The scale-invariance behavior has been widely observed in English or other phonetic language texts. In the present study, we examine whether the semantic language, Chinese can also show this behavior. Typically, the s...The scale-invariance behavior has been widely observed in English or other phonetic language texts. In the present study, we examine whether the semantic language, Chinese can also show this behavior. Typically, the scale-invariance behavior is examined in the series of character intervals for the four great Chinese novels by a method of detrended fluctuation analysis. We observe that the scale-invariance behavior characterized by a scaling exponent around 0.60 exists in each novel. Moreover, we divide each novel into three parts with equal number of chapters, and we also observe the existence of scale-invariance in the interval series for each part. Interestingly, we find that there is evident difference in the scaling exponents between the first(or second) part and the third part in the novel of A dream of red mansions, and the difference between parts is not evident for the other three novels. Our observation suggests that there are two writing styles in A dream of red mansions, which are consistent with current prevailing view that the first 80 chapters and the last 40 chapters were accomplished by Xueqin Cao and E Gao, respectively. Our method may shed light on the identification of writing styles in written texts.展开更多
Contraposing the need of the robust digital watermark for the copyright protection field, a new digital watermarking algorithm in the non-subsampled contourlet transform (NSCT) domain is proposed. The largest energy...Contraposing the need of the robust digital watermark for the copyright protection field, a new digital watermarking algorithm in the non-subsampled contourlet transform (NSCT) domain is proposed. The largest energy sub-band after NSCT is selected to embed watermark. The watermark is embedded into scaleinvariant feature transform (SIFT) regions. During embedding, the initial region is divided into some cirque sub-regions with the same area, and each watermark bit is embedded into one sub-region. Extensive simulation results and comparisons show that the algorithm gets a good trade-off of invisibility, robustness and capacity, thus obtaining good quality of the image while being able to effectively resist common image processing, and geometric and combo attacks, and normalized similarity is almost all reached.展开更多
A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low freq...A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix (or matching result) reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.展开更多
Analysis and recognition of ancient scripts is a challenging task as these scripts are inscribed on pillars,stones,or leaves.Optical recognition systems can help in preserving,sharing,and accelerate the study of the a...Analysis and recognition of ancient scripts is a challenging task as these scripts are inscribed on pillars,stones,or leaves.Optical recognition systems can help in preserving,sharing,and accelerate the study of the ancient scripts,but lack of standard dataset for such scripts is a major constraint.Although many scholars and researchers have captured and uploaded inscription images on various websites,manual searching,downloading and extraction of these images is tedious and error prone.Web search queries return a vast number of irrelevant results,and manually extracting images for a specific script is not scalable.This paper proposes a novelmultistage system to identify the specific set of script images from a large set of images downloaded from web sources.The proposed system combines the two most important pattern matching techniques-Scale Invariant Feature Transform(SIFT)and Template matching,in a sequential pipeline,and by using the key strengths of each technique,the system can discard irrelevant images while retaining a specific type of images.展开更多
At sufficiently large Reynolds numbers,turbulence is expected to exhibit scale-invariance in an intermediate("inertial")range of wavenumbers,as shown by power law behavior of the energy spectrum and also by ...At sufficiently large Reynolds numbers,turbulence is expected to exhibit scale-invariance in an intermediate("inertial")range of wavenumbers,as shown by power law behavior of the energy spectrum and also by a constant rate of energy transfer through wavenumber.However,there is an apparent contradiction between the definition of the energy flux(i.e.,the integral of the transfer spectrum)and the observed behavior of the transfer spectrum itself.This is because the transfer spectrum T(k)is invariably found to have a zero-crossing at a single point(at k=k*),implying that the corresponding energy flux cannot have an extended plateau but must instead have a maximum value at k=k*.This behavior was formulated as a paradox and resolved by the introduction of filtered/partitioned transfer spectra,which exploited the symmetries of the triadic interactions(J.Phys.A:Math.Theor.,2008).In this paper we consider the more general implications of that procedure for the spectral energy balance equation,also known as the Lin equation.It is argued that the resulting modified Lin equations(and their corresponding Navier–Stokes equations)offer a new starting point for both numerical and theoretical methods,which may lead to a better understanding of the underlying energy transfer processes in turbulence.In particular the filtered partitioned transfer spectra could provide a basis for a hybrid approach to the statistical closure problem,with the different spectra being tackled using different methods.展开更多
Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform(SIFT) features on 3D mes...Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform(SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis(PCA).Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.展开更多
The scale-invariant feature transform (SIFT) is often applied to extract tie-points for airborne SAR images. When a pair of airborne SAR images differs with look angles obviously, shadow sizes and shapes of same objec...The scale-invariant feature transform (SIFT) is often applied to extract tie-points for airborne SAR images. When a pair of airborne SAR images differs with look angles obviously, shadow sizes and shapes of same objects will differ obviously. In main and slave SAR images, key-points around shadows often match as tie-points, although they are not homologous points. The phenomenon worsens the performance of SIFT on SAR images. On the basis of SIFT, a modified matching method is proposed to decrease the number of incorrect tie-points. High-resolution airborne SAR images are used in Experiments. Experiment results show that the proposed method is very effective to extract correct tie-points for SAR images.展开更多
This paper studies the evolution of crescent-shaped dune under the influence of injected flux. A scaling law and a wind tunnel experiment are carried out for comparison. The experiment incorporates a novel image proce...This paper studies the evolution of crescent-shaped dune under the influence of injected flux. A scaling law and a wind tunnel experiment are carried out for comparison. The experiment incorporates a novel image processing algorithm to recover the evolutionary process. The theoretical and experimental results agree well in the middle stage of dune evolution, but deviate from each other in the initial and final stages, suggesting that the crescent-shaped dune evolution is intrinsically scale-variant and that the crescent shape breaks down under unsaturated condition.展开更多
In this article,a robust,effective,and scale-invariant weighted compact nonlinear scheme(WCNS)is proposed by introducing descaling techniques to the nonlinear weights of the WCNS-Z/D schemes.The new scheme achieves an...In this article,a robust,effective,and scale-invariant weighted compact nonlinear scheme(WCNS)is proposed by introducing descaling techniques to the nonlinear weights of the WCNS-Z/D schemes.The new scheme achieves an essentially non-oscillatory approximation of a discontinuous function(ENO-property),a scaleinvariant property with an arbitrary scale of a function(Si-property),and an optimal order of accuracy with smooth function regardless of the critical point(Cp-property).The classical WCNS-Z/D schemes do not satisfy Si-property intrinsically,which is caused by a loss of sub-stencils’adaptivity in the nonlinear interpolation of a discontinuous function when scaled by a small scale factor.A new nonlinear weight is devised by using an average of the function values and the descaling function,providing the new WCNS schemes(WCNS-Zm/Dm)with many attractive properties.The ENO-property,Si-property and Cp-property of the new WCNS schemes are validated numerically.Results show that the WCNS-Zm/Dm schemes satisfy the ENO-property and Si-property,while only the WCNS-Dm scheme satisfies the Cp-property.In addition,the Gaussian wave problem is solved by using successively refined grids to verify that the optimal order of accuracy of the new schemes can be achieved.Several one-dimensional shock tube problems,and two-dimensional double Mach reflection(DMR)problem and the Riemann IVP problem are simulated to illustrate the ENOproperty and Si-property of the scale-invariant WCNS-Zm/Dm schemes.展开更多
<Abstract>Phase space can be constructed for N equal and distinguishable binary subsystems which are correlated in a scale-invariant manner.In the paper,correlation coefficient and reduced probability are introd...<Abstract>Phase space can be constructed for N equal and distinguishable binary subsystems which are correlated in a scale-invariant manner.In the paper,correlation coefficient and reduced probability are introduced to characterize the scale-invariant correlated binary subsystems.Probabilistic sets for the correlated binary subsys-tems satisfy Leibnitz triangle rule in the sense that the marginal probabilities of N-system are equal to the joint probabilities of the(N-1)-system.For entropic index q=1,nonextensive entropy Sq is shown to be additive in the scale-invariant occupation of phase space.展开更多
