This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><...This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this system can be updated via our custom-built standalone android app and automatic restarting of the training and recognition process with an updated database. Using our proposed algorithm, a real-time face recognition accuracy of 78.40% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 98.05% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px have been achieved using the LRD200 database containing 200 images per person. With 100 images per person in the database (LRD100) the achieved accuracies are 60.60% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 95% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px respectively. A facial deflection of about 30</span></span></span><span><span><span><span><span style="color:#4F4F4F;font-family:-apple-system, " font-size:16px;white-space:normal;background-color:#ffffff;"="">°</span></span><span> on either side from the front face showed an average face recognition precision of 72.25%-81.85%. This face recognition system can be employed for law enforcement purposes, where the surveillance camera captures a low-resolution image because of the distance of a person from the camera. It can also be used as a surveillance system in airports, bus stations, etc., to reduce the risk of possible criminal threats.</span></span></span></span>展开更多
With the rapid development of artificial intelligence,face recognition systems are widely used in daily lives.Face recognition applications often need to process large amounts of image data.Maintaining the accuracy an...With the rapid development of artificial intelligence,face recognition systems are widely used in daily lives.Face recognition applications often need to process large amounts of image data.Maintaining the accuracy and low latency is critical to face recognition systems.After analyzing the two-tier architecture“client-cloud”face recognition systems,it is found that these systems have high latency and network congestion when massive recognition requirements are needed to be responded,and it is very inconvenient and inefficient to deploy and manage relevant applications on the edge of the network.This paper proposes a flexible and efficient edge computing accelerated architecture.By offloading part of the computing tasks to the edge server closer to the data source,edge computing resources are used for image preprocessing to reduce the number of images to be transmitted,thus reducing the network transmission overhead.Moreover,the application code does not need to be rewritten and can be easily migrated to the edge server.We evaluate our schemes based on the open source Azure IoT Edge,and the experimental results show that the three-tier architecture“Client-Edge-Cloud”face recognition system outperforms the state-of-art face recognition systems in reducing the average response time.展开更多
Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extrac...Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.展开更多
In recent work,adversarial stickers are widely used to attack face recognition(FR)systems in the physical world.However,it is difficult to evaluate the performance of physical attacks because of the lack of volunteers...In recent work,adversarial stickers are widely used to attack face recognition(FR)systems in the physical world.However,it is difficult to evaluate the performance of physical attacks because of the lack of volunteers in the experiment.In this paper,a simple attack method called incomplete physical adversarial attack(IPAA)is proposed to simulate physical attacks.Different from the process of physical attacks,when an IPAA is conducted,a photo of the adversarial sticker is embedded into a facial image as the input to attack FR systems,which can obtain results similar to those of physical attacks without inviting any volunteers.The results show that IPAA has a higher similarity with physical attacks than digital attacks,indicating that IPAA is able to evaluate the performance of physical attacks.IPAA is effective in quantitatively measuring the impact of the sticker location on the results of attacks.展开更多
Face recognition has emerged as one of the most prominent applications of image analysis and under-standing,gaining considerable attention in recent years.This growing interest is driven by two key factors:its extensi...Face recognition has emerged as one of the most prominent applications of image analysis and under-standing,gaining considerable attention in recent years.This growing interest is driven by two key factors:its extensive applications in law enforcement and the commercial domain,and the rapid advancement of practical technologies.Despite the significant advancements,modern recognition algorithms still struggle in real-world conditions such as varying lighting conditions,occlusion,and diverse facial postures.In such scenarios,human perception is still well above the capabilities of present technology.Using the systematic mapping study,this paper presents an in-depth review of face detection algorithms and face recognition algorithms,presenting a detailed survey of advancements made between 2015 and 2024.We analyze key methodologies,highlighting their strengths and restrictions in the application context.Additionally,we examine various datasets used for face detection/recognition datasets focusing on the task-specific applications,size,diversity,and complexity.By analyzing these algorithms and datasets,this survey works as a valuable resource for researchers,identifying the research gap in the field of face detection and recognition and outlining potential directions for future research.展开更多
