Based on particle filter framework,a robust tracker is proposed for tracking multiple faces of people moving in a scene.Although most existing algorithms are able to track human face well in controlled environments,th...Based on particle filter framework,a robust tracker is proposed for tracking multiple faces of people moving in a scene.Although most existing algorithms are able to track human face well in controlled environments,they usually fail when human face appearance changes significantly or it is sheltered.To solve this problem,we propose a method using color,contour and texture information of human face together for tracking.Firstly,we use the color and contour model to track human faces in initial images and extract pixels belonging to human face color.Then these pixels are used to form a training set for setting up texture model on eigenspace representations.The two models then work together in following tracking.To reflect changes in human face appearance,update methods are also proposed for the two models including an adaptive-factor by which the texture model can be updated much more effectively when the human face's texture or rotation changes dramatically.Experiment results show that the proposed method is able to track human faces well under large appearance rotation changes,as well as in case of total occlusion by similar color objects.展开更多
To reduce the vision problems caused by improper sitting posture,the research group used Raspberry Pi as the main controller for a multifunctional sitting posture detector with functions such as sitting posture detect...To reduce the vision problems caused by improper sitting posture,the research group used Raspberry Pi as the main controller for a multifunctional sitting posture detector with functions such as sitting posture detection,face positioning,cloud monitoring,etc.UUsing tech-nologies or algorithms such as machine vision and convolutional neural networks,our design can realize the user’s sitting posture error detec-tion,such as left,right,low head position,or forward body position with alarming,so that the user can maintain the appropriate sitting posture.展开更多
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...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.展开更多
Non-face-to-face psychological counseling systems rely on network technologies to anonymize information regard-ing client identity.However,these systems often face challenges concerning voice data leaks and the subopt...Non-face-to-face psychological counseling systems rely on network technologies to anonymize information regard-ing client identity.However,these systems often face challenges concerning voice data leaks and the suboptimal communication of the client’s non-verbal expressions,such as facial cues,to the counselor.This study proposes a metaverse-based psychological counseling system designed to enhance client identity protection while ensuring efficient information delivery to counselors during non-face-to-face counseling.The proposed systemincorporates a voicemodulation function that instantlymodifies/masks the client’s voice to safeguard their identity.Additionally,it employs real-time client facial expression recognition using an ensemble of decision trees to mirror the client’s non-verbal expressions through their avatar in the metaverse environment.The system is adaptable for use on personal computers and smartphones,offering users the flexibility to access metaverse-based psychological counseling across diverse environments.The performance evaluation of the proposed system confirmed that the voice modulation and real-time facial expression replication consistently achieve an average speed of 48.32 frames per second or higher,even when tested on the least powerful smartphone configurations.Moreover,a total of 550 actual psychological counseling sessions were conducted,and the average satisfaction rating reached 4.46 on a 5-point scale.This indicates that clients experienced improved identity protection compared to conventional non-face-to-face metaverse counseling approaches.Additionally,the counselor successfully addressed the challenge of conveying non-verbal cues from clients who typically struggled with non-face-to-face psychological counseling.The proposed systemholds significant potential for applications in interactive discussions and educational activities in the metaverse.展开更多
We present a novel approach for automatically detecting and tracking facial landmarks acrossposesandexpressionsfromin-the-wild monocular video data,e.g.,You Tube videos and smartphone recordings.Our method does not re...We present a novel approach for automatically detecting and tracking facial landmarks acrossposesandexpressionsfromin-the-wild monocular video data,e.g.,You Tube videos and smartphone recordings.Our method does not require any calibration or manual adjustment for new individual input videos or actors.Firstly,we propose a method of robust 2D facial landmark detection across poses,by combining shape-face canonical-correlation analysis with a global supervised descent method.Since 2D regression-based methods are sensitive to unstable initialization,and the temporal and spatial coherence of videos is ignored,we utilize a coarse-todense 3D facial expression reconstruction method to refine the 2D landmarks.On one side,we employ an in-the-wild method to extract the coarse reconstruction result and its corresponding texture using the detected sparse facial landmarks,followed by robust pose,expression,and identity estimation.On the other side,to obtain dense reconstruction results,we give a face tracking flow method that corrects coarse reconstruction results and tracks weakly textured areas;this is used to iteratively update the coarse face model.Finally,a dense reconstruction result is estimated after it converges.Extensive experiments on a variety of video sequences recorded by ourselves or downloaded from You Tube show the results of facial landmark detection and tracking under various lighting conditions,for various head poses and facial expressions.The overall performance and a comparison with state-of-art methods demonstrate the robustness and effectiveness of our method.展开更多
A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics tr...A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.展开更多
文摘Based on particle filter framework,a robust tracker is proposed for tracking multiple faces of people moving in a scene.Although most existing algorithms are able to track human face well in controlled environments,they usually fail when human face appearance changes significantly or it is sheltered.To solve this problem,we propose a method using color,contour and texture information of human face together for tracking.Firstly,we use the color and contour model to track human faces in initial images and extract pixels belonging to human face color.Then these pixels are used to form a training set for setting up texture model on eigenspace representations.The two models then work together in following tracking.To reflect changes in human face appearance,update methods are also proposed for the two models including an adaptive-factor by which the texture model can be updated much more effectively when the human face's texture or rotation changes dramatically.Experiment results show that the proposed method is able to track human faces well under large appearance rotation changes,as well as in case of total occlusion by similar color objects.
