Learning to represent 2D human face with mathematical model

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of pixels.The authors attempt to learn a continuous surface representation for face image with explicit function.First,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function element.Further,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of EmFace.The authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C datasets.Visualisation results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other factors.Furthermore,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

Generating animatable 3D cartoon faces from single portraits

Background With the development of virtual reality(VR)technology,there is a growing need for customized 3D avatars.However,traditional methods for 3D avatar modeling are either time-consuming or fail to retain the similarity to the person being modeled.This study presents a novel framework for generating animatable 3D cartoon faces from a single portrait image.Methods First,we transferred an input real-world portrait to a stylized cartoon image using StyleGAN.We then proposed a two-stage reconstruction method to recover a 3D cartoon face with detailed texture.Our two-stage strategy initially performs coarse estimation based on template models and subsequently refines the model by nonrigid deformation under landmark supervision.Finally,we proposed a semantic-preserving face-rigging method based on manually created templates and deformation transfer.Conclusions Compared with prior arts,the qualitative and quantitative results show that our method achieves better accuracy,aesthetics,and similarity criteria.Furthermore,we demonstrated the capability of the proposed 3D model for real-time facial animation.

Advancing Wound Filling Extraction on 3D Faces:An Auto-Segmentation and Wound Face Regeneration Approach

Facial wound segmentation plays a crucial role in preoperative planning and optimizing patient outcomes in various medical applications.In this paper,we propose an efficient approach for automating 3D facial wound segmentation using a two-stream graph convolutional network.Our method leverages the Cir3D-FaIR dataset and addresses the challenge of data imbalance through extensive experimentation with different loss functions.To achieve accurate segmentation,we conducted thorough experiments and selected a high-performing model from the trainedmodels.The selectedmodel demonstrates exceptional segmentation performance for complex 3D facial wounds.Furthermore,based on the segmentation model,we propose an improved approach for extracting 3D facial wound fillers and compare it to the results of the previous study.Our method achieved a remarkable accuracy of 0.9999993% on the test suite,surpassing the performance of the previous method.From this result,we use 3D printing technology to illustrate the shape of the wound filling.The outcomes of this study have significant implications for physicians involved in preoperative planning and intervention design.By automating facial wound segmentation and improving the accuracy ofwound-filling extraction,our approach can assist in carefully assessing and optimizing interventions,leading to enhanced patient outcomes.Additionally,it contributes to advancing facial reconstruction techniques by utilizing machine learning and 3D bioprinting for printing skin tissue implants.Our source code is available at https://github.com/SIMOGroup/WoundFilling3D.

A Framework for Driver DrowsinessMonitoring Using a Convolutional Neural Network and the Internet of Things

One of the major causes of road accidents is sleepy drivers.Such accidents typically result in fatalities and financial losses and disadvantage other road users.Numerous studies have been conducted to identify the driver’s sleepiness and integrate it into a warning system.Most studies have examined how the mouth and eyelids move.However,this limits the system’s ability to identify drowsiness traits.Therefore,this study designed an Accident Detection Framework(RPK)that could be used to reduce road accidents due to sleepiness and detect the location of accidents.The drowsiness detectionmodel used three facial parameters:Yawning,closed eyes(blinking),and an upright head position.This model used a Convolutional Neural Network(CNN)consisting of two phases.The initial phase involves video processing and facial landmark coordinate detection.The second phase involves developing the extraction of frame-based features using normalization methods.All these phases used OpenCV and TensorFlow.The dataset contained 5017 images with 874 open eyes images,850 closed eyes images,723 open-mouth images,725 closed-mouth images,761 sleepy-head images,and 1084 non-sleepy head images.The dataset of 5017 images was divided into the training set with 4505 images and the testing set with 512 images,with a ratio of 90:10.The results showed that the RPK design could detect sleepiness by using deep learning techniques with high accuracy on all three parameters;namely 98%for eye blinking,96%for mouth yawning,and 97%for head movement.Overall,the test results have provided an overview of how the developed RPK prototype can accurately identify drowsy drivers.These findings will have a significant impact on the improvement of road users’safety and mobility.