The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer a...The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer and the device layer.Besides,previous research fails to consider the facial characteristics including occluded and unoccluded parts.To solve the above problems,we put forward a device-edge collaborative occluded face recognition method based on cross-domain feature fusion.Specifically,the device-edge collaborative face recognition architecture gets the utmost out of maximizes device and edge resources for real-time occluded face recognition.Then,a cross-domain facial feature fusion method is presented which combines both the explicit domain and the implicit domain facial.Furthermore,a delay-optimized edge recognition task scheduling method is developed that comprehensively considers the task load,computational power,bandwidth,and delay tolerance constraints of the edge.This method can dynamically schedule face recognition tasks and minimize recognition delay while ensuring recognition accuracy.The experimental results show that the proposed method achieves an average gain of about 21%in recognition latency,while the accuracy of the face recognition task is basically the same compared to the baseline method.展开更多
Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in ...Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.展开更多
Face recognition has been a hot-topic in the field of pattern recognition where feature extraction and classification play an important role. However, convolutional neural network （CNN） and local binary pattern （LB...Face recognition has been a hot-topic in the field of pattern recognition where feature extraction and classification play an important role. However, convolutional neural network （CNN） and local binary pattern （LBP） can only extract single features of facial images, and fail to select the optimal classifier. To deal with the problem of classifier parameter optimization, two structures based on the support vector machine （SVM） optimized by artificial bee colony （ABC） algorithm are proposed to classify CNN and LBP features separately. In order to solve the single feature problem, a fusion system based on CNN and LBP features is proposed. The facial features can be better represented by extracting and fusing the global and local information of face images. We achieve the goal by fusing the outputs of feature classifiers. Explicit experimental results on Olivetti Research Laboratory （ORL） and face recognition technology （FERET） databases show the superiority of the proposed approaches.展开更多
Identifying faces in non-frontal poses presents a significant challenge for face recognition(FR)systems.In this study,we delved into the impact of yaw pose variations on these systems and devised a robust method for d...Identifying faces in non-frontal poses presents a significant challenge for face recognition(FR)systems.In this study,we delved into the impact of yaw pose variations on these systems and devised a robust method for detecting faces across a wide range of angles from 0°to±90°.We initially selected the most suitable feature vector size by integrating the Dlib,FaceNet(Inception-v2),and“Support Vector Machines(SVM)”+“K-nearest neighbors(KNN)”algorithms.To train and evaluate this feature vector,we used two datasets:the“Labeled Faces in the Wild(LFW)”benchmark data and the“Robust Shape-Based FR System(RSBFRS)”real-time data,which contained face images with varying yaw poses.After selecting the best feature vector,we developed a real-time FR system to handle yaw poses.The proposed FaceNet architecture achieved recognition accuracies of 99.7%and 99.8%for the LFW and RSBFRS datasets,respectively,with 128 feature vector dimensions and minimum Euclidean distance thresholds of 0.06 and 0.12.The FaceNet+SVM and FaceNet+KNN classifiers achieved classification accuracies of 99.26%and 99.44%,respectively.The 128-dimensional embedding vector showed the highest recognition rate among all dimensions.These results demonstrate the effectiveness of our proposed approach in enhancing FR accuracy,particularly in real-world scenarios with varying yaw poses.展开更多
In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fi...In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.展开更多
In many automatic face recognition systems, posture constraining is a key factor preventin g them from application. In thi5.paper, a series of strategles. will be described to achieve a system which enables face recog...In many automatic face recognition systems, posture constraining is a key factor preventin g them from application. In thi5.paper, a series of strategles. will be described to achieve a system which enables face recognition under varying pose. These approaches include the multi-view face modeling, the threshold image based face feature detection, the affine transformation based face posture normalization and the template matching based face idelltification. Combining all of these strategies, a face recognition system with the pose invariance is designed successfully. Using a 75MHZ Pentium PC and with a database of 75 individuals, 15 images for each person, and 225 test images with various postures, a very good recognition rate of 96.89% is obtained.展开更多
This paper uses principal component analysis （PCA） to train the face and extract the characteristic value. This approach achieves the purpose of rapid attendance. PCA is an early and important approach for face reco...This paper uses principal component analysis （PCA） to train the face and extract the characteristic value. This approach achieves the purpose of rapid attendance. PCA is an early and important approach for face recognization. It can reduce the dimension of face image space as well as describe the variation characteristics between different face images. The attendance system is a realtime system that requires shorter response time, for which PCA is a best choice. We use histogram equalization to eliminate the noise and improve the performance. With convenient MATLAB GUI visual operation interface, users can click on the corresponding button to implement face recognition tasks.展开更多
