Existing Face Recognition Systems Research Articles

Attention‐guided evolutionary attack with elastic‐net regularization on face recognition

In recent years, face recognition has achieved promising results along with the development of advanced Deep Neural Networks (DNNs). The existing face recognition systems are vulnerable to adversarial examples, which brings potential security risks. Evolutionary Attack (EA) has been successfully used to fool face recognition by inducing a minimum perturbation to a face image with few queries. However, EA employs the global information of face images but ignores their local characteristics. In addition, restricting the ℓ2-norm of adversarial perturbations hinders the diversity of adversarial perturbations. To solve the above problems, we propose Attention-guided Evolutionary Attack with Elastic-Net Regularization (ERAEA) for attacking face recognition. ERAEA extracts local facial characteristics by attention mechanism, effectively improving the attack effect and image perception quality. In particular, ERAEA adopts an attention mechanism to guide evolutionary direction, which operates on the covariance matrix as it contains crucial information about the evolutionary path. Furthermore, we design an adaptive elastic-net regularization to diversify the adversarial perturbation, accelerating the optimization performance. Extensive experiments obtained on three benchmarks demonstrate that our proposed method achieves better perturbation norm than the state-of-the-art methods with limited queries on face recognition and generates adversarial face images with higher perceptual quality. Besides, ERAEA requires fewer queries to achieve a fixed adversarial perturbation norm.

Using infrared to improve face recognition of individuals with highly pigmented skin

Face recognition is widely used for security and access control. Its performance is limited when working with highly pigmented skin tones due to training bias caused by the under-representation of darker-skinned individuals in existing datasets and the fact that darker skin absorbs more light and therefore reflects less discernible detail in the visible spectrum. To improve performance, this work incorporated the infrared (IR) spectrum, which is perceived by electronic sensors. We augmented existing datasets with images of highly pigmented individuals captured using the visible, IR, and full spectra and fine-tuned existing face recognition systems to compare the performance of these three. We found a marked improvement in accuracy and AUC values of the receiver operating characteristic (ROC) curves when including the IR spectrum, increasing performance from 97.5% to 99.0% for highly pigmented faces. Different facial orientations and narrow cropping also improved performance, and the nose region was the most important feature for recognition.

Facial Recognition System with Voice Message Enhancement

Face recognition system has always been a crucial human-computer interaction tool in most security systems, access control, video surveillance, commercial areas, and networks like Facebook as well. After development in the area of artificial intelligence and growing security concerns, face recognition system has attracted attention by providing maximum efficiency in face detection and recognition. Face recognition is considered to be a biometric artificial intelligence-based application. Face recognition is the process of recognizing the face of a person by a vision system. As an extension to the existing face recognition system in this model, a new feature is added i.e., a voice message as output that is produced for each face recognized. The voice message could be anything like a simple hello or even a complex sentence. Keywords: Artificial intelligence, Face recognition, voice message, OpenCV, pyttsx.

Perturbation Inactivation Based Adversarial Defense for Face Recognition

Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations. However, the generalization capacities of these methods are quite limited. In practice, they are still vulnerable to unseen adversarial attacks. Deep learning models are fairly robust to general perturbations, such as Gaussian noises. A straightforward approach is to inactivate the adversarial perturbations so that they can be easily handled as general perturbations. In this paper, a plug-and-play adversarial defense method, named perturbation inactivation (PIN), is proposed to inactivate adversarial perturbations for adversarial defense. We discover that the perturbations in different subspaces have different influences on the recognition model. There should be a subspace, called the immune space, in which the perturbations have fewer adverse impacts on the recognition model than in other subspaces. Hence, our method estimates the immune space and inactivates the adversarial perturbations by restricting them to this subspace. The proposed method can be generalized to unseen adversarial perturbations since it does not rely on a specific kind of adversarial attack method. This approach not only outperforms several state-of-the-art adversarial defense methods but also demonstrates a superior generalization capacity through exhaustive experiments. Moreover, the proposed method can be successfully applied to four commercial APIs without additional training, indicating that it can be easily generalized to existing face recognition systems. The source code is available at https://github.com/RenMin1991/Perturbation-Inactivate..