Participatory Forest Management and Gender Inclusiveness within the Community Forest Management Groups of Bhutan

Community forest management groups (CFMGs) in Bhutan exhibit participatory forest management practices that recognize the importance of community’s collective participation in the management of natural forest resources. This approach involves the community in the stewardship of designated forest areas and resources to ensure sustainable livelihoods and realization of forest conservation objectives. The increase of CFMGs in the country has been successful. However, research on the extent of gender-inclusive participation in CFMGs is either insufficient or missing vis-à-vis the allocation of decision-making power. Therefore, this study analyzes the factors influencing gender participation in CFMGs and their integration into decision-making processes. Primary data were collected from 12 study sites spanning 4 regions, complemented by secondary data from the Forest Department. Regression models were used to identify factors significantly influencing CFMG member participation in decision-making. The empirical results of this study reveal that gender is a significant factor influencing participation in CFMG decision-making. The study concludes that there is insufficient participation of women members in decision-making processes. Therefore, consideration of gender should be included in the development phase of the CFMG policy in addition to promoting awareness of inequity between gender and the promotion of leadership roles for women in CFMGs.

Primary Cutaneous Leiomyosarcoma of the Face: A Rare Tumor that Is Difficult to Diagnose

Leiomyosarcoma is a rare malignant tumour of the lower limbs. Its differential histological diagnosis is difficult and is made in the presence of young scar tissue, leimyoma, dermatofibroma, melanoma, rabdomyosarcoma, sarcomatoid carcinoma, fibroxantoma, Darrier Ferrand dermatofibrosarcoma and myofibroblastic tumours. Treatment is essentially surgical, with margins of 3 to 5 centimetres. We report two observations of tumours localised to the face, including one case of a known leiomyosarcoma and another case initially diagnosed as a leiomyosarcoma which turned out to be a cellular myofibroma with no sign of malignancy after several readings. The aim of this work is to review the literature on this pathology while highlighting the diagnostic and therapeutic difficulties. Conclusion: A rare smooth muscle tumour with a high risk of local recurrence in the event of incomplete treatment, leiomyosarcoma in its dermal component is preferentially located in the head and neck. Its treatment is exclusively surgical and highly mutilating.

Refined mathematical model for the breaching of concrete-face sand-gravel dams due to overtopping failure

Overtopping is one of the main reasons for the breaching of concrete-face sand-gravel dams(CFSGDs).In this study,a refined mathematical model was established based on the characteristics of the overtopping breaching of CFSGDs.The model characteristics were as follows:(1)Based on the Renormailzation Group(RNG)k-εturbulence theory and volume of fluid(VOF)method,the turbulent characteristics of the dam-break flow were simulated,and the erosion surface of the water and soil was tracked;(2)In consideration of the influence of the change in the sediment content on the dam-break flow,the dam material transport equation,which could reflect the characteristics of particle settlement and entrainment motion,was used to simulate the erosion process of the sand gravels;(3)Based on the bending moment balance method,a failure equation of the concrete face slab under dead weight and water load was established.The proposed model was verified through a case study on the failure of the Gouhou CFSGD.The results showed that the proposed model could well simulate the erosion mode of the special vortex flow of the CFSGD scouring the support body of the concrete face slab inward and reflect the mutual coupling relationship between the dam-break flow,sand gravels,and concrete face slabs.Compared with the measured values,the relative errors of the peak discharge,final breach average width,dam breaching duration,and maximum failure length of the face slab calculated using the proposed model were all less than 12%,thus verifying the rationality of the model.The proposed model was demonstrated to perform better and provide more detailed results than three selected parametric models and three simplified mathematical models.The study results can aid in establishing the risk level and devising early warning strategies for CFSGDs.

The Even-Odd and the Isoelectronicity Rules Applied to Single Covalent Bonds in Ionic, Double-Face-Centered Cubic and Diamond-Like Crystals

Although atom configuration in crystals is precisely known thanks to imaging techniques, there is no experimental way to know the exact location of bonds or charges. Many different representations have been proposed, yet no theory to unify conceptions. The present paper describes methods to derive bonds and charge location in double-face-centered cubic crystals with 4 and 6 atoms per unit cell using two novel rules introduced in earlier works: the even-odd and the isoelectronicity rules. Both of these rules were previously applied to ions, molecules and some solids, and the even-odd rule was also tested on two covalent crystal structures: centered-cubic and single-face-centered cubic crystals. In the present study, the diamond-like structure was subjected to the isoelectronicity rule in order to derive Zinc-blende structures. Rock-salt-like crystals were derived from each other using both rules. These structures represent together more than 230 different crystals. Findings for these structures are threefold: both rules describe a very sure method to obtain valid single covalent-bonded structures;single covalent structures can be used in every case instead of the classical ionic model;covalent bonds and charges positions do not have any relation with the valence number given in the periodic table.