Fractional diffusion equation for transport phenomena in fractal media is an integro-partial differential equation. For solving the problem of this kind of equation the invariants of the group of scaling transformatio...Fractional diffusion equation for transport phenomena in fractal media is an integro-partial differential equation. For solving the problem of this kind of equation the invariants of the group of scaling transformations are given and then used for deriving the integro-ordinary differential equation for the scale-invariant solution. With the help of Mellin transform the scale-invariant solution is obtained in terms of Fox functions. And the series and asymptotic representations for the solution are considered.展开更多
Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve sa...Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve satisfactory results.In this paper,we propose a face recognition algorithm that combines the traditional features and deep features of masked faces.For traditional features,we extract Local Binary Pattern(LBP),Scale-Invariant Feature Transform(SIFT)and Histogram of Oriented Gradient(HOG)features from the periocular region,and use the Support Vector Machines(SVM)classifier to perform personal identification.We also propose an improved Convolutional Neural Network(CNN)model Angular Visual Geometry Group Network(A-VGG)to learn deep features.Then we use the decision-level fusion to combine the four features.Comprehensive experiments were carried out on databases of real masked faces and simulated masked faces,including frontal and side faces taken at different angles.Images with motion blur were also tested to evaluate the robustness of the algorithm.Besides,the experiment of matching a masked face with the corresponding full face is accomplished.The experimental results show that the proposed algorithm has state-of-the-art performance in masked face recognition,and the periocular region has rich biological features and high discrimination.展开更多
Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combin...Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combining local spatio-temporal feature and global positional distribution information(PDI) of interest points, a novel motion descriptor is proposed in this paper. The proposed method detects interest points by using an improved interest point detection method. Then, 3-dimensional scale-invariant feature transform(3D SIFT) descriptors are extracted for every interest point. In order to obtain a compact description and efficient computation, the principal component analysis(PCA) method is utilized twice on the 3D SIFT descriptors of single frame and multiple frames. Simultaneously, the PDI of the interest points are computed and combined with the above features. The combined features are quantified and selected and finally tested by using the support vector machine(SVM) recognition algorithm on the public KTH dataset. The testing results have showed that the recognition rate has been significantly improved and the proposed features can more accurately describe human motion with high adaptability to scenarios.展开更多
This paper presents a biologically inspired local image descriptor that combines color and shape features. Compared with previous descriptors, red-cyan cells associated with L, M, and S cones (L for long, M for mediu...This paper presents a biologically inspired local image descriptor that combines color and shape features. Compared with previous descriptors, red-cyan cells associated with L, M, and S cones (L for long, M for medium, and S for short) are used to indicate one of the opponent color channels. Stepping forward from state-of-the-art color feature extraction, we exploit a new approach to compute the color orientation and magnitudes of three opponent color channels, namely, red-green, blue-yellow, and red-cyan, in two-dimensional space. Color orientation is calculated in histograms with magnitude weighting. We linearly concatenate the four-color-opponent-channel histogram and scale-invariant-feamre-transform histogram in the final step. We apply our biologically inspired descriptor to describe the local image feature. Quantitative comparisons with state-of-the-art descriptors demonstrate the significant advantages of maintaining invariance to photometric and geometric changes in image matching, particularly in cases, such as illumination variation and image blurring, where more color contrast information is observed.展开更多
The global context(GC) descriptor is improved for describing interest regions,uses gradient orientation for binning,and thus provides more robust invariance for geometric and photometric transformations.The performanc...The global context(GC) descriptor is improved for describing interest regions,uses gradient orientation for binning,and thus provides more robust invariance for geometric and photometric transformations.The performance of the improved GC(IGC) to image matching is studied through extensive experiments on the Oxford A?ne dataset.Empirical results indicate that the proposed IGC yields quite stable and robust results,signi?cantly outperforms the original GC,and also can outperform the classical scale-invariant feature transform(SIFT) in most of the test cases.By integrating the IGC to the SIFT,the resulting of hybrid SIFT+IGC performs best over all other single descriptors in these experimental evaluations with various geometric transformations.展开更多