Low-complexity fake face detection based on forensic similarity

In recent years, face synthesis and manipulation technology have been developed rapidly, and now it is feasible to synthesize extremely realistic fake face videos, which can easily deceive existing face recognition systems. Due to the high quality of fake videos, allowing fake face videos to propagate on Internet may cause serious ethical, moral and legal problems. Therefore, the effective and reliable detection method is urgently needed to distinguish fake face videos. We notice that existing face forgery methods commonly extract face area of each frame first and perform manipulations only on face areas while background areas remain unchanged. Therefore, the difference between the face area and the background area in a forged face frame is significantly larger than the difference between the face area and the background area in the corresponding unforged frame. In this paper, based on such observation, we propose a new detection method—forensic similarity method—which judges the authenticity of face video frames by detecting the difference in similarity between the face area and the background area. For evaluation, we conduct training and testing on FaceForensics++ dataset, and evaluate the generalization capability on Celeb-DF dataset. From the experimental results, we can find that the proposed method has a better or comparable performance, especially in the term of generalization capability. Compared with Xception, our model can attain 8–12% accuracy gains under Celeb-DF dataset. In addition, our model has lower complexity than Xception.

Cropping and attention based approach for masked face recognition.

The global epidemic of COVID-19 makes people realize that wearing a mask is one of the most effective ways to protect ourselves from virus infections, which poses serious challenges for the existing face recognition system. To tackle the difficulties, a new method for masked face recognition is proposed by integrating a cropping-based approach with the Convolutional Block Attention Module (CBAM). The optimal cropping is explored for each case, while the CBAM module is adopted to focus on the regions around eyes. Two special application scenarios, using faces without mask for training to recognize masked faces, and using masked faces for training to recognize faces without mask, have also been studied. Comprehensive experiments on SMFRD, CISIA-Webface, AR and Extend Yela B datasets show that the proposed approach can significantly improve the performance of masked face recognition compared with other state-of-the-art approaches.

Is Face Recognition with Masks Possible?

With the recent outbreak of the COVID-19 pandemic, wearing face masks has become extremely important to protect us, and to reduce the spread of the virus. This measure has made many existing face recognition systems ineffective as they were trained to work with unmasked faces. In this paper, several methods have been proposed for masked face recognition. Two pre-trained deep learning architectures (VGG16, and MobileNetV2) and the Histogram of Gradients (HOG) technique were used to extract the relevant features from face images of celebrities. A SoftMax layer and Support Vector Machines (SVM) were used for classification. Five scenarios were devised to assess the different models and approaches. With an accuracy of 96.8%, the best model was obtained with MobileNetV2 with a SoftMax layer on the dataset consisting of a mixture of masked and unmasked images. Three different types of masks were also used in this study. The mean accuracy was 91.35% when the same type of mask is used for training and testing. However, the accuracy dropped by an average of 5.6% when a different type of mask is used for training and testing. A contactless attendance system using the best masked face recognition model has also been implemented. © 2021. All Rights Reserved.

AN ADOPTION OF 2D-PCA/ICA BASED POST-PROCESSING DIMENSIONALITY REDUCTION ALGORITHM FOR FACIAL RECOGNITION SYSTEM

Face images undergo considerable amount of variations in pose, facial expression and illumination condition. This large variation in facial appearances of the same individual makes most Existing Face Recognition Systems (E-FRS) lack strong discrimination ability and timely inefficient for face representation due to holistic feature extraction technique used. In this paper, a novel face recognition framework, which is an extension of the standard (PCA) and (ICA) denoted as two-dimensional Principal Component Analysis (2D-PCA) and two-dimensional Independent Component Analysis (2D-ICA) respectively is proposed. The choice of 2D was advantageous as image covariance matrix can be constructed directly using original image matrices. The face images used in this study were acquired from the publicly available ORL and AR Face database. The features belonging to similar class were grouped and correlation calculated in the same order. Each technique was decomposed into different components by employing multi-dimensional grouped empirical mode decomposition using Gaussian function. The nearest neighbor (NN) classifier is used for classification. The results of evaluation showed that the 2D-PCA method using ORL database produced RA of 92.5%, PCA produced RA of 75.00%, ICA produced RA of 77.5%, 2D-ICA produced RA of 96.00%. However, 2D-PCA methods using AR database produced RA of 73.56%, PCA produced RA of 62.41%, ICA produced RA of 66.20%, 2D-ICA method produced RA of 77.45%. This study revealed that the developed face recognition framework algorithm achieves an improvement of 18.5% and 11.25% for the ORL and AR databases respectively as against PCA and ICA feature extraction techniques. Keywords: computer vision, dimensionality reduction techniques, face recognition, pattern recognition

