Efficient Face Research Articles

Path-based DEA models in multiplier form and returns-to-scale analysis

AbstractData envelopment analysis (DEA) models appear in envelopment and multiplier forms, which are in a primal-dual relationship. In this paper, we derive the general multiplier form of path-based models, encompassing radial, directional distance function, and hyperbolic distance function models as special cases. We investigate the economic interpretation of the multiplier models and uncover the link between shadow profit inefficiency and technical inefficiency provided by path-based models. Using the optimality conditions for the primal-dual pair, we precisely describe the two-way relationship between the optimal solutions of the multiplier model and the supporting hyperplanes of the technology set at the projection. This relationship serves as a mathematical justification for extending one of the early approaches to measuring returns-to-scale (RTS) onto the entire class of path-based models. Moreover, we demonstrate the eligibility of this method by revealing the fact that the set of all strongly efficient benchmarks for the assessed unit in path-based models does not need to belong to a single strongly efficient face of technology set. This finding changes the view on traditional approaches to RTS measurement that rely on supporting hyperplanes encompassing a single strongly efficient face of the technology set. In this new perspective, we propose two methods for RTS measurement. The first is based on the hyperplanes at the projection, and the second method adapts the minimum face method to be suitable for path-based models. Both methods are fully justified and brought to an algorithmic form.

A Research on Two-Stage Facial Occlusion Recognition Algorithm based on CNN

In recent years, pattern recognition has garnered widespread attention, especially in the domain of face recognition. Traditional face recognition methods have certain limitations in unconstrained environments due to factors such as lighting, facial expressions, and poses. Deep learning can be used to address these challenges. This paper proposes a comprehensive approach to face occlusion recognition based on a two-stage Convolutional Neural Network (CNN). Face verification aims at verifying whether two face images belong to the same individual, and it is a more fundamental task compared to face recognition. The process of face recognition essentially involves multiple instances of face verification, sequentially validating different individuals to ultimately determine the corresponding individual for each face. The primary steps in this research include facial detection, image preprocessing, facial landmark localization, facial landmark extraction, feature matching recognition, and 2D image-assisted 3D face reconstruction. A novel two-stage CNN was designed for facial detection and alignment. The first stage of the network is dedicated to the search for facial windows and regressing vector boundaries. The second stage utilizes 2D images to assist in 3D face reconstruction and perform secondary recognition for cases not identified in the first stage. This method demonstrated excellent performance in handling facial occlusions, achieving high accuracy on datasets such as AFW and FDDB. On the test dataset, face recognition accuracy reached 97.3%, surpassing the original network accuracy of 89.1%. This method outperforms traditional algorithms and general CNN approaches. This study achieved efficient face validation and further handling of unrecognized situations, contributing to the enhancement of face recognition system performance.

Real-time Performance Comparison of Face Detection Algorithms using Raspberry Pi

Abstract This study reviewed state-of-the-art face-detection techniques like Haar cascade, Dlib HOG, MTCNN, and MediaPipe; implemented and tested them on Raspberry Pi, and evaluated their accuracy, speed, and frames per second. Overall, the research underscores the practical challenges of face detection, including varying lighting, facial expressions, occlusions, poses, scale of face, and accessories, and provides valuable insights for developers and researchers working on edge AI applications on low-cost edge devices. The study found that the MediaPipe face detection algorithm demonstrated robust performance, even with low-quality images, and showed good efficiency and resource management on the Raspberry Pi. The research emphasized the importance of considering factors like accuracy, speed, and resource efficiency in face detection on edge devices. The findings suggest that MediaPipe is a strong candidate for applications requiring efficient face detection, affordable and versatile platforms like Raspberry Pi. By focusing on the Raspberry Pi, the study offers a unique perspective on the performance of state-of-the-art face detection algorithms in real-world, resource-constrained environments, making it a significant contribution to the field of face recognition and edge computing.