Road visual navigation relies on accurate road models.This study was aimed at proposing an improved scale-invariant feature transform(SIFT)algorithm for recovering depth information from farmland road images,which wou...Road visual navigation relies on accurate road models.This study was aimed at proposing an improved scale-invariant feature transform(SIFT)algorithm for recovering depth information from farmland road images,which would provide a reliable path for visual navigation.The mean image of pixel value in five channels(R,G,B,S and V)were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm,for achieving precise location of the feature points and ensuring the uniformity and density of the feature points.The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45ºin eight directions was then treated as the feature vector,and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points.In order to achieve the depth information of farmland road images,the energy method of feature points was used for eliminating the mismatched points.Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48%and 5.6 s,respectively,with the accuracy for depth recovery of-7.17%-2.97%in a certain sight distance.The mean uniformity,time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%,5.0-6.5 s,and higher than 88%,respectively,indicating that performance for achieving the feature points(e.g.,uniformity,matching accuracy,and algorithm real-time)of the improved SIFT algorithm were superior to that of conventional SIFT algorithm.This study provides an important reference for navigation technology of agricultural equipment based on machine vision.展开更多
This paper describes a person identifcation method for a mobile robot which performs specifc person following under dynamic complicated environments like a school canteen where many persons exist.We propose a distance...This paper describes a person identifcation method for a mobile robot which performs specifc person following under dynamic complicated environments like a school canteen where many persons exist.We propose a distance-dependent appearance model which is based on scale-invariant feature transform(SIFT) feature.SIFT is a powerful image feature that is invariant to scale and rotation in the image plane and also robust to changes of lighting condition.However,the feature is weak against afne transformations and the identifcation power will thus be degraded when the pose of a person changes largely.We therefore use a set of images taken from various directions to cope with pose changes.Moreover,the number of SIFT feature matches between the model and an input image will decrease as the person becomes farther away from the camera.Therefore,we also use a distance-dependent threshold.The person following experiment was conducted using an actual mobile robot,and the quality assessment of person identifcation was performed.展开更多
基金Supported by the Innovation and Entrepreneurship Program of Shanghai University of Science and Technology under Grant No.XJ10252127National Natural Science Foundation of China under Grant Nos.11875042 and 11505114
文摘The scale-invariance behavior has been widely observed in English or other phonetic language texts. In the present study, we examine whether the semantic language, Chinese can also show this behavior. Typically, the scale-invariance behavior is examined in the series of character intervals for the four great Chinese novels by a method of detrended fluctuation analysis. We observe that the scale-invariance behavior characterized by a scaling exponent around 0.60 exists in each novel. Moreover, we divide each novel into three parts with equal number of chapters, and we also observe the existence of scale-invariance in the interval series for each part. Interestingly, we find that there is evident difference in the scaling exponents between the first(or second) part and the third part in the novel of A dream of red mansions, and the difference between parts is not evident for the other three novels. Our observation suggests that there are two writing styles in A dream of red mansions, which are consistent with current prevailing view that the first 80 chapters and the last 40 chapters were accomplished by Xueqin Cao and E Gao, respectively. Our method may shed light on the identification of writing styles in written texts.
基金supported by the National Natural Science Foundation of China(61379010)the Natural Science Basic Research Plan in Shaanxi Province of China(2015JM6293)
文摘Contraposing the need of the robust digital watermark for the copyright protection field, a new digital watermarking algorithm in the non-subsampled contourlet transform (NSCT) domain is proposed. The largest energy sub-band after NSCT is selected to embed watermark. The watermark is embedded into scaleinvariant feature transform (SIFT) regions. During embedding, the initial region is divided into some cirque sub-regions with the same area, and each watermark bit is embedded into one sub-region. Extensive simulation results and comparisons show that the algorithm gets a good trade-off of invisibility, robustness and capacity, thus obtaining good quality of the image while being able to effectively resist common image processing, and geometric and combo attacks, and normalized similarity is almost all reached.