Verifying the Effectiveness of New Face Spoofing DB with Capture Angle and Distance

Face recognition is a representative biometric that can be easily used; however, spoofing attacks threaten the security of face biometric systems by generating fake faces. Thus, it is not advisable to only consider sophisticated spoofing cases, such as three-dimensional masks, because they require additional equipment, thereby increasing the implementation cost. To prevent easy face spoofing attacks through print and display, the two-dimensional (2D) image analysis method using existing face recognition systems is reasonable. Therefore, we proposed a new database called the “pattern recognition-face spoofing advancement database” that can be used to prevent such attacks based on 2D image analysis. To the best of our knowledge, this is the first face spoofing database that considers the changes in both the angle and distance. Therefore, it can be used to train various positional relationships between a face and camera. We conducted various experiments to verify the efficiency of this database. The spoofing detection accuracy of our database using ResNet-18 was found to be 96.75%. The experimental results for various scenarios demonstrated that the spoof detection performances were better for images with pinch angle, near distance images, and replay attacks than those for front images, far distance images, and print attacks, respectively. In the cross-database verification result, the performance when tested with other databases (DBs) after training with our DB was better than the opposite. The results of cross-device verification in terms of camera type showed negligible difference; thus, it was concluded that the type of image sensor does not affect the detection accuracy. Consequently, it was confirmed that the proposed DB that considers various distances, capture angles, lighting conditions, and backgrounds can be used as a training DB to detect spoofing attacks in general face recognition systems.

Human Face Identification based on Optimal Sparse Features

Security of human being is an important aspect in the context of data communication. To maintain security, technology is being developed from alpha-numeric passwords to biometric scanners. Recent advancement in security is the user authentication using face recognition. But the flaws in existing face recognition systems are yet to be addressed. This paper discusses solutions to the issues encountered by face recognition systems. Sparsity based classification is performed in this work. This method can handle errors occurs due to compress in and occlusion in a robust manner. We suggest a comprehensive classification algorithm characterized by sparse representation and 1l -minimization. In this method, the feature points and selection of features are not critical. The effect of change in occlusion can be easily addressed by using this optimal sparse representation based classification (OSRC) algorithm.

Review on Facial Recognition

Generally face recognition perform many operations in our daily life such as security purpose identification of people and verification purpose. The basic aim of my project is to design an effective and secure technique for authentication using face recognition that can search or recognize a human face among the thousands of persons and improve the performance of face recognition system in low light conditions and also evaluate the performance of the designed framework by comparing the performance of existing face recognition system. This study also provides a automatic system through which a given still image or video of a scene, identify one or more persons in this scene by using a stored database of facial images.

Recognizing Disguised Faces in the Wild

Research in face recognition has seen tremendous growth over the past couple of decades. Beginning from algorithms capable of performing recognition in constrained environments, existing face recognition systems achieve very high accuracies on large-scale unconstrained face datasets. While upcoming algorithms continue to achieve improved performance, many of them are susceptible to reduced performance under disguise variations, one of the most challenging covariate of face recognition. In this paper, the disguised faces in the wild (DFW) dataset is presented, which contains over 11000 images of 1000 identities with variations across different types of disguise accessories (the DFW dataset link: http://iab-rubric.org/resources/dfw.html ). The images are collected from the Internet, resulting in unconstrained variations similar to real-world settings. This is a unique dataset that contains impersonator and genuine obfuscated face images for each subject. The DFW dataset has been analyzed in terms of three levels of difficulty: 1) easy; 2) medium; and 3) hard, in order to showcase the challenging nature of the problem. The dataset was released as part of the First International Workshop and Competition on DFW at the Conference on Computer Vision and Pattern Recognition, 2018. This paper presents the DFW dataset in detail, including the evaluation protocols, baseline results, performance analysis of the submissions received as part of the competition, and three levels of difficulties of the DFW challenge dataset.