Automated Video-Based Face Detection Using Harris Hawks Optimization with Deep Learning

Face recognition technology automatically identifies an individual from image or video sources.The detection process can be done by attaining facial characteristics from the image of a subject face.Recent developments in deep learning(DL)and computer vision(CV)techniques enable the design of automated face recognition and tracking methods.This study presents a novel Harris Hawks Optimization with deep learning-empowered automated face detection and tracking(HHODL-AFDT)method.The proposed HHODL-AFDT model involves a Faster region based convolution neural network(RCNN)-based face detection model and HHO-based hyperparameter opti-mization process.The presented optimal Faster RCNN model precisely rec-ognizes the face and is passed into the face-tracking model using a regression network(REGN).The face tracking using the REGN model uses the fea-tures from neighboring frames and foresees the location of the target face in succeeding frames.The application of the HHO algorithm for optimal hyperparameter selection shows the novelty of the work.The experimental validation of the presented HHODL-AFDT algorithm is conducted using two datasets and the experiment outcomes highlighted the superior performance of the HHODL-AFDT model over current methodologies with maximum accuracy of 90.60%and 88.08%under PICS and VTB datasets,respectively.

The Relation between Mental Workload and Face Temperature in Flight Simulation

In this research, we study the relationship between mental workload and facial temperature of aircraft participants during a simulated takeoff flight. We conducted experiments to comprehend the correlation between work and facial temperature within the flight simulator. The experiment involved a group of 10 participants who played the role of pilots in a simulated A-320 flight. Six different flying scenarios were designed to simulate normal and emergency situations on airplane takeoff that would occur in different levels of mental workload for the participants. The measurements were workload assessment, face temperatures, and heart rate monitoring. Throughout the experiments, we collected a total of 120 instances of takeoffs, together with over 10 hours of time-series data including heart rate, workload, and face thermal images and temperatures. Comparative analysis of EEG data and thermal image types, revealed intriguing findings. The results indicate a notable inverse relationship between workload and facial muscle temperatures, as well as facial landmark points. The results of this study contribute to a deeper understanding of the physiological effects of workload, as well as practical implications for aviation safety and performance.

Three-dimensional pseudo-dynamic reliability analysis of seismic shield tunnel faces combined with sparse polynomial chaos expansion

To address the seismic face stability challenges encountered in urban and subsea tunnel construction,an efficient probabilistic analysis framework for shield tunnel faces under seismic conditions is proposed.Based on the upper-bound theory of limit analysis,an improved three-dimensional discrete deterministic mechanism,accounting for the heterogeneous nature of soil media,is formulated to evaluate seismic face stability.The metamodel of failure probabilistic assessments for seismic tunnel faces is constructed by integrating the sparse polynomial chaos expansion method(SPCE)with the modified pseudo-dynamic approach(MPD).The improved deterministic model is validated by comparing with published literature and numerical simulations results,and the SPCE-MPD metamodel is examined with the traditional MCS method.Based on the SPCE-MPD metamodels,the seismic effects on face failure probability and reliability index are presented and the global sensitivity analysis(GSA)is involved to reflect the influence order of seismic action parameters.Finally,the proposed approach is tested to be effective by a engineering case of the Chengdu outer ring tunnel.The results show that higher uncertainty of seismic response on face stability should be noticed in areas with intense earthquakes and variation of seismic wave velocity has the most profound influence on tunnel face stability.