基金supported by the National Natural Science Foundation of China (6117212711071002)+1 种基金the Specialized Research Fund for the Doctoral Program of Higher Education (20113401110006)the Innovative Research Team of 211 Project in Anhui University (KJTD007A)
文摘A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix (or matching result) reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.
文摘Analysis and recognition of ancient scripts is a challenging task as these scripts are inscribed on pillars,stones,or leaves.Optical recognition systems can help in preserving,sharing,and accelerate the study of the ancient scripts,but lack of standard dataset for such scripts is a major constraint.Although many scholars and researchers have captured and uploaded inscription images on various websites,manual searching,downloading and extraction of these images is tedious and error prone.Web search queries return a vast number of irrelevant results,and manually extracting images for a specific script is not scalable.This paper proposes a novelmultistage system to identify the specific set of script images from a large set of images downloaded from web sources.The proposed system combines the two most important pattern matching techniques-Scale Invariant Feature Transform(SIFT)and Template matching,in a sequential pipeline,and by using the key strengths of each technique,the system can discard irrelevant images while retaining a specific type of images.
文摘At sufficiently large Reynolds numbers,turbulence is expected to exhibit scale-invariance in an intermediate("inertial")range of wavenumbers,as shown by power law behavior of the energy spectrum and also by a constant rate of energy transfer through wavenumber.However,there is an apparent contradiction between the definition of the energy flux(i.e.,the integral of the transfer spectrum)and the observed behavior of the transfer spectrum itself.This is because the transfer spectrum T(k)is invariably found to have a zero-crossing at a single point(at k=k*),implying that the corresponding energy flux cannot have an extended plateau but must instead have a maximum value at k=k*.This behavior was formulated as a paradox and resolved by the introduction of filtered/partitioned transfer spectra,which exploited the symmetries of the triadic interactions(J.Phys.A:Math.Theor.,2008).In this paper we consider the more general implications of that procedure for the spectral energy balance equation,also known as the Lin equation.It is argued that the resulting modified Lin equations(and their corresponding Navier–Stokes equations)offer a new starting point for both numerical and theoretical methods,which may lead to a better understanding of the underlying energy transfer processes in turbulence.In particular the filtered partitioned transfer spectra could provide a basis for a hybrid approach to the statistical closure problem,with the different spectra being tackled using different methods.
基金Project(XDA06020300)supported by the"Strategic Priority Research Program"of the Chinese Academy of SciencesProject(12511501700)supported by the Research on the Key Technology of Internet of Things for Urban Community Safety Based on Video Sensor networks
文摘Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform(SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis(PCA).Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.
基金Supported by the National Key Research and Development Program of China(No.2016YFB0502502)the Special Research and Trial Production Project of Sanya(No.sy17xs0113)
文摘The scale-invariant feature transform (SIFT) is often applied to extract tie-points for airborne SAR images. When a pair of airborne SAR images differs with look angles obviously, shadow sizes and shapes of same objects will differ obviously. In main and slave SAR images, key-points around shadows often match as tie-points, although they are not homologous points. The phenomenon worsens the performance of SIFT on SAR images. On the basis of SIFT, a modified matching method is proposed to decrease the number of incorrect tie-points. High-resolution airborne SAR images are used in Experiments. Experiment results show that the proposed method is very effective to extract correct tie-points for SAR images.
基金funded by the National Natural Science Foundation of China(11402190)the China Postdoctoral Science Foundation(2014M552443)the Natural Science Foundation of Shaanxi Province(2013JQ2001)
文摘This paper studies the evolution of crescent-shaped dune under the influence of injected flux. A scaling law and a wind tunnel experiment are carried out for comparison. The experiment incorporates a novel image processing algorithm to recover the evolutionary process. The theoretical and experimental results agree well in the middle stage of dune evolution, but deviate from each other in the initial and final stages, suggesting that the crescent-shaped dune evolution is intrinsically scale-variant and that the crescent shape breaks down under unsaturated condition.
基金supported by the Hunan Provincial Natural Science Foundation of China(No.2022JJ40539)National Natural Science Foundation of China(No.11972370)National Key Project(No.GJXM92579).