Performance Evaluation of Kernel-Based Feature Extraction Techniques for Face Recognition System

Face recognition is considered to be one of the most reliable biometrics where security issues are of concerned. Feature extraction which is a functional block of a face recognition system becomes a critical problem when there is need to obtain the best feature with minimum classification error and low running time. Most existing face recognition systems have adopted different non-linear feature extraction techniques for face recognition but identification of the most suitable non-linear kernel variants for these systems remain an open problem. Hence, this research work analyzed the performance of three kernel feature extraction technique (Kernel Principal Component Analysis, Kernel Linear Discriminant Analysis and Kernel Independent Component Analysis) for face recognition system. A database of 360 face images was created by obtaining facial images from LAUTECH Biometric Research Group consisting of six facial expressions of 60 persons. Images were preprocessed (gray scaling, cropping and histogram equalization) and the kernel variants were used to extract distinctive features and reduce the dimensionality of each of the images from 600x800 pixels to four smaller dimensions: 50x50, 100x100, 150x150 and 200x200 pixels. Euclidean Distance similarity measure was used for classification. The performance of the three kernel variants was evaluated for face recognition system using 180 images for training and 180 images for testing using the following metrics: Recognition Accuracy (RA) and Recognition Time (RT). Empirical result indicate that KLDA performs best for face recognition system with an average accuracy of 94.52%. The larger image dimension also results in better recognition performance. We intend to experiment on other classifiers for face recognition system in our future work. Keywords— Biometrics, Face, Feature extraction, Kernel, KICA, KPCA, KLDA, Linear, Non-linear;

FD-GAN: Face De-Morphing Generative Adversarial Network for Restoring Accomplice’s Facial Image

Face morphing attack is proved to be a serious threat to the existing face recognition systems. Although a few face morphing detection methods have been put forward, the face morphing accomplice's facial restoration remains a challenging problem. In this paper, a face de-morphing generative adversarial network (FD-GAN) is proposed to restore the accomplice's facial image. It utilizes a symmetric dual network architecture and two levels of restoration losses to separate the identity feature of the morphing accomplice. By exploiting the captured facial image (containing the criminal's identity) from the face recognition system and the morphed image stored in the e-passport system (containing both criminal and accomplice's identities), the FD-GAN can effectively restore the accomplice's facial image. Experimental results and analysis demonstrate the effectiveness of the proposed scheme. It has great potential to be implemented for detecting the face morphing accomplice in a real identity verification scenario.

Sensor-Assisted Multi-View Face Recognition System on Smart Glass

Face recognition is a hot research topic with a variety of application possibilities, including video surveillance and mobile payment. It has been well researched in traditional computer vision community. However, new research issues arise when it comes to resource constrained devices, such as smart glasses, due to the overwhelming computation and energy requirements of the accurate face recognition methods. In this paper, we propose a robust and efficient sensor-assisted face recognition system on smart glasses by exploring the power of multimodal sensors including the camera and Inertial Measurement Unit (IMU) sensors. The system is based on a novel face recognition algorithm, namely Multi-view Sparse Representation Classification (MVSRC), by exploiting the prolific information among multi-view face images. To improve the efficiency of MVSRC on smart glasses, we propose two novel sampling optimization strategies using the less expensive inertial sensors. Our evaluations on public and private datasets show that the proposed method is up to 10 percent more accurate than the state-of-the-art multi-view face recognition methods while its computation cost is the same order as an efficient benchmark method (e.g., Eigenfaces). Finally, extensive real-world experiments show that our proposed system improves recognition accuracy by up to 15 percent while achieving the same level of system overhead compared to the existing face recognition system (OpenCV algorithms) on smart glasses.