Deep neural networks,especially face recognition models,have been shown to be vulnerable to adversarial examples.However,existing attack methods for face recognition systems either cannot attack black-box models,are n...Deep neural networks,especially face recognition models,have been shown to be vulnerable to adversarial examples.However,existing attack methods for face recognition systems either cannot attack black-box models,are not universal,have cumbersome deployment processes,or lack camouflage and are easily detected by the human eye.In this paper,we propose an adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles.To achieve visual camouflage,we use a generative adversarial network(GAN).The scale of the generative network of GAN is increased to balance the performance conflict between concealment and adversarial behavior,the perceptual loss function based on VGG19 is used to constrain the color style and enhance GAN’s learning ability,and the fine-grained meta-learning adversarial attack strategy is used to carry out black-box attacks.Sufficient visualization results demonstrate that compared with existing methods,the proposed method can generate samples with camouflage and adversarial characteristics.Meanwhile,extensive quantitative experiments show that the generated samples have a high attack success rate against black-box models.展开更多
The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.H...The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.However,one’s negative psychology is often hidden,and it is difficult to detect and effectively intervene before the tragedy.How to effectively identify students with suicidal tendencies in order to prevent tragedies has aroused extensive research and discussion among the government,academia and the public.Through investigation and research,it is found that the current popular computer cutting-edge technologies such as artificial intelligence and computer vision can be well used for human emotion recognition and behavior prediction,and put into use in schools as a mental health auxiliary diagnosis and treatment system,thus effectively reducing the suicide rate on campus.The scenario assumes that machine learning can be used to deduce the risk of psychological problems in human samples by analyzing the frequency of negative emotions in facial expressions.Based on this,this paper proposes an effective solution for campus suicide prediction,and designs a set of auxiliary diagnosis and treatment system based on campus monitoring network system for suicide behavior prediction and student mental health analysis.Through preliminary experimental analysis and verification,the suicide psychological auxiliary diagnosis and treatment system has achieved good results in face recognition success rate,emotion recognition success rate and behavior prediction success rate.With the input of more experimental data and the increase of self-training time,the prediction system will perform better.展开更多
The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.H...The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.However,one's negative psychology is often hidden,and it is difficult to detect and effectively intervene before the tragedy.How to effectively identify students with suicidal tendencies in order to prevent tragedies has aroused extensive research and discussion among the government,academia and the public.Through investigation and research,it is found that the current popular computer cutting-edge technologies such as artificial intelligence and computer vision can be well used for human emotion recognition and behavior prediction,and put into use in schools as a mental health auxiliary diagnosis and treatment system,thus effectively reducing the suicide rate on campus.The scenario assumes that machine learning can be used to deduce the risk of psychological problems in human samples by analyzing the frequency of negative emotions in facial expressions.Based on this,this paper proposes an effective solution for campus suicide prediction,and designs a set of auxiliary diagnosis and treatment system based on campus monitoring network system for suicide behavior prediction and student mental health analysis.Through preliminary experimental analysis and verification,the suicide psychological auxiliary diagnosis and treatment system has achieved good results in face recognition success rate,emotion recognition success rate and behavior prediction success rate.With the input of more experimental data and the increase of self-training time,the prediction system will perform better.展开更多
Deep neural networks(DNNs)are widely adopted in daily life and the security problems of DNNs have drawn attention from both scientific researchers and industrial engineers.Many related works show that DNNs are vulnera...Deep neural networks(DNNs)are widely adopted in daily life and the security problems of DNNs have drawn attention from both scientific researchers and industrial engineers.Many related works show that DNNs are vulnerable to adversarial examples that are generated with subtle perturbation to original images in both digital domain and physical domain.As a most common application of DNNs,face recognition systems are likely to cause serious consequences if they are attacked by the adversarial examples.In this paper,we implement an adversarial attack system for face recognition in both digital domain that generates adversarial face images to fool the recognition system,and physical domain that generates customized glasses to fool the system when a person wears the glasses.Experiments show that our system attacks face recognition systems effectively.Furthermore,our system could misguide the recognition system to identify a person wearing the customized glasses as a certain target.We hope this research could help raise the attention of artificial intelligence security and promote building robust recognition systems.展开更多