An efficient face and mask detection by embedded device via thermal imaging camera

Abstract Since 87.9% of COVID-19 patients develop a fever symptom, the mandatory wearing of masks, temperature screening, and isolation of individuals with fever are the most import methods for community epidemic prevention. This study develops a thermal imaging thermometer embedded system with face, face mask, and temperature detection capabilities using low-end CPU devices. The hardware includes a Raspberry Pi 4, FLIR Lepton 3.5 LWIR Micro Thermal Camera Module, display screen, and alarm. The system is characterized by its low cost and lightweight design, and it only needs to detect necessary areas around the face area during face mask and temperature detection, effectively avoiding external interference and further enhancing the effectiveness of epidemic prevention. The face detection model is based on the YOLO-Fastest architecture and has been improved, referred to as Pi-fast. In terms of performance on the training and testing sets, our proposed Pi-fast achieves Mean Average Precision (mAP) values of 99.64% and 93.18%, F1 score values of 0.94 and 0.87, and Intersection over Union (IoU)values of 78.07% and 65.98%, respectively. Regarding system performance, the frame rate of FLIR Lepton 3.5 Thermal Camera Module hardware specifications is 8.7 FPS. When using YOLO-Fastest and proposed Pi-fast model for detection on the proposed thermal imaging system, the frame rates are 6.58 FPS and 7.32FPS, respectively. The proposed Pi-fast model outperforms YOLO-Fastest about 0.74 FPS (11.2%). The system can detect objects at a distance of about 7 meters from the lens in thermographic camera with a resolution of only 160×120 pixels, making it suitable for multi-person screening and improving the screening process’s efficiency. The system can effectively perform temperature screening and face mask detection, making it suitable for office buildings, schools, medical clinics, and other public areas. During the severe epidemic period, the proposed thermal imaging embedded system that was actually used for epidemic prevention work at I-Shou University, improving screening efficiency and reducing labour costs.

Diagnosis and Screening of Velocardiofacial Syndrome by Evaluating Facial Photographs Using a Deep Learning-Based Algorithm.

Early detection of rare genetic diseases, including velocardiofacial syndrome (VCFS), is essential for patient well-being. However, their rarity and limited clinical experience of physicians make diagnosis challenging. Deep learning algorithms have emerged as promising tools for efficient and accurate diagnosis. This study investigates the use of a deep learning algorithm to develop a face recognition model for diagnosing VCFS. The study employed publicly available labeled face datasets to train the multitask cascaded convolutional neural networks (MTCNN) model. Subsequently, we examined the binary classification performance for diagnosing VCFS using the most efficient face recognition model. A total of 98 VCFS patients (920 facial photographs) and 91 non-VCFS controls (463 facial photographs) were randomly divided into training and test sets. Additionally, we analyzed whether the classification results matched the known facial phenotype of VCFS. The face recognition model demonstrated high accuracy, ranging from 94% to 99%, depending on the training dataset. The accuracy of the binary classification diagnostic model varied from 81% to 88% when evaluating with photographs taken at various angles, but reached 95% evaluating with frontal photographs only. Gradient-weighted class activation mapping heatmap revealed the high importance level of perinasal and periorbital areas, exhibiting consistency with the conventional facial phenotypes of VCFS. This study shows the feasibility and effectiveness of MTCNN-based model for detecting VCFS solely from facial photographs. The high accuracy underscores the potential of deep learning in aiding early diagnosis of rare genetic diseases, facilitating timely interventions for patient care.

Dense pedestrian face detection in complex environments

To address the problem of dense crowd face detection in complex environments, this paper proposes a face detection model named Deep and Compact Face Detection (DCFD), which adopts an improved lightweight EfficientNetV2 network to replace the backbone network of RetinaFace. A large kernel attention mechanism is introduced to address the face detection task more accurately. The backbone network, an improved efficient channel attention (ECA) mechanism, is added to further improve the algorithm performance. The feature fusion module is an improved neural architecture search feature pyramid network (NAS-FPN) that significantly improves the face detection accuracy in different scenes. To balance the training process of positive and negative samples, we use the focus loss function to replace the traditional cross-entropy loss function. In different environments, the DCFD algorithm has shown efficient face detection performance. This algorithm provides not only a feasible and effective solution for solving the problem of face detection in dense groups but also an important basis for improving the accuracy of face detection models in practical applications.