文摘In this article,a robust,effective,and scale-invariant weighted compact nonlinear scheme(WCNS)is proposed by introducing descaling techniques to the nonlinear weights of the WCNS-Z/D schemes.The new scheme achieves an essentially non-oscillatory approximation of a discontinuous function(ENO-property),a scaleinvariant property with an arbitrary scale of a function(Si-property),and an optimal order of accuracy with smooth function regardless of the critical point(Cp-property).The classical WCNS-Z/D schemes do not satisfy Si-property intrinsically,which is caused by a loss of sub-stencils’adaptivity in the nonlinear interpolation of a discontinuous function when scaled by a small scale factor.A new nonlinear weight is devised by using an average of the function values and the descaling function,providing the new WCNS schemes(WCNS-Zm/Dm)with many attractive properties.The ENO-property,Si-property and Cp-property of the new WCNS schemes are validated numerically.Results show that the WCNS-Zm/Dm schemes satisfy the ENO-property and Si-property,while only the WCNS-Dm scheme satisfies the Cp-property.In addition,the Gaussian wave problem is solved by using successively refined grids to verify that the optimal order of accuracy of the new schemes can be achieved.Several one-dimensional shock tube problems,and two-dimensional double Mach reflection(DMR)problem and the Riemann IVP problem are simulated to illustrate the ENOproperty and Si-property of the scale-invariant WCNS-Zm/Dm schemes.
基金the National Natural Science Foundation of China(No.60474069)
文摘<Abstract>Phase space can be constructed for N equal and distinguishable binary subsystems which are correlated in a scale-invariant manner.In the paper,correlation coefficient and reduced probability are introduced to characterize the scale-invariant correlated binary subsystems.Probabilistic sets for the correlated binary subsys-tems satisfy Leibnitz triangle rule in the sense that the marginal probabilities of N-system are equal to the joint probabilities of the(N-1)-system.For entropic index q=1,nonextensive entropy Sq is shown to be additive in the scale-invariant occupation of phase space.
基金Supported by the National Natural Science Foundation of China (10461005)the Department Fund of Science and Technology in Tianjin Higher Education Institutions (20050404).
文摘Fractional diffusion equation for transport phenomena in fractal media is an integro-partial differential equation. For solving the problem of this kind of equation the invariants of the group of scaling transformations are given and then used for deriving the integro-ordinary differential equation for the scale-invariant solution. With the help of Mellin transform the scale-invariant solution is obtained in terms of Fox functions. And the series and asymptotic representations for the solution are considered.
基金Supported by the Postgraduate Research and Practice Innovation Program of Nanjing University of Aeronautics and Astronautics(XCXJH20220318)。
文摘Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve satisfactory results.In this paper,we propose a face recognition algorithm that combines the traditional features and deep features of masked faces.For traditional features,we extract Local Binary Pattern(LBP),Scale-Invariant Feature Transform(SIFT)and Histogram of Oriented Gradient(HOG)features from the periocular region,and use the Support Vector Machines(SVM)classifier to perform personal identification.We also propose an improved Convolutional Neural Network(CNN)model Angular Visual Geometry Group Network(A-VGG)to learn deep features.Then we use the decision-level fusion to combine the four features.Comprehensive experiments were carried out on databases of real masked faces and simulated masked faces,including frontal and side faces taken at different angles.Images with motion blur were also tested to evaluate the robustness of the algorithm.Besides,the experiment of matching a masked face with the corresponding full face is accomplished.The experimental results show that the proposed algorithm has state-of-the-art performance in masked face recognition,and the periocular region has rich biological features and high discrimination.
基金supported by National Natural Science Foundation of China(No.61103123)Scientific Research Foundation for the Returned Overseas Chinese Scholars,State Education Ministry
文摘Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combining local spatio-temporal feature and global positional distribution information(PDI) of interest points, a novel motion descriptor is proposed in this paper. The proposed method detects interest points by using an improved interest point detection method. Then, 3-dimensional scale-invariant feature transform(3D SIFT) descriptors are extracted for every interest point. In order to obtain a compact description and efficient computation, the principal component analysis(PCA) method is utilized twice on the 3D SIFT descriptors of single frame and multiple frames. Simultaneously, the PDI of the interest points are computed and combined with the above features. The combined features are quantified and selected and finally tested by using the support vector machine(SVM) recognition algorithm on the public KTH dataset. The testing results have showed that the recognition rate has been significantly improved and the proposed features can more accurately describe human motion with high adaptability to scenarios.
