It is found that in some cases the complete and irreducible scale invariants given by Ref.[1] are not independent. There are some implicit functional relations among them. The scale invariants for two different cases ...It is found that in some cases the complete and irreducible scale invariants given by Ref.[1] are not independent. There are some implicit functional relations among them. The scale invariants for two different cases are calculated. The first case is an arbitrary second order tensor. The second case includes a symmetric tensor, an antisymmetric tensor and a vector. By using the eigentensor notation it is proved that in the first case there are only six independent scale invariants rather than seven as reported in Ref.[1] and in the second case there are only nine independent scale invariants which are less than that obtained in Ref.[1].展开更多
On the basis of scale invariant feature transform(SIFT) descriptors,a novel kind of local invariants based on SIFT sequence scale(SIFT-SS) is proposed and applied to target classification.First of all,the merits o...On the basis of scale invariant feature transform(SIFT) descriptors,a novel kind of local invariants based on SIFT sequence scale(SIFT-SS) is proposed and applied to target classification.First of all,the merits of using an SIFT algorithm for target classification are discussed.Secondly,the scales of SIFT descriptors are sorted by descending as SIFT-SS,which is sent to a support vector machine(SVM) with radial based function(RBF) kernel in order to train SVM classifier,which will be used for achieving target classification.Experimental results indicate that the SIFT-SS algorithm is efficient for target classification and can obtain a higher recognition rate than affine moment invariants(AMI) and multi-scale auto-convolution(MSA) in some complex situations,such as the situation with the existence of noises and occlusions.Moreover,the computational time of SIFT-SS is shorter than MSA and longer than AMI.展开更多
Stable local feature detection is a fundamental component of many stereo vision problems such as 3-D reconstruction, object localization, and object tracking. A robust method for extracting scale-invariant feature poi...Stable local feature detection is a fundamental component of many stereo vision problems such as 3-D reconstruction, object localization, and object tracking. A robust method for extracting scale-invariant feature points is presented. First, the Harris corners in three-level pyramid are extracted. Then, the points detected at the highest level of the pyramid are correctly propagated to the lower level by pyramid based scale invariant (PBSI) method. The corners detected repeatedly in different levels are chosen as final feature points. Finally, the characteristic scale is obtained based on maximum entropy method. The experimental results show that the algorithm has low computation cost, strong antinoise capability, and excellent performance in the presence of significant scale changes.展开更多
Real-world networks exhibit complex topological interactions that pose a significant computational challenge to analyses of such networks.Due to limited resources,there is an urgent need to develop dimensionality redu...Real-world networks exhibit complex topological interactions that pose a significant computational challenge to analyses of such networks.Due to limited resources,there is an urgent need to develop dimensionality reduction techniques that can significantly reduce the structural complexity of initial large-scale networks.In this paper,we propose a subgraph extraction method based on the node centrality measure to reduce the size of the initial network topology.Specifically,nodes with smaller centrality value are removed from the initial network to obtain a subgraph with a smaller size.Our results demonstrate that various real-world networks,including power grids,technology,transportation,biology,social,and language networks,exhibit self-similarity behavior during the reduction process.The present results reveal the selfsimilarity and scale invariance of real-world networks from a different perspective and also provide an effective guide for simplifying the topology of large-scale networks.展开更多
Relative radiometric normalization (RRN) minimizes radiometric differences among images caused by inconsistencies of acquisition conditions rather than changes in surface. Scale invariant feature transform (SIFT) has ...Relative radiometric normalization (RRN) minimizes radiometric differences among images caused by inconsistencies of acquisition conditions rather than changes in surface. Scale invariant feature transform (SIFT) has the ability to automatically extract control points (CPs) and is commonly used for remote sensing images. However, its results are mostly inaccurate and sometimes contain incorrect matching caused by generating a small number of false CP pairs. These CP pairs have high false alarm matching. This paper presents a modified method to improve the performance of SIFT CPs matching by applying sum of absolute difference (SAD) in a different manner for the new optical satellite generation called near-equatorial orbit satellite and multi-sensor images. The proposed method, which has a significantly high rate of correct matches, improves CP matching. The data in this study were obtained from the RazakSAT satellite a new near equatorial satellite system. The proposed method involves six steps: 1) data reduction, 2) applying the SIFT to automatically extract CPs, 3) refining CPs matching by using SAD algorithm with empirical threshold, and 4) calculation of true CPs intensity values over all image’ bands, 5) preforming a linear regression model between the intensity values of CPs locate in reverence and sensed image’ bands, 6) Relative radiometric normalization conducting using regression transformation functions. Different thresholds have experimentally tested and used in conducting this study (50 and 70), by followed the proposed method, and it removed the false extracted SIFT CPs to be from 775, 1125, 883, 804, 883 and 681 false pairs to 342, 424, 547, 706, 547, and 469 corrected and matched pairs, respectively.展开更多