In this paper, we propose a video searching system that utilizes face recognition as searching indexing feature. As the applications of video cameras have great increase in recent years, face recognition makes a perfe...In this paper, we propose a video searching system that utilizes face recognition as searching indexing feature. As the applications of video cameras have great increase in recent years, face recognition makes a perfect fit for searching targeted individuals within the vast amount of video data. However, the performance of such searching depends on the quality of face images recorded in the video signals. Since the surveillance video cameras record videos without fixed postures for the object, face occlusion is very common in everyday video. The proposed system builds a model for occluded faces using fuzzy principal component analysis(FPCA), and reconstructs the human faces with the available information. Experimental results show that the system has very high efficiency in processing the real life videos, and it is very robust to various kinds of face occlusions. Hence it can relieve people reviewers from the front of the monitors and greatly enhances the efficiency as well. The proposed system has been installed and applied in various environments and has already demonstrated its power by helping solving real cases.展开更多
With the continuous expansion of urban rail transit network, the traditional intelligent gate passing technology is difficult to meet the needs of passengers for urban rail transit. Technologies such as face recogniti...With the continuous expansion of urban rail transit network, the traditional intelligent gate passing technology is difficult to meet the needs of passengers for urban rail transit. Technologies such as face recognition and credit payment can well solve this problem. Through the innovative technology research and pilot practice research on the scientific research project "multimodal biometrics + credit payment" led by S metro, this paper summarizes and reviews the project organization, development process and technical route, refines the project results, and prospects and plans the application of the project scientific research results in the follow-up engineering projects of S metro.展开更多
In principal component analysis （PCA） algorithms for face recognition, to reduce the influence of the eigenvectors which relate to the changes of the illumination on abstract features, a modified PCA （MPCA） algori...In principal component analysis （PCA） algorithms for face recognition, to reduce the influence of the eigenvectors which relate to the changes of the illumination on abstract features, a modified PCA （MPCA） algorithm is proposed. The method is based on the idea of reducing the influence of the eigenvectors associated with the large eigenvalues by normalizing the feature vector element by its corresponding standard deviation. The Yale face database and Yale face database B are used to verify the method. The simulation results show that, for front face and even under the condition of limited variation in the facial poses, the proposed method results in better performance than the conventional PCA and linear discriminant analysis （LDA） approaches, and the computational cost remains the same as that of the PCA, and much less than that of the LDA.展开更多
With the aim of extracting the features of face images in face recognition, a new method of face recognition by fusing global features and local features is presented. The global features are extracted using principal...With the aim of extracting the features of face images in face recognition, a new method of face recognition by fusing global features and local features is presented. The global features are extracted using principal component analysis （PCA）. Active appearance model （AAM） locates 58 facial fiducial points, from which 17 points are characterized as local features using the Gabor wavelet transform （GWT）. Normalized global match degree （local match degree） can be obtained by global features （local features） of the probe image and each gallery image. After the fusion of normalized global match degree and normalized local match degree, the recognition result is the class that included the gallery image corresponding to the largest fused match degree. The method is evaluated by the recognition rates over two face image databases （AR and SJTU-IPPR）. The experimental results show that the method outperforms PCA and elastic bunch graph matching （EBGM）. Moreover, it is effective and robust to expression, illumination and pose variation in some degree.展开更多
文摘This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this system can be updated via our custom-built standalone android app and automatic restarting of the training and recognition process with an updated database. Using our proposed algorithm, a real-time face recognition accuracy of 78.40% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 98.05% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px have been achieved using the LRD200 database containing 200 images per person. With 100 images per person in the database (LRD100) the achieved accuracies are 60.60% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 95% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px respectively. A facial deflection of about 30</span></span></span><span><span><span><span><span style="color:#4F4F4F;font-family:-apple-system, " font-size:16px;white-space:normal;background-color:#ffffff;"="">°</span></span><span> on either side from the front face showed an average face recognition precision of 72.25%-81.85%. This face recognition system can be employed for law enforcement purposes, where the surveillance camera captures a low-resolution image because of the distance of a person from the camera. It can also be used as a surveillance system in airports, bus stations, etc., to reduce the risk of possible criminal threats.</span></span></span></span>
基金This work is supported by the National Key Research and Development Program of China under Grant(No.2016YFB1000302)the National Natural Science Foundation of China under Grant(No.61832020).