Development of a DFN-based probabilistic block theory approach for bench face angle design in open pit mining

In open pit mining,uncontrolled block instabilities have serious social,economic and regulatory consequences,such as casualties,disruption of operation and increased regulation difficulties.For this reason,bench face angle,as one of the controlling parameters associated with block instabilities,should be carefully designed for sustainable mining.This study introduces a discrete fracture network(DFN)-based probabilistic block theory approach for the fast design of the bench face angle.A major advantage is the explicit incorporation of discontinuity size and spatial distribution in the procedure of key blocks testing.The proposed approach was applied to a granite mine in China.First,DFN models were generated from a multi-step modeling procedure to simulate the complex structural characteristics of pit slopes.Then,a modified key blocks searching method was applied to the slope faces modeled,and a cumulative probability of failure was obtained for each sector.Finally,a bench face angle was determined commensurate with an acceptable risk level of stability.The simulation results have shown that the number of hazardous traces exposed on the slope face can be significantly reduced when the suggested bench face angle is adopted,indicating an extremely low risk of uncontrolled block instabilities.

A Comparative Study on the Processing of Emojis and Faces in Human Communication

In the digital era,emojis have enriched the way people communicate and research on emojis explosively increased in recent years.However,few noticed their functions from the neurocognitive perspective,especially their similarities and differences with facial expressions in traditional face-to-face communication.To fill this gap,we conducted a Meta-analysis with 25 independent effect sizes from previous experimental studies.The present study shows that emojis have slight advantages in processing efficiency,which might be attributed to their simplicity in design,namely the omission of complex facial features,but the difference between emoji and face processing is not significant.In addition,emotional valence and experimental methods do not have significant influences,which suggests that emojis are equally effective as human faces in emotional expression.The current research contributes to the knowledge in digital communication and the crucial role played by emojis therein.

Discourse Analysis Based on Face-Threatening Theory-A Case Study of TucaodahuiⅢ

Face and politeness are very important parts in people’s daily communication.But people will violate the principle of politeness for protecting their own face.Therefore,they usually choose to use more humorous words or jocular words to communicate in order to avoid direct contradictions.Starting from the face-threatening acts in the face theory and politeness principle,this paper briefly analyzes the face-threatening acts and its humorous usage in the TucaodahuiⅢ.

基于AHP-TOPSIS的快速掘进工作面作业安全风险评判

对掘进工作面进行作业安全风险评判是矿井安全高效生产的必要条件,更是实现人矿平安的前提。以神东某矿12203主运顺槽快速掘进工作面为研究案例,从作业人员因素(人)、机器设备因素(机)、开采地质因素(环)、安全管理因素(管)等四个维度出发,采用层次分析法(AHP)和优劣解距离法(TOPSIS),分析了掘进工作面作业安全风险因素,建立了作业安全风险评判指标体系,确定了评判指标权重,提出了基于AHP-TOPSIS的快速掘进工作面作业安全风险评判模型。研究结果表明:该掘进工作面作业安全风险评判结果为0.358,安全风险等级为Ⅱ级。综合评判结果可为掘进工作面安全生产管理提供参考依据。

Spoofing Face Detection Using Novel Edge-Net Autoencoder for Security

Recent security applications in mobile technologies and computer sys-tems use face recognition for high-end security.Despite numerous security tech-niques,face recognition is considered a high-security control.Developers fuse and carry out face identification as an access authority into these applications.Still,face identification authentication is sensitive to attacks with a 2-D photo image or captured video to access the system as an authorized user.In the existing spoofing detection algorithm,there was some loss in the recreation of images.This research proposes an unobtrusive technique to detect face spoofing attacks that apply a single frame of the sequenced set of frames to overcome the above-said problems.This research offers a novel Edge-Net autoencoder to select convoluted and dominant features of the input diffused structure.First,this pro-posed method is tested with the Cross-ethnicity Face Anti-spoofing(CASIA),Fetal alcohol spectrum disorders(FASD)dataset.This database has three models of attacks:distorted photographs in printed form,photographs with removed eyes portion,and video attacks.The images are taken with three different quality cameras:low,average,and high-quality real and spoofed images.An extensive experimental study was performed with CASIA-FASD,3 Diagnostic Machine Aid-Digital(DMAD)dataset that proved higher results when compared to existing algorithms.

