Deepfake technology can be used to replace people’s faces in videos or pictures to show them saying or doing things they never said or did. Deepfake media are often used to extort, defame, and manipulate public opini...Deepfake technology can be used to replace people’s faces in videos or pictures to show them saying or doing things they never said or did. Deepfake media are often used to extort, defame, and manipulate public opinion. However, despite deepfake technology’s risks, current deepfake detection methods lack generalization and are inconsistent when applied to unknown videos, i.e., videos on which they have not been trained. The purpose of this study is to develop a generalizable deepfake detection model by training convoluted neural networks (CNNs) to classify human facial features in videos. The study formulated the research questions: “How effectively does the developed model provide reliable generalizations?” A CNN model was trained to distinguish between real and fake videos using the facial features of human subjects in videos. The model was trained, validated, and tested using the FaceForensiq++ dataset, which contains more than 500,000 frames and subsets of the DFDC dataset, totaling more than 22,000 videos. The study demonstrated high generalizability, as the accuracy of the unknown dataset was only marginally (about 1%) lower than that of the known dataset. The findings of this study indicate that detection systems can be more generalizable, lighter, and faster by focusing on just a small region (the human face) of an entire video.展开更多
Air gun arrays are often used in marine energy exploration and marine geological surveys.The study of the single bubble dynamics and multibubbles produced by air guns interacting with each other is helpful in understa...Air gun arrays are often used in marine energy exploration and marine geological surveys.The study of the single bubble dynamics and multibubbles produced by air guns interacting with each other is helpful in understanding pressure signals.We used the van der Waals air gun model to simulate the wavelets of a sleeve gun of various offsets and arrival angles.Several factors were taken into account,such as heat transfer,the thermodynamically open quasi-static system,the vertical rise of the bubble,and air gun post throttling.Marine vertical cables are located on the seafloor,but hydrophones are located in seawater and are far away from the air gun array vertically.This situation conforms to the acquisition conditions of the air gun far-field wavelet and thus avoids the problems of ship noise,ocean surges,and coupling.High-quality 3D wavelet data of air gun arrays were collected during a vertical cable test in the South China Sea in 2017.We proposed an evaluation method of multidimensional facial features,including zeropeak amplitude,peak-peak amplitude,bubble period,primary-to-bubble ratio,frequency spectrum,instantaneous amplitude,instantaneous phase,and instantaneous frequency,to characterize the 3D air gun wave field.The match between the facial features in the field and simulated data provides confidence for the use of the van der Waals air gun model to predict air gun wavelet and facial features to evaluate air gun array.展开更多
An efficient algorithm for facial features extractions is proposed. The facial features we segment are the two eyes, nose and mouth. The algorithm is based on an improved Gabor wavelets edge detector, morphological ap...An efficient algorithm for facial features extractions is proposed. The facial features we segment are the two eyes, nose and mouth. The algorithm is based on an improved Gabor wavelets edge detector, morphological approach to detect the face region and facial features regions, and an improved T-shape face mask to locate the extract location of facial features. The experimental results show that the proposed method is robust against facial expression, illumination, and can be also effective if the person wearing glasses, and so on.展开更多
In this paper, a facial feature extracting method is proposed to transform three-dimension (3D) head images of infants with deformational plagiocephaly for assessment of asymmetry. The features of 3D point clouds of...In this paper, a facial feature extracting method is proposed to transform three-dimension (3D) head images of infants with deformational plagiocephaly for assessment of asymmetry. The features of 3D point clouds of an infant's cranium can be identified by local feature analysis and a two-phase k-means classification algorithm. The 3D images of infants with asymmetric cranium can then be aligned to the same pose. The mirrored head model obtained from the symmetry plane is compared with the original model for the measurement of asymmetry. Numerical data of the cranial volume can be reviewed by a pediatrician to adjust the treatment plan. The system can also be used to demonstrate the treatment progress.展开更多
Active Shape Model (ASM) is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis (PCA) to statistically model the variabil...Active Shape Model (ASM) is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis (PCA) to statistically model the variability in the training set of example shapes. Independent Component Analysis (ICA) has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.展开更多
Precise facial feature extraction is essential to the high-level face recognition and expression analysis. This paper presents a novel method for the real-time geometric facial feature extraction from live video. In t...Precise facial feature extraction is essential to the high-level face recognition and expression analysis. This paper presents a novel method for the real-time geometric facial feature extraction from live video. In this paper, the input image is viewed as a weighted graph. The segmentation of the pixels corresponding to the edges of facial components of the mouth, eyes, brows, and nose is implemented by means of random walks on the weighted graph. The graph has an 8-connected lattice structure and the weight value associated with each edge reflects the likelihood that a random walker will cross that edge. The random walks simulate an anisot- ropic diffusion process that filters out the noise while preserving the facial expression pixels. The seeds for the segmentation are obtained from a color and motion detector. The segmented facial pixels are represented with linked lists in the origi- nal geometric form and grouped into different parts corresponding to facial components. For the convenience of implementing high-level vision, the geometric description of facial component pixels is further decomposed into shape and reg- istration information. Shape is defined as the geometric information that is invariant under the registration transformation, such as translation, rotation, and isotropic scale. Statistical shape analysis is carried out to capture global facial fea- tures where the Procrustes shape distance measure is adopted. A Bayesian ap- proach is used to incorporate high-level prior knowledge of face structure. Experimental results show that the proposed method is capable of real-time extraction of precise geometric facial features from live video. The feature extraction is robust against the illumination changes, scale variation, head rotations, and hand interference.展开更多