文摘With the rapid development of artificial intelligence,face recognition systems are widely used in daily lives.Face recognition applications often need to process large amounts of image data.Maintaining the accuracy and low latency is critical to face recognition systems.After analyzing the two-tier architecture“client-cloud”face recognition systems,it is found that these systems have high latency and network congestion when massive recognition requirements are needed to be responded,and it is very inconvenient and inefficient to deploy and manage relevant applications on the edge of the network.This paper proposes a flexible and efficient edge computing accelerated architecture.By offloading part of the computing tasks to the edge server closer to the data source,edge computing resources are used for image preprocessing to reduce the number of images to be transmitted,thus reducing the network transmission overhead.Moreover,the application code does not need to be rewritten and can be easily migrated to the edge server.We evaluate our schemes based on the open source Azure IoT Edge,and the experimental results show that the three-tier architecture“Client-Edge-Cloud”face recognition system outperforms the state-of-art face recognition systems in reducing the average response time.
基金the financial support from Natural Science Foundation of Gansu Province(Nos.22JR5RA217,22JR5RA216)Lanzhou Science and Technology Program(No.2022-2-111)+1 种基金Lanzhou University of Arts and Sciences School Innovation Fund Project(No.XJ2022000103)Lanzhou College of Arts and Sciences 2023 Talent Cultivation Quality Improvement Project(No.2023-ZL-jxzz-03)。
文摘Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.
文摘In recent work,adversarial stickers are widely used to attack face recognition(FR)systems in the physical world.However,it is difficult to evaluate the performance of physical attacks because of the lack of volunteers in the experiment.In this paper,a simple attack method called incomplete physical adversarial attack(IPAA)is proposed to simulate physical attacks.Different from the process of physical attacks,when an IPAA is conducted,a photo of the adversarial sticker is embedded into a facial image as the input to attack FR systems,which can obtain results similar to those of physical attacks without inviting any volunteers.The results show that IPAA has a higher similarity with physical attacks than digital attacks,indicating that IPAA is able to evaluate the performance of physical attacks.IPAA is effective in quantitatively measuring the impact of the sticker location on the results of attacks.
文摘Face recognition has emerged as one of the most prominent applications of image analysis and under-standing,gaining considerable attention in recent years.This growing interest is driven by two key factors:its extensive applications in law enforcement and the commercial domain,and the rapid advancement of practical technologies.Despite the significant advancements,modern recognition algorithms still struggle in real-world conditions such as varying lighting conditions,occlusion,and diverse facial postures.In such scenarios,human perception is still well above the capabilities of present technology.Using the systematic mapping study,this paper presents an in-depth review of face detection algorithms and face recognition algorithms,presenting a detailed survey of advancements made between 2015 and 2024.We analyze key methodologies,highlighting their strengths and restrictions in the application context.Additionally,we examine various datasets used for face detection/recognition datasets focusing on the task-specific applications,size,diversity,and complexity.By analyzing these algorithms and datasets,this survey works as a valuable resource for researchers,identifying the research gap in the field of face detection and recognition and outlining potential directions for future research.