Systems using numerous cameras are emerging in many fields due to their ease of production and reduced cost, and one of the fields where they are expected to be used more actively in the near future is in image-based ...Systems using numerous cameras are emerging in many fields due to their ease of production and reduced cost, and one of the fields where they are expected to be used more actively in the near future is in image-based rendering (IBR). Color correction between views is necessary to use multi-view systems in IBR to make audiences feel comfortable when views are switched or when a free viewpoint video is displayed. Color correction usually involves two steps: the first is to adjust camera parameters such as gain, brightness, and aperture before capture, and the second is to modify captured videos through image processing. This paper deals with the latter, which does not need a color pattern board. The proposed method uses scale invariant feature transform (SIFT) to detect correspondences, treats RGB channels independently, calculates lookup tables with an energy-minimization approach, and corrects captured video with these tables. The experimental results reveal that this approach works well.展开更多
To improve the performance of the scale invariant feature transform ( SIFT), a modified SIFT (M-SIFT) descriptor is proposed to realize fast and robust key-point extraction and matching. In descriptor generation, ...To improve the performance of the scale invariant feature transform ( SIFT), a modified SIFT (M-SIFT) descriptor is proposed to realize fast and robust key-point extraction and matching. In descriptor generation, 3 rotation-invariant concentric-ring grids around the key-point location are used instead of 16 square grids used in the original SIFT. Then, 10 orientations are accumulated for each grid, which results in a 30-dimension descriptor. In descriptor matching, rough rejection mismatches is proposed based on the difference of grey information between matching points. The per- formance of the proposed method is tested for image mosaic on simulated and real-worid images. Experimental results show that the M-SIFT descriptor inherits the SIFT' s ability of being invariant to image scale and rotation, illumination change and affine distortion. Besides the time cost of feature extraction is reduced by 50% compared with the original SIFT. And the rough rejection mismatches can reject at least 70% of mismatches. The results also demonstrate that the performance of the pro- posed M-SIFT method is superior to other improved SIFT methods in speed and robustness.展开更多
Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are genera...Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are generally used to get SIFT descriptors in order to reduce the complexity. The regions which have a similar grayscale level but different hues tend to produce wrong matching results in this case. Therefore, the loss of color information may result in decreasing of matching ratio. An image matching algorithm based on SIFT is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. Experimental results show that the proposed algorithm can effectively differentiate the regions with different colors but the similar grayscale level, and increase the matching ratio of image matching based on SIFT. Furthermore, it does not introduce much complexity than the traditional SIFT.展开更多
Scale Invariant Feature Transform (SIFT) algorithm is a widely used computer vision algorithm that detects and extracts local feature descriptors from images. SIFT is computationally intensive, making it infeasible fo...Scale Invariant Feature Transform (SIFT) algorithm is a widely used computer vision algorithm that detects and extracts local feature descriptors from images. SIFT is computationally intensive, making it infeasible for single threaded im-plementation to extract local feature descriptors for high-resolution images in real time. In this paper, an approach to parallelization of the SIFT algorithm is demonstrated using NVIDIA’s Graphics Processing Unit (GPU). The parallel-ization design for SIFT on GPUs is divided into two stages, a) Algorithm de-sign-generic design strategies which focuses on data and b) Implementation de-sign-architecture specific design strategies which focuses on optimally using GPU resources for maximum occupancy. Increasing memory latency hiding, eliminating branches and data blocking achieve a significant decrease in aver-age computational time. Furthermore, it is observed via Paraver tools that our approach to parallelization while optimizing for maximum occupancy allows GPU to execute memory bound SIFT algorithm at optimal levels.展开更多
To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature ...To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.展开更多
The results of face recognition are often inaccurate due to factors such as illumination,noise intensity,and affine/projection transformation.In response to these problems,the scale invariant feature transformation(SI...The results of face recognition are often inaccurate due to factors such as illumination,noise intensity,and affine/projection transformation.In response to these problems,the scale invariant feature transformation(SIFT) is proposed,but its computational complexity and complication seriously affect the efficiency of the algorithm.In order to solve this problem,SIFT algorithm is proposed based on principal component analysis(PCA) dimensionality reduction.The algorithm first uses PCA algorithm,which has the function of screening feature points,to filter the feature points extracted in advance by the SIFT algorithm;then the high-dimensional data is projected into the low-dimensional space to remove the redundant feature points,thereby changing the way of generating feature descriptors and finally achieving the effect of dimensionality reduction.In this paper,through experiments on the public ORL face database,the dimension of SIFT is reduced to 20 dimensions,which improves the efficiency of face extraction;the comparison of several experimental results is completed and analyzed to verify the superiority of the improved algorithm.展开更多
