in the Zhang neural network (ZNN). The work is validated by theoretical analysis and simulation. PAGE 816 Two researchers from South Korea introduce attention-guided domain adaptation networks for face recognition under an unsupervised setting. The proposed module is applied to category classifiers and domain discriminators in a channel-wise manner. By learning the optimal adaptation factor for each channel the networks successfully align source and target domains. The residual error ||Ax(t)−b||of VPFTZNN (5) (for γ= 100,p= 3 and q= 2) and GNN [12]. PAGE 840 A capacitor-based bionic synapse is proposed, harnessing the partial polarisation switching of multi-domain properties in polycrystalline Zr-doped HfO2 ferroelectric materials. The synapse shows multi-level capacitance modulation characteristics. This research lays the groundwork for realising high-density integration neuromorphic computing systems. Proposed attention-guided model. PAGE 806 Chinese researchers propose a time-difference integrator which can compensate for the time-error caused by leakage current in gated delay-buffer cells. It is implemented in a 28-nm CMOS process, achieving a gain of 27.39 dB with a 317 kHz 30 ps peak-to-peak sinosudal input and consumes 110.3 μW with 50 MHz sampling rate from a 0.9 V supply. Simplified schematic of the prepared capacitor with TiN/HZO/TiN structure. PAGE 808 Two researchers from New Zealand present the design and analysis of a tunable low-noise amplifier, capable of achieveing single-band (1 GHz), dual-band (1 GHz and 1.7 GHz–2.5 GHz) and wideband (1.6–2.5 GHz) operations. The amplifier has a measured power gain of 7–15 dB and a noise figure of 1.2–2.2 dB across all bands. Simulated integrated time error. Multimode tunable low-noise amplifier design.

Attention‐guided adaptation factors for unsupervised facial domain adaptation

In this Letter, the authors introduce attention-guided domain adaptation networks for face recognition under the unsupervised setting. Recently, there has been a dramatic increase in demand for real-world face recognition problems under severe domain shifts. Adversarial learning of the domain adaptation network has shown promising results for this problem. However, this approach has limitations in manually setting the adaptation factor that controls the trade-off between feature discriminability and domain-invariance. To address this critical issue, the authors propose attention-guided domain adaptation networks that can learn the optimal adaptation factor without the manual configurations. The proposed attention-guided module is applied to both category classifier and domain discriminator in a channel-wise manner. By learning the optimal adaptation factor for each channel, the proposed networks successfully align the source domain to the target domain and show state-of-the-art performance on the public datasets.

Feature extraction based on deep‐convolutional neural network for face recognition

SummaryFeature extraction is a critical technology that affects the accuracy of face recognition. However, certain features are highly related to changes in face are difficult to extract because of the influences of individual differences and illumination. Therefore, features can accurately describe the changes in face are urgently required. For this reason, this article proposes a feature extraction method based on deep learning. This method combines the features extracted by Local Binary Patterns and by Convolutional Neural Network convolutional layer in the network connection layer, thus obtaining classification features with high representation ability and solving the problem of single feature extraction. The VGG‐16 network proposed in this article has been improved by changing the framework structure. Some experiments based on the Labeled Faces in the Wild dataset are performed, and results show that, in terms of accuracy and the sensitivity to light, the proposed method reaches 99.56% and 80.35% respectively. The recognition results obtained from fused features are superior to which of single feature recognition. Simulation results show that the method is more robust to changes in the illumination condition and more efficient than the existing methods.

Automatic Identification of Down Syndrome Using Facial Images with Deep Convolutional Neural Network.

Down syndrome is one of the most common genetic disorders. The distinctive facial features of Down syndrome provide an opportunity for automatic identification. Recent studies showed that facial recognition technologies have the capability to identify genetic disorders. However, there is a paucity of studies on the automatic identification of Down syndrome with facial recognition technologies, especially using deep convolutional neural networks. Here, we developed a Down syndrome identification method utilizing facial images and deep convolutional neural networks, which quantified the binary classification problem of distinguishing subjects with Down syndrome from healthy subjects based on unconstrained two-dimensional images. The network was trained in two main steps: First, we formed a general facial recognition network using a large-scale face identity database (10,562 subjects) and then trained (70%) and tested (30%) a dataset of 148 Down syndrome and 257 healthy images curated through public databases. In the final testing, the deep convolutional neural network achieved 95.87% accuracy, 93.18% recall, and 97.40% specificity in Down syndrome identification. Our findings indicate that the deep convolutional neural network has the potential to support the fast, accurate, and fully automatic identification of Down syndrome and could add considerable value to the future of precision medicine.

Point cloud based deep convolutional neural network for 3D face recognition

Face recognition is a challenging task as it has to deal with several issues such as illumination orientation and variability among the different faces. Previous works have shown that 3D face is a robust biometric trait and is less sensitive to light and pose variations. Also due to availability of inexpensive sensors and new 3D data acquisition techniques it has become easy to capture 3D data. A 3D depth image of a face is found to be rich in information and biometric recognition performance can be enhanced by using 3D face data along with convolutional neural network. However the shortcoming of this approach is the conversion of 3D data to lower dimensions (depth image) which suffer from loss of geometric information and the network becomes computationally expensive. In this work we endeavor to apply deep learning method for 3D face recognition and propose a deep convolutional neural network based on PointNet architecture which consumes point cloud directly as input and siamese network for similarity learning. Further we propose a solution to the issue of a limited database by applying data augmentation at the point cloud level. Our proposed technique shows encouraging performance on Bosphorus and IIT Indore 3D face databases.

DEVELOPMENT A SYSTEM FOR CLASSIFYING AND RECOGNIZING PERSON’S FACE

The purpose of this article is to summarize the knowledge gained in the development and implementation of a neural network for facial recognition. Neural networks are used to solve complex tasks that require analytical calculations similar to what the human brain does. Machine learning algorithms are the foundation of a neural network. As input, the algorithm receives an image with people's faces, then searches for faces in this image using HOG (Histogram of oriented gradients). The result is images with explicit face structures. To determine unique facial features, the Face landmark algorithm is used, which finds 68 special points on the face. These points can be used to centerthe eyes and mouth for more accurate encoding. To get an accurate “face map” consisting of 128 dimensions, you need to use image encoding. Using the obtained data, the convolutional neural network can determine people's faces using the SVM linear classifier algorithm.