基于RetinaFace与FaceNet的动态人脸识别系统设计

针对在现有人脸静态识别过程中被识别人需等待配合的问题,文中提出了一种动态人脸识别系统。该系统采用了基于RetinaFace与FaceNet算法的动态人脸检测和识别方法,并进行了优化,以达到高识别精度和实时性的目标。其中,RetinaFace检测采用GhostNet作为骨干网络,使用Adaptive-NMS(Non Max Suppression)非极大值抑制用于人脸框的回归,FaceNet识别采用MobileNetV1作为骨干网络,使用Triplet损失与交叉熵损失结合的联合损失函数用以人脸分类。优化后的算法在检测与识别上具有良好表现,改进RetinaFace算法在WiderFace数据集下检测精度为93.35%、90.84%和80.43%,FPS(Frames Per Second)可达53 frame·s^(-1)。动态人脸检测平均检测精度为96%,FPS为21 frame·s^(-1)。当FaceNet阈值设为1.15时,识别率最高达到98.23%。动态识别系统平均识别精度98%,FPS可达20 frame·s^(-1)。实验结果表明,该系统解决了人脸静态识别中需等待配合的问题,具有较高的识别精度与实时性。

Stability analysis of tunnel face reinforced with face bolts

Face bolting has been widely utilized to enhance the stability of tunnel face,particularly in soft soil tunnels.However,the influence of bolt reinforcement and its layout on tunnel face stability has not been systematically studied.Based on the theory of linear elastic mechanics,this study delved into the specific mechanisms of bolt reinforcement on the tunnel face in both horizontal and vertical dimensions.It also identified the primary failure types of bolts.Additionally,a design approach for tunnel face bolts that incorporates spatial layout was established using the limit equilibrium method to enhance the conventional wedge-prism model.The proposed model was subsequently validated through various means,and the specific influence of relevant bolt design parameters on tunnel face stability was analyzed.Furthermore,design principles for tunnel face bolts under different geological conditions were presented.The findings indicate that bolt failure can be categorized into three stages:tensile failure,pullout failure,and comprehensive failure.Increasing cohesion,internal friction angle,bolt density,and overlap length can effectively enhance tunnel face stability.Due to significant variations in stratum conditions,tailored design approaches based on specific failure stages are necessary for bolt design.

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.

A Deep Transfer Learning Approach for Addressing Yaw Pose Variation to Improve Face Recognition Performance

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.

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RetinaFace和FaceNet算法的佩戴口罩人脸识别系统研究

在疫情暴发期间,佩戴口罩已成为一项重要的公共防疫措施。但口罩遮盖会导致基于图像的人脸识别系统识别准确率降低、检测速度变慢。本研究设计了一种基于RetinaFace和FaceNet算法的佩戴口罩人脸识别系统。首先,使用RetinaFace算法训练得到RetinaFace模型,实现人脸关键点定位功能;其次,采用FaceNet算法训练得到FaceNet模型,提取人脸特征向量并构建特征数据库;最后,通过比对待识别人脸特征向量与数据库中向量的欧氏距离,输出识别结果。实验结果表明,该系统在RKNN模型转换后的识别速度超过25 f/s,在数据集Mask-LFW上,特征向量间欧氏距离阈值设定为1.01时,ACC最高达93.78%,AUC为91.03%。该系统满足实时性且具有较高的检测准确率,可满足实验室、公司、工厂或一些公共场所的使用需求。

VanillaFaceNet:一种高精度快速推理的牛脸识别方法

快速精准确定牛只身份对于牛只活体贷款,改善牛只骗保等问题具有重要意义。针对不同牛只面部差异小,FaceNet网络层数深,推理速度较慢,模型分类精度不足等问题,该研究提出了基于FaceNet的牛脸识别方法-VanillaFaceNet。该方法首先将FaceNet的主干特征提取网络替换为极简网络VanillaNet-13并提出动态激活和增强型线性变换的激活函数两种方法提高网络的非线性;然后,提出一种新的DBCA(dual-branch coordinate attention)注意力模块,能够更好地反映不同牛只面部特征之间的差异,从而提高网络的识别精度;最后,针对triplet loss仅能减小牛只类间差异的问题,采用center-triplet loss联合监督来减少牛只类内差异,从而提高了相同牛只身份比对的准确性。基于自建的牛脸数据集对该模型进行训练和测试,试验结果表明,VanillaFaceNet对牛只识别的准确率达到88.21%,每秒传输帧数为26.23帧。与FaceNet、MobileFaceNet、CenterFace、CosFace和ArcFace算法相比,本文算法的识别准确率分别提高了2.99、9.58、6.26、3.85和4.49个百分点,推理速度分别提升了2.67、0.77、0.10、1.28和0.94帧/s。该模型对牛只有较为优秀的识别效果,适于在嵌入式设备上部署,实现了牛只面部识别精度和推理速度之间的平衡。