基金supported by National Natural Science Foundation of China(61901071,61871062,61771082,U20A20157)Science and Natural Science Foundation of Chongqing,China(cstc2020jcyjzdxmX0024)+6 种基金University Innovation Research Group of Chongqing(CXQT20017)Program for Innovation Team Building at Institutions of Higher Education in Chongqing(CXTDX201601020)Natural Science Foundation of Chongqing,China(CSTB2022NSCQ-MSX0600)Youth Innovation Group Support Program of ICE Discipline of CQUPT(SCIE-QN-2022-04)Chongqing Municipal Technology Innovation and Application Development Special Key Project(cstc2020jscxdxwtBX0053)China Postdoctoral Science Foundation Project,China(2022MD723723)Chongqing Postdoctoral Research Project Special Funding,China(2023CQBSHTB3092)。
文摘The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer and the device layer.Besides,previous research fails to consider the facial characteristics including occluded and unoccluded parts.To solve the above problems,we put forward a device-edge collaborative occluded face recognition method based on cross-domain feature fusion.Specifically,the device-edge collaborative face recognition architecture gets the utmost out of maximizes device and edge resources for real-time occluded face recognition.Then,a cross-domain facial feature fusion method is presented which combines both the explicit domain and the implicit domain facial.Furthermore,a delay-optimized edge recognition task scheduling method is developed that comprehensively considers the task load,computational power,bandwidth,and delay tolerance constraints of the edge.This method can dynamically schedule face recognition tasks and minimize recognition delay while ensuring recognition accuracy.The experimental results show that the proposed method achieves an average gain of about 21%in recognition latency,while the accuracy of the face recognition task is basically the same compared to the baseline method.
文摘Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.
基金supported by the Natural Science Foundation of Shandong Province ( ZR2014FM039)the National Natural Science Foundation of China ( 61771293)
文摘Face recognition has been a hot-topic in the field of pattern recognition where feature extraction and classification play an important role. However, convolutional neural network （CNN） and local binary pattern （LBP） can only extract single features of facial images, and fail to select the optimal classifier. To deal with the problem of classifier parameter optimization, two structures based on the support vector machine （SVM） optimized by artificial bee colony （ABC） algorithm are proposed to classify CNN and LBP features separately. In order to solve the single feature problem, a fusion system based on CNN and LBP features is proposed. The facial features can be better represented by extracting and fusing the global and local information of face images. We achieve the goal by fusing the outputs of feature classifiers. Explicit experimental results on Olivetti Research Laboratory （ORL） and face recognition technology （FERET） databases show the superiority of the proposed approaches.
基金funding for the project,excluding research publication,from the Board of Research in Nuclear Sciences(BRNS)under Grant Number 59/14/05/2019/BRNS.
文摘Identifying faces in non-frontal poses presents a significant challenge for face recognition(FR)systems.In this study,we delved into the impact of yaw pose variations on these systems and devised a robust method for detecting faces across a wide range of angles from 0°to±90°.We initially selected the most suitable feature vector size by integrating the Dlib,FaceNet(Inception-v2),and“Support Vector Machines(SVM)”+“K-nearest neighbors(KNN)”algorithms.To train and evaluate this feature vector,we used two datasets:the“Labeled Faces in the Wild(LFW)”benchmark data and the“Robust Shape-Based FR System(RSBFRS)”real-time data,which contained face images with varying yaw poses.After selecting the best feature vector,we developed a real-time FR system to handle yaw poses.The proposed FaceNet architecture achieved recognition accuracies of 99.7%and 99.8%for the LFW and RSBFRS datasets,respectively,with 128 feature vector dimensions and minimum Euclidean distance thresholds of 0.06 and 0.12.The FaceNet+SVM and FaceNet+KNN classifiers achieved classification accuracies of 99.26%and 99.44%,respectively.The 128-dimensional embedding vector showed the highest recognition rate among all dimensions.These results demonstrate the effectiveness of our proposed approach in enhancing FR accuracy,particularly in real-world scenarios with varying yaw poses.
文摘In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.