文摘To reduce the vision problems caused by improper sitting posture,the research group used Raspberry Pi as the main controller for a multifunctional sitting posture detector with functions such as sitting posture detection,face positioning,cloud monitoring,etc.UUsing tech-nologies or algorithms such as machine vision and convolutional neural networks,our design can realize the user’s sitting posture error detec-tion,such as left,right,low head position,or forward body position with alarming,so that the user can maintain the appropriate sitting posture.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2023R349)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.This study is supported via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2023/R/1444).
文摘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.
基金supported by“Regional Innovation Strategy(RIS)”through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(MOE)(2021RIS-004)supported by the Technology Development Program(S3230339)funded by the Ministry of SMEs and Startups(MSS,Korea).
文摘Non-face-to-face psychological counseling systems rely on network technologies to anonymize information regard-ing client identity.However,these systems often face challenges concerning voice data leaks and the suboptimal communication of the client’s non-verbal expressions,such as facial cues,to the counselor.This study proposes a metaverse-based psychological counseling system designed to enhance client identity protection while ensuring efficient information delivery to counselors during non-face-to-face counseling.The proposed systemincorporates a voicemodulation function that instantlymodifies/masks the client’s voice to safeguard their identity.Additionally,it employs real-time client facial expression recognition using an ensemble of decision trees to mirror the client’s non-verbal expressions through their avatar in the metaverse environment.The system is adaptable for use on personal computers and smartphones,offering users the flexibility to access metaverse-based psychological counseling across diverse environments.The performance evaluation of the proposed system confirmed that the voice modulation and real-time facial expression replication consistently achieve an average speed of 48.32 frames per second or higher,even when tested on the least powerful smartphone configurations.Moreover,a total of 550 actual psychological counseling sessions were conducted,and the average satisfaction rating reached 4.46 on a 5-point scale.This indicates that clients experienced improved identity protection compared to conventional non-face-to-face metaverse counseling approaches.Additionally,the counselor successfully addressed the challenge of conveying non-verbal cues from clients who typically struggled with non-face-to-face psychological counseling.The proposed systemholds significant potential for applications in interactive discussions and educational activities in the metaverse.
基金supported by the Harbin Institute of Technology Scholarship Fund 2016the National Centre for Computer Animation,Bournemouth University
文摘We present a novel approach for automatically detecting and tracking facial landmarks acrossposesandexpressionsfromin-the-wild monocular video data,e.g.,You Tube videos and smartphone recordings.Our method does not require any calibration or manual adjustment for new individual input videos or actors.Firstly,we propose a method of robust 2D facial landmark detection across poses,by combining shape-face canonical-correlation analysis with a global supervised descent method.Since 2D regression-based methods are sensitive to unstable initialization,and the temporal and spatial coherence of videos is ignored,we utilize a coarse-todense 3D facial expression reconstruction method to refine the 2D landmarks.On one side,we employ an in-the-wild method to extract the coarse reconstruction result and its corresponding texture using the detected sparse facial landmarks,followed by robust pose,expression,and identity estimation.On the other side,to obtain dense reconstruction results,we give a face tracking flow method that corrects coarse reconstruction results and tracks weakly textured areas;this is used to iteratively update the coarse face model.Finally,a dense reconstruction result is estimated after it converges.Extensive experiments on a variety of video sequences recorded by ourselves or downloaded from You Tube show the results of facial landmark detection and tracking under various lighting conditions,for various head poses and facial expressions.The overall performance and a comparison with state-of-art methods demonstrate the robustness and effectiveness of our method.
基金supported in part by the National Key R&D Program of China(2021ZD0140407)in part by the National Natural Science Foundation of China(Grant No.U21A20523).
文摘A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.