Efficient face anti-spoofing via head-aware transformer based knowledge distillation with 5 MB model parameters

Although face recognition technology has been applied in many scenarios, it still suffers from many types of presentation attacks, so face anti-spoofing (FAS) becomes a hot topic in computer vision. Recently, vision transformer is recognized as the mainstream architecture for FAS, which always relies on auxiliary information, sophisticated tricks and huge model parameters. Considering that face based identity authentication usually takes place on mobile-like devices, therefore how to design an effective and lightweight model is of great significance. Inspired by the powerful global modeling ability of self-attention and the model compression ability of knowledge distillation, a simple yet effective knowledge distillation approach is proposed for FAS under transformer framework. Our primary idea is to leverage the rich knowledge of a teacher network pre-trained on large-scale face data to guide the learning of a lightweight student network. The main contributions of our method are threefold: (1) Feature- and logits-level distillation are combined to transfer the rich knowledge of teacher to student. (2) A head-aware strategy is proposed to deal with the dimension mismatching issue of middle encoder layers between teacher and student networks, in which a novel attention head correlation matrix is introduced. (3) Our method can bridge the performance gap between teacher and student, and the resulting student network is extremely lightweight with only 5 MB parameters. Extensive experiments are conducted on three public face-spoofing datasets, CASIA-FASD, Replay-Attack and OULU-NPU, the results demonstrate that our method can obtain performance on par with or superior to most FAS methods and outperform many knowledge distillation methods. Meanwhile, the distilled student network achieves excellent performance with 17× fewer parameters and 9× faster inference time compared to the teacher network. The code will be publicly available at https://github.com/Maricle-zhangjun/HaTFAS.

Planning in management: identifying alternative ways of improving performance toward best practices

AbstractPlanning is an important part of the management of organizations, which deals with the setting of targets that guide the actions needed to improve performance. Decision making is at the essence of planning, as it involves the identification of alternative directions for improvement and the selection of a future course of action. Decision makers (DMs) appreciate information on different ways of improving performance toward best practices, so they can make a choice of the plan that is more closely aligned with management in an ex post evaluation of possibilities. This paper responds to the need of providing DMs with a few (manageable) alternatives when planning improvements. The proposed approach is developed within the framework of data envelopment analysis (DEA). Although DEA has been used for planning, there is a gap in the literature in the sense that we can find only a few papers that have the explicit aim of identifying alternatives. In order to deal with this issue, we explore the whole DEA strong efficient frontier through all of its maximal efficient faces, which allows us to handle targets determined by a broad range of reference sets, and then use location theory tools, namely a p‐median problem, for the selection of p representatives that define alternative directions for improvement. Eventually, DMs are provided with a decision‐support tool for planning improvements by learning from the best practices of others, without requiring prior information on preferences.

Augmented Attention: Enhancing Morph Detection in Face Recognition

Face Morphing is a technique that involves blending two or more faces to create new often realistic- looking images. These morphed images are generated or created using morphing techniques or photo manipulation tools pose a significant peril to face recognition systems. In this paper, we proposed a method to improve deep learning based face morphing detection systems to be more robust against face morphing attacks. Leveraging deep learning models and algorithms including MTCNN (Multitask Cascaded Convolutional Neural Network) for efficient face extraction from original and morphed faces with a high accuracy and FaceNet for extracting unified embeddings from the faces. The project aims to push the boundaries of face morphing detection capabilities by leveraging feature combination techniques using cosine distance and SSIM(structural similarity index measure) for identifying the similarity between faces and applying spatial attention mechanism which aims to enhance the feature representation learned by the model by focusing on the most informative parts of the image and training support vector machine classifier and voting classifier using the extracted embeddings significantly helps in building a robust face morphing detection system.