The “facial composite” is one of the major fields in the forensic science that helps the criminal investigators to carry out their investigation process. The survey conducted by United States Law Enforcement Agencie...The “facial composite” is one of the major fields in the forensic science that helps the criminal investigators to carry out their investigation process. The survey conducted by United States Law Enforcement Agencies confirms that 80% of the law enforcement agencies use computer automated composite systems whereas Sri Lanka is still far behind in the process of facial composite with lot of inefficiencies in the current manual process. Hence this research introduces a novel approach for the manual facial composite process, while eliminating the inefficiencies of the manual procedure in Sri Lanka. In order to overcome this situation, this study introduces an automated image processing based software solution with 2D facial feature templates targeting the Sri Lankan population. Thus, this was the first ever approach that creates the 2D facial feature templates by incorporating both medically defined indexes and relevant aesthetic aspects. Hence, this research study is comprised of two separate analyses on anthropometric indices and facial feature shapes which were carried out targeting the local population. Subsequently, several evaluation techniques were utilized to evaluate this methodology where we obtained an overall success rate as 70.19%. The ultimate goal of this research study is to provide a system to the law enforcement agencies in order to carry out an efficient and effective facial composite process which can lead to increase the success rate of suspect identification.展开更多
Race classification is a long-standing challenge in the field of face image analysis.The investigation of salient facial features is an important task to avoid processing all face parts.Face segmentation strongly bene...Race classification is a long-standing challenge in the field of face image analysis.The investigation of salient facial features is an important task to avoid processing all face parts.Face segmentation strongly benefits several face analysis tasks,including ethnicity and race classification.We propose a race-classification algorithm using a prior face segmentation framework.A deep convolutional neural network(DCNN)was used to construct a face segmentation model.For training the DCNN,we label face images according to seven different classes,that is,nose,skin,hair,eyes,brows,back,and mouth.The DCNN model developed in the first phase was used to create segmentation results.The probabilistic classification method is used,and probability maps(PMs)are created for each semantic class.We investigated five salient facial features from among seven that help in race classification.Features are extracted from the PMs of five classes,and a new model is trained based on the DCNN.We assessed the performance of the proposed race classification method on four standard face datasets,reporting superior results compared with previous studies.展开更多
In this paper,a novel face recognition method,named as wavelet-curvelet-fractal technique,is proposed. Based on the similarities embedded in the images,we propose to utilize the wave-let-curvelet-fractal technique to ...In this paper,a novel face recognition method,named as wavelet-curvelet-fractal technique,is proposed. Based on the similarities embedded in the images,we propose to utilize the wave-let-curvelet-fractal technique to extract facial features. Thus we have the wavelet’s details in diagonal,vertical,and horizontal directions,and the eight curvelet details at different angles. Then we adopt the Euclidean minimum distance classifier to recognize different faces. Extensive comparison tests on dif-ferent data sets are carried out,and higher recognition rate is obtained by the proposed technique.展开更多
This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical lim...This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical limitations.The proposed method can track the user’s eye movements in real time under normal image resolution and lighting conditions using a regular webcam,without special equipment such as infrared illuminators.After the pre-processing steps used to deal with illumination variations,the pupil center is detected using iterative thresholding by applying geometric constraints.Experimental results show that robustness and speed in determining the pupil’s location in real time for users of various ethnicities,under various lighting conditions,at different distances from the webcam and with standard resolution images.展开更多
文摘Deepfake technology can be used to replace people’s faces in videos or pictures to show them saying or doing things they never said or did. Deepfake media are often used to extort, defame, and manipulate public opinion. However, despite deepfake technology’s risks, current deepfake detection methods lack generalization and are inconsistent when applied to unknown videos, i.e., videos on which they have not been trained. The purpose of this study is to develop a generalizable deepfake detection model by training convoluted neural networks (CNNs) to classify human facial features in videos. The study formulated the research questions: “How effectively does the developed model provide reliable generalizations?” A CNN model was trained to distinguish between real and fake videos using the facial features of human subjects in videos. The model was trained, validated, and tested using the FaceForensiq++ dataset, which contains more than 500,000 frames and subsets of the DFDC dataset, totaling more than 22,000 videos. The study demonstrated high generalizability, as the accuracy of the unknown dataset was only marginally (about 1%) lower than that of the known dataset. The findings of this study indicate that detection systems can be more generalizable, lighter, and faster by focusing on just a small region (the human face) of an entire video.