Facial marks for improving face recognition

Recent studies have shown that the use of soft biometrics (e.g. gender, ethnicity, facial marks) as supplementary information in face images, can increase the accuracy of the recognition process of individuals. Facial marks (e.g. moles, freckles, warts) have shown to be useful, particularly, in this regard. In this paper we propose a new method for combining existing face recognition systems with the information obtained from facial marks in order to improve their performance. We first introduce an algorithm for automatically detecting facial marks, which are then represented using Histograms of Oriented Gradients (HoG), and are matched taking into account their position in the face image. Extensive experiments are conducted in order to show the effectiveness of the proposed facial mark detection algorithm, and to corroborate the benefits of using the information of facial marks on top of traditional face recognition systems. Due to the lack of proper public benchmarks to validate facial mark detection, we also present and make available a dataset with manual annotations for this purpose.

A Techniques for Face Recognition Systems

In this research, a comparison of the various techniques used for face recognition is shown in tabular format to give a precise overview of what different authors have already projected in this particular field. A systematic review of 40 journal articles pertaining to feature dimensionality reduction was carried out. The articles were reviewed to appraise the methodology and to identify the key parameters that were used for testing and evaluation. The dates of publication of the articles were between 2007 and 2015. Ten percent (10%) of the articles reported the training time for their system while twenty four percent (24%) reported their testing time. Sixty seven percent (67%) of the reviewed articles reported the image dimension used in the research. Also, only fourty eight percent (48%) of the reviewed articles compared their result with other existing methods. The main emphasis of this survey is to identify the major trade-offs of parameters and (or) metrics for evaluating the performance of the techniques employed in dimensionality reduction by existing face recognition systems. Findings from the review carried out showed that major performance metrics reported by vast amount of researchers in this review is recognition accuracy in which eighty six percent (86%) of the authors reported in their experiment. Keywords: Optimal Subset, High Dimension, Face Recognition, Biometrics, Feature Vector

Face Recognition in the Wild

Face recognition is one of the most important tasks in pattern recognition and computer vision. The most conventional way to per- form face recognition is to compare a set of facial features that are extracted from a source image or a video frame with a reference image database of known faces. Such a classification takes the form of a prediction within a closed-set of classes. However, a more realistic scenario that fits the ground truth of real-world face recognition applications is to consider the possibility of encountering faces that do not belong to any of the training classes, i.e., an open-set classification. Such a constraint is very challenging to most existing face recognition systems since the latter are based on closed-set classification methods which always assign a training label to novel unknown instances even if they represent unseen faces that are not represented in the reference database. This results in a misclassification. In this paper, we introduce Face Recognition in the Wild (FRW), a novel face recognition system that allows (1) to efficiently recognize known faces from the reference database, and (2) to prevent misclassifying instances that represent unknown and unseen faces. FRW formulates this problem as a multi-class classification in an open-set context where the presence of instances from unknown classes is possible. Experimental results on the challenging Olivetti Faces benchmark dataset show the efficiency of our approach in open-set face recognition problems.

Recognizing Surgically Altered Face Images and 3D Facial Expression Recognition

Altering Facial appearances using surgical procedures are common now days. But it raised challenges for face recognition algorithms. Plastic surgery introduces non linear variations. Because of these variations it is difficult to be modeled by the existing face recognition system. Here presents a multi objective evolutionary granular algorithm. It operates on several granules extracted from a face images at multiple level of granularity. This granular information is unified in an evolutionary manner using multi objective genetic approach. Then identify the facial expression from the face images. For that 3D facial shapes are considering here. A novel automatic feature selection method is proposed based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidian distances between 83 facial feature points in the 3D space. A regularized multi-class AdaBoost classification algorithm is used here to get the highest average recognition rate.

Joint Feature Learning for Face Recognition

This paper presents a new joint feature learning (JFL) approach to automatically learn feature representation from raw pixels for face recognition. Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. Since different face regions have different physical characteristics, we propose to use different feature dictionaries to represent them, and to learn multiple yet related feature projection matrices for these regions simultaneously. Hence position-specific discriminative information can be exploited for face representation. Having learned these feature projections for different face regions, we perform spatial pooling for face patches within each region to enhance the representative power of the learned features. Moreover, we stack our JFL model into a deep architecture to exploit hierarchical information for feature representation and further improve the recognition performance. Experimental results on five widely used face data sets show the effectiveness of our proposed approach.