Internet development and green economic efficiency in China: A new perspective of government's dual goal constraints and citizens' green lifestyle

AbstractThe rapid development of the information and communication technologies (ITCs) and the internet is deeply embedded in all aspects of economic life. With its high economic efficiency and significant green attributes, digitalization provides opportunities for promoting a green economy. However, the effects of digitalization and internet development on China's green economic efficiency are understudied. There is also a gap in research on how digitalization and internet development influence Chinese citizens to choose a green lifestyle from the consumer perspective. This article aims to enrich the research in this field by exploring the effects of internet development on green economic efficiency in China. The article further analyses how digitalization and internet development can encourage citizens to choose a green lifestyle. Drawing on panel data from 257 cities in China spanning the period from 2012 to 2020, this article utilizes the entropy method and the SBM‐GML model to assess the correlation between internet development and green economy efficiency. We also employ the basic regression model, system GMM model, mediation effect model and adjustment model to study the impact of internet development on urban green economic efficiency. The study found that internet development and green economic efficiency face constraints that are inherent in the government's dual economic growth and environmental goals and targets. We also found that digitalization and internet development can promote citizens' adoption of green lifestyles through the fostering of citizen environmental concern and green consumption habits. Further analysis shows that internet development has a more pronounced effect on green economic efficiency in eastern cities, large cities, non‐resource‐based cities and cities with higher economic development. These findings provide useful references for developing countries that promote urban green economic efficiency through digitalization and internet development.

Planning improvements through data envelopment analysis (DEA) benchmarking based on a selection of peers

Incorporating preferences on suitable peers into benchmarking analyses may ensure the setting of appropriate targets, which enable designing plans for improving performance that are aligned with management. This paper deals with target setting in situations where decision makers (DMs) have previously made a selection of peer candidates for the benchmarking of a given organization. A first approach is developed within the framework of conventional Data Envelopment Analysis (DEA), which is the technology mostly used in non-parametric frontier analysis. It provides targets from reference sets consisting of peer candidates that span a face of the strong efficient frontier of the production possibility set (PPS). These targets result from solving a DEA-like model, thus preventing from the need to identify all of the maximal efficient faces (MEFs) of the DEA frontier. We also propose a second approach where the convexity in DEA is somehow relaxed to allow additionally for reference sets consisting of candidates that are Pareto-efficient, provided that their convex hull is not dominated by other units. In that sense, the targets found can be seen as representing best practices. This approach broadens the range of alternatives when planning improvements, and may eventually provide closer targets.

ResRetinaFace: an efficient face detection network based on RetinaFace and residual structure

ResRetinaFace: an efficient face detection network based on RetinaFace and residual structure

A Novel Deep Transfer Learning-Based Approach for Face Pose Estimation

Abstract An efficient face recognition system is essential for security and authentication-based applications. However, real-time face recognition systems have a few significant concerns, including face pose orientations. In the last decade, numerous solutions have been introduced to estimate distinct face pose orientations. Nevertheless, these solutions must be adequately addressed for the three main face pose orientations: Yaw, Pitch, and Roll. This paper proposed a novel deep transfer learning-based multitasking approach for solving three integrated tasks, i.e., face detection, landmarks detection, and face pose estimation. The face pose variation vulnerability has been intensely investigated here underlying three modules: image preprocessing, feature extraction module through deep transfer learning, and regression module for estimating the face poses. The experiments are performed on the well-known benchmark dataset Annotated Faces in the Wild (AFW). We evaluate the outcomes of the experiments to reveal that our proposed approach is superior to other recently available solutions.