基金the National Natural Science Foundation of China(Nos.91958206,91858215)the National Key Research and Development Program Pilot Project(Nos.2018YFC1405901,2017YFC0307401)+1 种基金the Fundamental Research Funds for the Central Univer-sities(No.201964016)the Marine Geological Survey Program of China Geological Survey(No.DD20190819)。
文摘Air gun arrays are often used in marine energy exploration and marine geological surveys.The study of the single bubble dynamics and multibubbles produced by air guns interacting with each other is helpful in understanding pressure signals.We used the van der Waals air gun model to simulate the wavelets of a sleeve gun of various offsets and arrival angles.Several factors were taken into account,such as heat transfer,the thermodynamically open quasi-static system,the vertical rise of the bubble,and air gun post throttling.Marine vertical cables are located on the seafloor,but hydrophones are located in seawater and are far away from the air gun array vertically.This situation conforms to the acquisition conditions of the air gun far-field wavelet and thus avoids the problems of ship noise,ocean surges,and coupling.High-quality 3D wavelet data of air gun arrays were collected during a vertical cable test in the South China Sea in 2017.We proposed an evaluation method of multidimensional facial features,including zeropeak amplitude,peak-peak amplitude,bubble period,primary-to-bubble ratio,frequency spectrum,instantaneous amplitude,instantaneous phase,and instantaneous frequency,to characterize the 3D air gun wave field.The match between the facial features in the field and simulated data provides confidence for the use of the van der Waals air gun model to predict air gun wavelet and facial features to evaluate air gun array.
基金Sponsored by the National Natural Science Foundation of China (60772066)
文摘An efficient algorithm for facial features extractions is proposed. The facial features we segment are the two eyes, nose and mouth. The algorithm is based on an improved Gabor wavelets edge detector, morphological approach to detect the face region and facial features regions, and an improved T-shape face mask to locate the extract location of facial features. The experimental results show that the proposed method is robust against facial expression, illumination, and can be also effective if the person wearing glasses, and so on.
文摘In this paper, a facial feature extracting method is proposed to transform three-dimension (3D) head images of infants with deformational plagiocephaly for assessment of asymmetry. The features of 3D point clouds of an infant's cranium can be identified by local feature analysis and a two-phase k-means classification algorithm. The 3D images of infants with asymmetric cranium can then be aligned to the same pose. The mirrored head model obtained from the symmetry plane is compared with the original model for the measurement of asymmetry. Numerical data of the cranial volume can be reviewed by a pediatrician to adjust the treatment plan. The system can also be used to demonstrate the treatment progress.
文摘Active Shape Model (ASM) is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis (PCA) to statistically model the variability in the training set of example shapes. Independent Component Analysis (ICA) has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.