文摘In many automatic face recognition systems, posture constraining is a key factor preventin g them from application. In thi5.paper, a series of strategles. will be described to achieve a system which enables face recognition under varying pose. These approaches include the multi-view face modeling, the threshold image based face feature detection, the affine transformation based face posture normalization and the template matching based face idelltification. Combining all of these strategies, a face recognition system with the pose invariance is designed successfully. Using a 75MHZ Pentium PC and with a database of 75 individuals, 15 images for each person, and 225 test images with various postures, a very good recognition rate of 96.89% is obtained.
基金Supported by Higher School Science and Technology Innovation Fund Project(2013160)Changzhi College Teaching Reform Fund Project(JY201503)
文摘This paper uses principal component analysis （PCA） to train the face and extract the characteristic value. This approach achieves the purpose of rapid attendance. PCA is an early and important approach for face recognization. It can reduce the dimension of face image space as well as describe the variation characteristics between different face images. The attendance system is a realtime system that requires shorter response time, for which PCA is a best choice. We use histogram equalization to eliminate the noise and improve the performance. With convenient MATLAB GUI visual operation interface, users can click on the corresponding button to implement face recognition tasks.
基金the National Key Research and Development Program of China(No.2022ZD0210500)the National Natural Science Foundation of China(Nos.61972067,U21A20491,and 62103437)the Dalian Outstanding Youth Science Foundation(No.2022RJ01)。
文摘Deep neural networks,especially face recognition models,have been shown to be vulnerable to adversarial examples.However,existing attack methods for face recognition systems either cannot attack black-box models,are not universal,have cumbersome deployment processes,or lack camouflage and are easily detected by the human eye.In this paper,we propose an adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles.To achieve visual camouflage,we use a generative adversarial network(GAN).The scale of the generative network of GAN is increased to balance the performance conflict between concealment and adversarial behavior,the perceptual loss function based on VGG19 is used to constrain the color style and enhance GAN’s learning ability,and the fine-grained meta-learning adversarial attack strategy is used to carry out black-box attacks.Sufficient visualization results demonstrate that compared with existing methods,the proposed method can generate samples with camouflage and adversarial characteristics.Meanwhile,extensive quantitative experiments show that the generated samples have a high attack success rate against black-box models.
文摘The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.However,one’s negative psychology is often hidden,and it is difficult to detect and effectively intervene before the tragedy.How to effectively identify students with suicidal tendencies in order to prevent tragedies has aroused extensive research and discussion among the government,academia and the public.Through investigation and research,it is found that the current popular computer cutting-edge technologies such as artificial intelligence and computer vision can be well used for human emotion recognition and behavior prediction,and put into use in schools as a mental health auxiliary diagnosis and treatment system,thus effectively reducing the suicide rate on campus.The scenario assumes that machine learning can be used to deduce the risk of psychological problems in human samples by analyzing the frequency of negative emotions in facial expressions.Based on this,this paper proposes an effective solution for campus suicide prediction,and designs a set of auxiliary diagnosis and treatment system based on campus monitoring network system for suicide behavior prediction and student mental health analysis.Through preliminary experimental analysis and verification,the suicide psychological auxiliary diagnosis and treatment system has achieved good results in face recognition success rate,emotion recognition success rate and behavior prediction success rate.With the input of more experimental data and the increase of self-training time,the prediction system will perform better.
文摘The phenomenon of teenage campus suicide has become the focus of attention of parents,schools and the society.The causes behind it are extremely complicated,and the root cause is psychological and spiritual problems.However,one's negative psychology is often hidden,and it is difficult to detect and effectively intervene before the tragedy.How to effectively identify students with suicidal tendencies in order to prevent tragedies has aroused extensive research and discussion among the government,academia and the public.Through investigation and research,it is found that the current popular computer cutting-edge technologies such as artificial intelligence and computer vision can be well used for human emotion recognition and behavior prediction,and put into use in schools as a mental health auxiliary diagnosis and treatment system,thus effectively reducing the suicide rate on campus.The scenario assumes that machine learning can be used to deduce the risk of psychological problems in human samples by analyzing the frequency of negative emotions in facial expressions.Based on this,this paper proposes an effective solution for campus suicide prediction,and designs a set of auxiliary diagnosis and treatment system based on campus monitoring network system for suicide behavior prediction and student mental health analysis.Through preliminary experimental analysis and verification,the suicide psychological auxiliary diagnosis and treatment system has achieved good results in face recognition success rate,emotion recognition success rate and behavior prediction success rate.With the input of more experimental data and the increase of self-training time,the prediction system will perform better.