广角SS-OCT En Face结构投射图揭示未成年人玻璃体早期液化特征

目的:应用广角扫频源光学相干断层扫描成像(swept-source optical coherence tomography,SS-OCT)的en face结构投射图研究玻璃体早期液化特征。方法:使用SS-OCT进行18 mm×18 mm的容积(Cube)扫描,创建并分析健康未成年人(年龄5~18岁)70眼的系列玻璃体en face结构投射图。结果:在未成年人中,视网膜前的玻璃体包含4种液化结构,分别为后皮质前玻璃体囊袋(posterior precortical vitreous pocket,PPVP)、视盘前Martegiani区(the area of Martegiani,AM)、血管前液化裂隙(prevascular vitreous fissures,PVF)和液化池(cistern)。所有研究眼均能检出PPVP、AM和PVF,其中22眼(31.4%)的PPVP和AM连通。41眼(58.6%)可检出液化池,且其年龄大于未检出液化池的个体(P=0.01),液化池的发生与年龄呈正相关(r_(s)=0.315,P=0.008)。液化池的象限空间分布频率依次为颞上(90.2%)、鼻上(58.5%)、颞下(36.6%)、鼻下(24.4%),最常累及颞上象限(P<0.001)。结论:PPVP、AM和PVF是健康人群视网膜前玻璃体早期液化过程中均出现的特征。液化池的发生与年龄呈正相关,最常出现在颞上象限,可能是年龄相关性玻璃体液化变性的结果。

Probabilistic analysis of tunnel face seismic stability in layered rock masses using Polynomial Chaos Kriging metamodel

Face stability is an essential issue in tunnel design and construction.Layered rock masses are typical and ubiquitous;uncertainties in rock properties always exist.In view of this,a comprehensive method,which combines the Upper bound Limit analysis of Tunnel face stability,the Polynomial Chaos Kriging,the Monte-Carlo Simulation and Analysis of Covariance method(ULT-PCK-MA),is proposed to investigate the seismic stability of tunnel faces.A two-dimensional analytical model of ULT is developed to evaluate the virtual support force based on the upper bound limit analysis.An efficient probabilistic analysis method PCK-MA based on the adaptive Polynomial Chaos Kriging metamodel is then implemented to investigate the parameter uncertainty effects.Ten input parameters,including geological strength indices,uniaxial compressive strengths and constants for three rock formations,and the horizontal seismic coefficients,are treated as random variables.The effects of these parameter uncertainties on the failure probability and sensitivity indices are discussed.In addition,the effects of weak layer position,the middle layer thickness and quality,the tunnel diameter,the parameters correlation,and the seismic loadings are investigated,respectively.The results show that the layer distributions significantly influence the tunnel face probabilistic stability,particularly when the weak rock is present in the bottom layer.The efficiency of the proposed ULT-PCK-MA is validated,which is expected to facilitate the engineering design and construction.

基于FACE模型的AADL体系架构模型构建方法

在时间敏感任务关键航空航天等软件系统研制中,FACE(future airborne capability environment)开放架构模型和AADL(architecture analysis&design language)体系架构模型相结合的建模技术正逐渐成为研究热点。因此,提出了基于FACE模型的AADL模型自动构建方法。采用上下文无关文法给出了FACE模型语法结构的形式化定义;给出了FACE模型到AADL模型的映射机制,包括26类FACE模型元素到AADL模型元素的映射规则,并采用图同态理论证明了映射规则的正确性;基于映射规则设计StringTemplate模板和引擎算法,自动构建AADL模型;将4个方面共计12大类FACE模型元素作为实验对象,设计241个FACE模型实例作为测试用例,构建的AADL模型均在OSATE工具中通过验证。所提方法已被实际应用于航空领域,这样避免概要设计阶段和详细设计阶段的重复建模工作。

Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

基于SSD与FaceNet的人脸识别系统设计

人脸识别技术广泛应用于考勤管理、移动支付等智慧建设中。伴随着常态化的口罩干扰,传统人脸识别算法已无法满足实际应用需求,为此,本文利用深度学习模型SSD以及FaceNet模型对人脸识别系统展开设计。首先,为消除现有数据集中亚洲人脸占比小造成的类内间距变化差距不明显的问题,在CAS-IA Web Face公开数据集的基础上对亚洲人脸数据进行扩充;其次,为解决不同口罩样式对特征提取的干扰,使用SSD人脸检测模型与DLIB人脸关键点检测模型提取人脸关键点,并利用人脸关键点与口罩的空间位置关系,额外随机生成不同的口罩人脸,组成混合数据集;最后,在混合数据集上进行模型训练并将训练好的模型移植到人脸识别系统中,进行检测速度与识别精度验证。实验结果表明,系统的实时识别速度达20 fps以上,人脸识别模型准确率在构建的混合数据集中达到97.1%,在随机抽取的部分LFW数据集验证的准确率达99.7%,故而该系统可满足实际应用需求,在一定程度上提高人脸识别的鲁棒性与准确性。

基于YOLO5Face重分布的小尺度人脸检测方法

针对复杂场景下小尺度人脸检测精度较低的问题,提出了一种基于YOLO5Face重分布的小尺度人脸检测方法。方法以YOLO5Face为基础,在网络浅层引入改进的CBAM注意力并对模型计算重分布,提升复杂场景下小尺度人脸检测精度的同时降低模型参数量;采用融合mixup的数据增强方法,充分训练模型小尺度人脸检测分支;依据人脸检测特性,将softmax损失作为分类损失以最大化类间特征的差异。在WiderFace各个子集上的实验结果表明,与主流人脸检测方法相比,改进后的模型满足实时性的同时,小尺度人脸检测精度较高,其中Hard子集检测精度比YOLO5Face提升2个百分点。

Inverse reliability analysis and design for tunnel face stability considering soil spatial variability

The traditional deterministic analysis for tunnel face stability neglects the uncertainties of geotechnical parameters,while the simplified reliability analysis which models the potential uncertainties by means of random variables usually fails to account for soil spatial variability.To overcome these limitations,this study proposes an efficient framework for conducting reliability analysis and reliability-based design(RBD)of tunnel face stability in spatially variable soil strata.The three-dimensional(3D)rotational failure mechanism of the tunnel face is extended to account for the soil spatial variability,and a probabilistic framework is established by coupling the extended mechanism with the improved Hasofer-Lind-Rackwits-Fiessler recursive algorithm(iHLRF)as well as its inverse analysis formulation.The proposed framework allows for rapid and precise reliability analysis and RBD of tunnel face stability.To demonstrate the feasibility and efficacy of the proposed framework,an illustrative case of tunnelling in frictional soils is presented,where the soil's cohesion and friction angle are modelled as two anisotropic cross-correlated lognormal random fields.The results show that the proposed method can accurately estimate the failure probability(or reliability index)regarding the tunnel face stability and can efficiently determine the required supporting pressure for a target reliability index with soil spatial variability being taken into account.Furthermore,this study reveals the impact of various factors on the support pressure,including coefficient of variation,cross-correlation between cohesion and friction angle,as well as autocorrelation distance of spatially variable soil strata.The results also demonstrate the feasibility of using the forward and/or inverse first-order reliability method(FORM)in high-dimensional stochastic problems.It is hoped that this study may provide a practical and reliable framework for determining the stability of tunnels in complex soil strata.

Sparse representation scheme with enhanced medium pixel intensity for face recognition

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.

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.

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.

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.

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.

Face animation based on multiple sources and perspective alignment

Background Face image animation generates a synthetic human face video that harmoniously integrates the identity derived from the source image and facial motion obtained from the driving video.This technology could be beneficial in multiple medical fields,such as diagnosis and privacy protection.Previous studies on face animation often relied on a single source image to generate an output video.With a significant pose difference between the source image and the driving frame,the quality of the generated video is likely to be suboptimal because the source image may not provide sufficient features for the warped feature map.Methods In this study,we propose a novel face-animation scheme based on multiple sources and perspective alignment to address these issues.We first introduce a multiple-source sampling and selection module to screen the optimal source image set from the provided driving video.We then propose an inter-frame interpolation and alignment module to further eliminate the misalignment between the selected source image and the driving frame.Conclusions The proposed method exhibits superior performance in terms of objective metrics and visual quality in large-angle animation scenes compared to other state-of-the-art face animation methods.It indicates the effectiveness of the proposed method in addressing the distortion issues in large-angle animation.