Face Mask and Social Distance Monitoring via Computer Vision and Deployable System Architecture

The coronavirus(COVID-19)is a lethal virus causing a rapidly infec-tious disease throughout the globe.Spreading awareness,taking preventive mea-sures,imposing strict restrictions on public gatherings,wearing facial masks,and maintaining safe social distancing have become crucial factors in keeping the virus at bay.Even though the world has spent a whole year preventing and curing the disease caused by the COVID-19 virus,the statistics show that the virus can cause an outbreak at any time on a large scale if thorough preventive measures are not maintained accordingly.Tofight the spread of this virus,technologically developed systems have become very useful.However,the implementation of an automatic,robust,continuous,and lightweight monitoring system that can be efficiently deployed on an embedded device still has not become prevalent in the mass community.This paper aims to develop an automatic system to simul-taneously detect social distance and face mask violation in real-time that has been deployed in an embedded system.A modified version of a convolutional neural network,the ResNet50 model,has been utilized to identify masked faces in peo-ple.You Only Look Once(YOLOv3)approach is applied for object detection and the DeepSORT technique is used to measure the social distance.The efficiency of the proposed model is tested on real-time video sequences taken from a video streaming source from an embedded system,Jetson Nano edge computing device,and smartphones,Android and iOS applications.Empirical results show that the implemented model can efficiently detect facial masks and social distance viola-tions with acceptable accuracy and precision scores.

Optimizing Deep Neural Networks for Face Recognition to Increase Training Speed and Improve Model Accuracy

Convolutional neural networks continually evolve to enhance accuracy in addressing various problems,leading to an increase in computational cost and model size.This paper introduces a novel approach for pruning face recognition models based on convolutional neural networks.The proposed method identifies and removes inefficient filters based on the information volume in feature maps.In each layer,some feature maps lack useful information,and there exists a correlation between certain feature maps.Filters associated with these two types of feature maps impose additional computational costs on the model.By eliminating filters related to these categories of feature maps,the reduction of both computational cost and model size can be achieved.The approach employs a combination of correlation analysis and the summation of matrix elements within each feature map to detect and eliminate inefficient filters.The method was applied to two face recognition models utilizing the VGG16 and ResNet50V2 backbone architectures.In the proposed approach,the number of filters removed in each layer varies,and the removal process is independent of the adjacent layers.The convolutional layers of both backbone models were initialized with pre-trained weights from ImageNet.For training,the CASIA-WebFace dataset was utilized,and the Labeled Faces in the Wild(LFW)dataset was employed for benchmarking purposes.In the VGG16-based face recognition model,a 0.74%accuracy improvement was achieved while reducing the number of convolution parameters by 26.85%and decreasing Floating-point operations per second(FLOPs)by 47.96%.For the face recognition model based on the ResNet50V2 architecture,the ArcFace method was implemented.The removal of inactive filters in this model led to a slight decrease in accuracy by 0.11%.However,it resulted in enhanced training speed,a reduction of 59.38%in convolution parameters,and a 57.29%decrease in FLOPs.

An analytical solution for evaluating the safety of an exposed face in a paste backfill stope incorporating the arching phenomenon

In current underground mining, the stability of the exposed backfill face is a basic issue associated with mining design and has been the subject of considerable research in mining safety and efficiency. In this study, an improved analytical solution for evaluating the safety of vertically exposed faces in backfilling was proposed. Based on a differential slice method, the proposed solution emphasizes the arching effect as having the advantages of more rigor and wider scalability. Feasibility of the proposed solution was validated with classic centrifuge results. Good agreement between compared results indicated that the proposed solution skillfully predicts the behavior of the paste centrifuge model. Additionally, calculation of exposed face safety in sequential filling was presented. The proposed solution has practical significance in mine backfill design.

基于AHP-TOPSIS的煤矿采掘工作面风险评价

为实现对风险因素的评估和管控的目的,构建了管理、环境、技术、设施、人员5个一级指标及28个二级指标的采掘工作面风险评价指标体系,建立了AHP-TOPSIS评价模型,并结合煤矿现场实际情况进行采掘风险评价。研究结果表明,影响袁店二矿采掘安全风险因素最显著的是安全生产投入、煤炭自燃、安全技术措施针对性、排水系统设置、安全风险意识,符合实际情况,说明AHP-TOPSIS计算得出煤矿采掘工作面风险评价可靠性较高。