基金This work is supported in part by the National Natural Science Foundation of China under Grant 61902082,U1636215the Guangdong Province Key research and Development Plan under Grant 2019B010136003.
文摘Deep neural networks(DNNs)are widely adopted in daily life and the security problems of DNNs have drawn attention from both scientific researchers and industrial engineers.Many related works show that DNNs are vulnerable to adversarial examples that are generated with subtle perturbation to original images in both digital domain and physical domain.As a most common application of DNNs,face recognition systems are likely to cause serious consequences if they are attacked by the adversarial examples.In this paper,we implement an adversarial attack system for face recognition in both digital domain that generates adversarial face images to fool the recognition system,and physical domain that generates customized glasses to fool the system when a person wears the glasses.Experiments show that our system attacks face recognition systems effectively.Furthermore,our system could misguide the recognition system to identify a person wearing the customized glasses as a certain target.We hope this research could help raise the attention of artificial intelligence security and promote building robust recognition systems.
基金supported by the National Natural Science Foundation of China(No.61502256)
文摘In this paper, we propose a video searching system that utilizes face recognition as searching indexing feature. As the applications of video cameras have great increase in recent years, face recognition makes a perfect fit for searching targeted individuals within the vast amount of video data. However, the performance of such searching depends on the quality of face images recorded in the video signals. Since the surveillance video cameras record videos without fixed postures for the object, face occlusion is very common in everyday video. The proposed system builds a model for occluded faces using fuzzy principal component analysis(FPCA), and reconstructs the human faces with the available information. Experimental results show that the system has very high efficiency in processing the real life videos, and it is very robust to various kinds of face occlusions. Hence it can relieve people reviewers from the front of the monitors and greatly enhances the efficiency as well. The proposed system has been installed and applied in various environments and has already demonstrated its power by helping solving real cases.
文摘With the continuous expansion of urban rail transit network, the traditional intelligent gate passing technology is difficult to meet the needs of passengers for urban rail transit. Technologies such as face recognition and credit payment can well solve this problem. Through the innovative technology research and pilot practice research on the scientific research project "multimodal biometrics + credit payment" led by S metro, this paper summarizes and reviews the project organization, development process and technical route, refines the project results, and prospects and plans the application of the project scientific research results in the follow-up engineering projects of S metro.
文摘In principal component analysis （PCA） algorithms for face recognition, to reduce the influence of the eigenvectors which relate to the changes of the illumination on abstract features, a modified PCA （MPCA） algorithm is proposed. The method is based on the idea of reducing the influence of the eigenvectors associated with the large eigenvalues by normalizing the feature vector element by its corresponding standard deviation. The Yale face database and Yale face database B are used to verify the method. The simulation results show that, for front face and even under the condition of limited variation in the facial poses, the proposed method results in better performance than the conventional PCA and linear discriminant analysis （LDA） approaches, and the computational cost remains the same as that of the PCA, and much less than that of the LDA.
文摘With the aim of extracting the features of face images in face recognition, a new method of face recognition by fusing global features and local features is presented. The global features are extracted using principal component analysis （PCA）. Active appearance model （AAM） locates 58 facial fiducial points, from which 17 points are characterized as local features using the Gabor wavelet transform （GWT）. Normalized global match degree （local match degree） can be obtained by global features （local features） of the probe image and each gallery image. After the fusion of normalized global match degree and normalized local match degree, the recognition result is the class that included the gallery image corresponding to the largest fused match degree. The method is evaluated by the recognition rates over two face image databases （AR and SJTU-IPPR）. The experimental results show that the method outperforms PCA and elastic bunch graph matching （EBGM）. Moreover, it is effective and robust to expression, illumination and pose variation in some degree.