基金Acknowledgment This study was supported by the National Natural Science Foundation of China (grant 61101155) and the Jilin Province Science and Technology Development Program (20101504).
文摘This paper presents a biologically inspired local image descriptor that combines color and shape features. Compared with previous descriptors, red-cyan cells associated with L, M, and S cones (L for long, M for medium, and S for short) are used to indicate one of the opponent color channels. Stepping forward from state-of-the-art color feature extraction, we exploit a new approach to compute the color orientation and magnitudes of three opponent color channels, namely, red-green, blue-yellow, and red-cyan, in two-dimensional space. Color orientation is calculated in histograms with magnitude weighting. We linearly concatenate the four-color-opponent-channel histogram and scale-invariant-feamre-transform histogram in the final step. We apply our biologically inspired descriptor to describe the local image feature. Quantitative comparisons with state-of-the-art descriptors demonstrate the significant advantages of maintaining invariance to photometric and geometric changes in image matching, particularly in cases, such as illumination variation and image blurring, where more color contrast information is observed.
基金the National Natural Science Foundation of China(Nos.60970109 and 61170228)
文摘The global context(GC) descriptor is improved for describing interest regions,uses gradient orientation for binning,and thus provides more robust invariance for geometric and photometric transformations.The performance of the improved GC(IGC) to image matching is studied through extensive experiments on the Oxford A?ne dataset.Empirical results indicate that the proposed IGC yields quite stable and robust results,signi?cantly outperforms the original GC,and also can outperform the classical scale-invariant feature transform(SIFT) in most of the test cases.By integrating the IGC to the SIFT,the resulting of hybrid SIFT+IGC performs best over all other single descriptors in these experimental evaluations with various geometric transformations.
基金This work was financially supported by the Zhejiang Science and Technology Department Basic Public Welfare Research Project(LGN18F030001)the Major Project of Zhejiang Science and Technology Department(2016C02G2100540).
文摘Road visual navigation relies on accurate road models.This study was aimed at proposing an improved scale-invariant feature transform(SIFT)algorithm for recovering depth information from farmland road images,which would provide a reliable path for visual navigation.The mean image of pixel value in five channels(R,G,B,S and V)were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm,for achieving precise location of the feature points and ensuring the uniformity and density of the feature points.The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45ºin eight directions was then treated as the feature vector,and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points.In order to achieve the depth information of farmland road images,the energy method of feature points was used for eliminating the mismatched points.Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48%and 5.6 s,respectively,with the accuracy for depth recovery of-7.17%-2.97%in a certain sight distance.The mean uniformity,time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%,5.0-6.5 s,and higher than 88%,respectively,indicating that performance for achieving the feature points(e.g.,uniformity,matching accuracy,and algorithm real-time)of the improved SIFT algorithm were superior to that of conventional SIFT algorithm.This study provides an important reference for navigation technology of agricultural equipment based on machine vision.
基金supported by JSPS KAKENHI (No.23700203) and NEDO Intelligent RT Software Project
文摘This paper describes a person identifcation method for a mobile robot which performs specifc person following under dynamic complicated environments like a school canteen where many persons exist.We propose a distance-dependent appearance model which is based on scale-invariant feature transform(SIFT) feature.SIFT is a powerful image feature that is invariant to scale and rotation in the image plane and also robust to changes of lighting condition.However,the feature is weak against afne transformations and the identifcation power will thus be degraded when the pose of a person changes largely.We therefore use a set of images taken from various directions to cope with pose changes.Moreover,the number of SIFT feature matches between the model and an input image will decrease as the person becomes farther away from the camera.Therefore,we also use a distance-dependent threshold.The person following experiment was conducted using an actual mobile robot,and the quality assessment of person identifcation was performed.