A Lightweight Face Detector via Bi-Stream Convolutional Neural Network and Vision Transformer

Lightweight convolutional neural networks are widely used for face detection due to their ability to learn local representations through spatial induction bias and translational invariance. However, convolutional face detectors have limitations in detecting faces under challenging conditions like occlusion, blurring, or changes in facial poses, primarily attributed to fixed-size receptive fields and a lack of global modeling. Transformer-based models have advantages on learning global representations but are insensitive to capture local patterns. To address these limitations, we propose an efficient face detector that combines convolutional neural network and transformer architectures. We introduce a bi-stream structure that integrates convolutional neural network and transformer blocks within the backbone network, enabling the preservation of local pattern features and the extraction of global context. To further preserve the local details captured by convolutional neural networks, we propose a feature enhancement convolution block in a hierarchical backbone structure. Additionally, we devise a multiscale feature aggregation module to enhance obscured and blurred facial features. Experimental results demonstrate that our method has achieved improved lightweight face detection accuracy with an average precision of 95.30%, 94.20%, and 87.56% across the easy, medium, and hard subdatasets of WIDER FACE, respectively. Therefore, we believe our method will be a useful supplement to the collection of current artificial intelligence models and benefit the engineering applications of face detection.

Age-Invariant Face Recognition Using FaceNet and Multi-task Cascaded Convolutional Networks (MTCNN)

In an era where face recognition technology serves as a cornerstone for security, surveillance, and human-computer interaction, the persistence of age-related variations in facial appearance presents a significant challenge. This research introduces an innovative solution that amalgamates the capabilities of the FaceNet deep learning model with Multi-task Cascaded Convolutional Networks (MTCNN) to achieve precise and robust face recognition across diverse age groups. Leveraging FaceNet's prowess in extracting distinctive features from facial images and mapping them to a high-dimensional feature space for efficient face matching, our system incorporates MTCNN as a pre-processing step to accurately detect and align faces, effectively mitigating age-related changes in facial geometry. Crucially, this novel approach obviates the need for age-specific databases and age group categorization, rendering it a versatile and practical solution for age-invariant face recognition. Rigorous experimentation on benchmark datasets underscores the system's resilience and accuracy across a broad spectrum of age groups, culminating in state-of-the-art results in age-invariant face recognition. The implications of this proposed approach are profound, promising to fortify security measures and enhance user experiences in applications such as access control, personal identification, and customer service, while ensuring dependable and accurate face recognition, irrespective of an individual's age. Key Words: Face recognition, face aging, generative adversarial networks

Development of Face Recognition System Using Support Vector Machine Algorithm

This research paper describes a face recognition system constructed with the Support Vector Machine (SVM) method. The technique implements the Convolutional Neural Network (CNN) approach for extracting features, which improves the accuracy of recognising faces. The method confirms an efficient and accurate facial recognition procedure by utilising SVM's ability to detect complex patterns within retrieved characteristics. The article explores how the system is implemented and optimised performance, with a focus on obtaining performance in real time. The experimental findings demonstrate the practical application of the SVM-based facial recognition system, emphasising its numerous potential applications in security, the authentication process, as well as interaction between humans and computers. The implementation of CNN for extracting features provides refinement to the system, proving its flexibility to complex face characteristics and confirming its feasibility in actual applications. The results indicate that the suggested system is an effective facial recognition technique. Furthermore, the system is computationally efficient, taking just a few seconds to evaluate an individual face for extracting features and recognition. The system for identifying faces uses modern approaches to enhance both speed and precision, making it a potential option for a variety of applications. Its capacity to swiftly and correctly detect faces in real-time circumstances is a substantial development in facial identification technologies. The system's capability has been comprehensively evaluated, and it satisfies the essential criteria for practical implementation in real-world situations, making it an important addition to the continued development of secure and efficient face recognition systems.

SNResNet: A New Architecture Based on SqNxt Blocks and Rish Activation for Efficient Face Recognition

SNResNet: A New Architecture Based on SqNxt Blocks and Rish Activation for Efficient Face Recognition

A signal detection-based confidence-similarity model of face matching.