基金the National Natural Science Foundation of China (Grant No. 60672071)the Ministry of Science and Technology (Grant No. 2005CCA04400)the Ministry of Education (Grant No. NCET-05-0534)
文摘Precise facial feature extraction is essential to the high-level face recognition and expression analysis. This paper presents a novel method for the real-time geometric facial feature extraction from live video. In this paper, the input image is viewed as a weighted graph. The segmentation of the pixels corresponding to the edges of facial components of the mouth, eyes, brows, and nose is implemented by means of random walks on the weighted graph. The graph has an 8-connected lattice structure and the weight value associated with each edge reflects the likelihood that a random walker will cross that edge. The random walks simulate an anisot- ropic diffusion process that filters out the noise while preserving the facial expression pixels. The seeds for the segmentation are obtained from a color and motion detector. The segmented facial pixels are represented with linked lists in the origi- nal geometric form and grouped into different parts corresponding to facial components. For the convenience of implementing high-level vision, the geometric description of facial component pixels is further decomposed into shape and reg- istration information. Shape is defined as the geometric information that is invariant under the registration transformation, such as translation, rotation, and isotropic scale. Statistical shape analysis is carried out to capture global facial fea- tures where the Procrustes shape distance measure is adopted. A Bayesian ap- proach is used to incorporate high-level prior knowledge of face structure. Experimental results show that the proposed method is capable of real-time extraction of precise geometric facial features from live video. The feature extraction is robust against the illumination changes, scale variation, head rotations, and hand interference.
文摘The “facial composite” is one of the major fields in the forensic science that helps the criminal investigators to carry out their investigation process. The survey conducted by United States Law Enforcement Agencies confirms that 80% of the law enforcement agencies use computer automated composite systems whereas Sri Lanka is still far behind in the process of facial composite with lot of inefficiencies in the current manual process. Hence this research introduces a novel approach for the manual facial composite process, while eliminating the inefficiencies of the manual procedure in Sri Lanka. In order to overcome this situation, this study introduces an automated image processing based software solution with 2D facial feature templates targeting the Sri Lankan population. Thus, this was the first ever approach that creates the 2D facial feature templates by incorporating both medically defined indexes and relevant aesthetic aspects. Hence, this research study is comprised of two separate analyses on anthropometric indices and facial feature shapes which were carried out targeting the local population. Subsequently, several evaluation techniques were utilized to evaluate this methodology where we obtained an overall success rate as 70.19%. The ultimate goal of this research study is to provide a system to the law enforcement agencies in order to carry out an efficient and effective facial composite process which can lead to increase the success rate of suspect identification.
基金This work was partially supported by a National Research Foundation of Korea(NRF)grant(No.2019R1F1A1062237)under the ITRC(Information Technology Research Center)support program(IITP-2021-2018-0-01431)supervised by the IITP(Institute for Information and Communications Technology Planning and Evaluation)funded by the Ministry of Science and ICT(MSIT),Korea.
文摘Race classification is a long-standing challenge in the field of face image analysis.The investigation of salient facial features is an important task to avoid processing all face parts.Face segmentation strongly benefits several face analysis tasks,including ethnicity and race classification.We propose a race-classification algorithm using a prior face segmentation framework.A deep convolutional neural network(DCNN)was used to construct a face segmentation model.For training the DCNN,we label face images according to seven different classes,that is,nose,skin,hair,eyes,brows,back,and mouth.The DCNN model developed in the first phase was used to create segmentation results.The probabilistic classification method is used,and probability maps(PMs)are created for each semantic class.We investigated five salient facial features from among seven that help in race classification.Features are extracted from the PMs of five classes,and a new model is trained based on the DCNN.We assessed the performance of the proposed race classification method on four standard face datasets,reporting superior results compared with previous studies.
基金Supported by the College of Heilongjiang Province, Electronic Engineering Key Lab Project dzzd200602Heilongjiang Province Educational Bureau Scientific Technology Important Project 11531z18
文摘In this paper,a novel face recognition method,named as wavelet-curvelet-fractal technique,is proposed. Based on the similarities embedded in the images,we propose to utilize the wave-let-curvelet-fractal technique to extract facial features. Thus we have the wavelet’s details in diagonal,vertical,and horizontal directions,and the eight curvelet details at different angles. Then we adopt the Euclidean minimum distance classifier to recognize different faces. Extensive comparison tests on dif-ferent data sets are carried out,and higher recognition rate is obtained by the proposed technique.
文摘This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical limitations.The proposed method can track the user’s eye movements in real time under normal image resolution and lighting conditions using a regular webcam,without special equipment such as infrared illuminators.After the pre-processing steps used to deal with illumination variations,the pupil center is detected using iterative thresholding by applying geometric constraints.Experimental results show that robustness and speed in determining the pupil’s location in real time for users of various ethnicities,under various lighting conditions,at different distances from the webcam and with standard resolution images.