Face matching consists of the ability to decide whether two face images (or more) belong to the same person or to different identities. Face matching is crucial for efficient face recognition and plays an important role in applied settings such as passport control and eyewitness memory. However, despite extensive research, the mechanisms that govern face-matching performance are still not well understood. Moreover, to date, many researchers hold on to the belief that match and mismatch conditions are governed by two separate systems, an assumption that likely thwarted the development of a unified model of face matching. The present study outlines a unified unequal variance confidence-similarity signal detection-based model of face-matching performance, one that facilitates the use of receiver operating characteristics (ROC) and confidence-accuracy plots to better understand the relations between match and mismatch conditions, and their relations to factors of confidence and similarity. A binomial feature-matching mechanism is developed to support this signal detection model. The model can account for the presence of both within-identities and between-identities sources of variation in face recognition and explains a myriad of face-matching phenomena, including the match-mismatch dissociation. The model is also capable of generating new predictions concerning the role of confidence and similarity and their intricate relations with accuracy. The new model was tested against six alternative competing models (some postulate discrete rather than continuous representations) in three experiments. Data analyses consisted of hierarchically nested model fitting, ROC curve analyses, and confidence-accuracy plots analyses. All of these provided substantial support in the signal detection-based confidence-similarity model. The model suggests that the accuracy of face-matching performance can be predicted by the degree of similarity/dissimilarity of the depicted faces and the level of confidence in the decision. Moreover, according to the model, confidence and similarity ratings are strongly correlated. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

On the search for efficient face recognition algorithm subject to multiple environmental constraints

From literature, majority of face recognition modules suffer performance challenges when presented with test images acquired under multiple constrained environments (occlusion and varying expressions). The performance of these models further deteriorates as the degree of degradation of the test images increases (relatively higher occlusion level). Deep learning-based face recognition models have attracted much attention in the research community as they are purported to outperform the classical PCA-based methods. Unfortunately their application to real-life problems is limited because of their intensive computational complexity and relatively longer run-times. This study proposes an enhancement of some PCA-based methods (with relatively lower computational complexity and run-time) to overcome the challenges posed to the recognition module in the presence of multiple constraints. The study compared the performance of enhanced classical PCA-based method (HE-GC-DWT-PCA/SVD) to FaceNet algorithm (deep learning method) using expression variant face images artificially occluded at 30% and 40%. The study leveraged on two statistical imputation methods of MissForest and Multiple Imputation by Chained Equations (MICE) for occlusion recovery. From the numerical evaluation results, although the two models achieved the same recognition rate (85.19%) at 30% level of occlusion, the enhanced PCA-based algorithm (HE-GC-DWT-PCA/SVD) outperformed the FaceNet model at 40% occlusion rate, with a recognition rate of 83.33%. Although both Missforest and MICE performed creditably well as de-occlusion mechanisms at higher levels of occlusion, MissForest outperforms the MICE imputation mechanism. MissForest imputation mechanism and the proposed HE-GC-DWT-PCA/SVD algorithm are recommended for occlusion recovery and recognition of multiple constrained test images respectively.

Autistic Individuals Do Not Alter Visual Processing Strategy During Encoding Versus Recognition of Faces: A Hidden Markov Modeling Approach.

Visual face recognition-the ability to encode, discriminate, and recognize the faces of others-is fundamentally supported by eye movements and is a common source of difficulty for autistic individuals. We aimed to evaluate how visual processing strategies (i.e., eye movement patterns) directly support encoding and recognition of faces in autistic and neurotypical (NT) individuals. We used a hidden Markov modeling approach to evaluate the spatiotemporal dynamics of eye movements in autistic (n = 15) and neurotypical (NT) adolescents (n = 17) during a face identity recognition task. We discovered distinct eye movement patterns among all participants, which included a focused and exploratory strategy. When evaluating change in visual processing strategy across encoding and recognition phases, autistic individuals did not shift their eye movement patterns like their NT peers, who shifted to a more exploratory visual processing strategy during recognition. These findings suggest that autistic individuals do not modulate their visual processing strategy across encoding and recognition of faces, which may be an indicator of less efficient face processing.