A general operational protocol which provides permanent macroscopic coherence of the response of any stable complex system put in an ever-changing environment is proposed. It turns out that the coherent response consi...A general operational protocol which provides permanent macroscopic coherence of the response of any stable complex system put in an ever-changing environment is proposed. It turns out that the coherent response consists of two parts: 1) a specific discrete pattern, called by the author homeostatic one, whose characteristics are robust to the statistics of the environment;2) the rest part of the response forms a stationary homogeneous process whose coarse-grained structure obeys universal distribution which turns out to be scale-invariant. It is demonstrated that, for relatively short time series, a measurement, viewed as a solitary operation of coarse-graining, superimposed on the universal distribution results in a rich variety of behaviors ranging from periodic-like to stochastic-like, to a sequences of irregular fractal-like objects and sequences of random-like events. The relevance of the Central Limit theorem applies to the latter case. Yet, its application is still an approximation which holds for relatively short time series and for specific low resolution of the measurement equipment. It is proven that the asymptotic behavior in each and every of the above cases is provided by the recently proven decomposition theorem.展开更多
This paper proposes a new set of 3D rotation scaling and translation invariants of 3D radially shifted Legendre moments. We aim to develop two kinds of transformed shifted Legendre moments: a 3D substituted radial sh...This paper proposes a new set of 3D rotation scaling and translation invariants of 3D radially shifted Legendre moments. We aim to develop two kinds of transformed shifted Legendre moments: a 3D substituted radial shifted Legendre moments (3DSRSLMs) and a 3D weighted radial one (3DWRSLMs). Both are centered on two types of polynomials. In the first case, a new 3D ra- dial complex moment is proposed. In the second case, new 3D substituted/weighted radial shifted Legendremoments (3DSRSLMs/3DWRSLMs) are introduced using a spherical representation of volumetric image. 3D invariants as derived from the sug- gested 3D radial shifted Legendre moments will appear in the third case. To confirm the proposed approach, we have resolved three is- sues. To confirm the proposed approach, we have resolved three issues: rotation, scaling and translation invariants. The result of experi- ments shows that the 3DSRSLMs and 3DWRSLMs have done better than the 3D radial complex moments with and without noise. Sim- ultaneously, the reconstruction converges rapidly to the original image using 3D radial 3DSRSLMs and 3DWRSLMs, and the test of 3D images are clearly recognized from a set of images that are available in Princeton shape benchmark (PSB) database for 3D image.展开更多
The "theory of self-similar oscillatory finite-time singularities" of Sornette reflects accurately the spatio-temporal evolution and trends of development of events and processes in complex systems approaching to th...The "theory of self-similar oscillatory finite-time singularities" of Sornette reflects accurately the spatio-temporal evolution and trends of development of events and processes in complex systems approaching to the singularities, and the effect of prediction for catastrophic events has been tested to be satisfactory. The authors take the contents of the chemical element tungsten as the carrier of positive feedback (or activator) in the ore formation, then try to apply the theory to studying and analyzing the onset and development of ore formation in the Dajishan (大吉山) tungsten ore area, Jiangxi (江西) Province, China. The results of the study show that during the spatio-temporal evolution from outside the ore area to its center, the contents of the chemical element tungsten and their loga- rithmic derivatives (local fractal dimension) manifest an obvious regularity: by way of the process of oscillation and the transition to power-law accelerating growth, they eventually approach the center of ore formation. The regularity makes clear that in the complex ore-forming system of the Dajishan tungsten ore deposit, the chemical element tungsten plays the role of carrier of positive and negative feedback, and by competing with each other, approaches to singularity in finite time by virtue of self-similar log-periodic oscillations and succeeded by power-law accelerating growth. In this way the onset of ore formation is realized. This regularity reflects correctly the dynamic process of ore formation of the studied ore deposit. The authors hold that Sornette's theory can be further applied to the prediction of perspective areas.展开更多
Gabor filters are generally regarded as the most bionic filters corresponding to the visual perception of human. Their filtered coefficients thus are widely utilized to represent the texture information of irises. How...Gabor filters are generally regarded as the most bionic filters corresponding to the visual perception of human. Their filtered coefficients thus are widely utilized to represent the texture information of irises. However, these wavelet-based iris representations are inevitably being misaligned in iris matching stage. In this paper, we try to improve the characteristics of bionic Gabor representations of each iris via combining the local Gabor features and the key-point descriptors of Scale Invariant Feature Transformation (SIFT), which respectively simulate the process of visual object class recognition in frequency and spatial domains. A localized approach of Gabor features is used to avoid the blocking effect in the process of image division, meanwhile a SIFT key point selection strategy is provided to remove the noises and probable misaligned key points. For the combination of these iris features, we propose a support vector regression based fusion rule, which may fuse their matching scores to a scalar score to make classification decision. The experiments on three public and self-developed iris datasets validate the discriminative ability of our multiple bionic iris features, and also demonstrate that the fusion system outperforms some state-of-the-art methods.展开更多
This paper focuses mainly on semi-strapdown image homing guided (SSIHG) system design based on optical flow for a six-degree-of-freedom (6-DOF) axial-symmetric skid-to-turn missile. Three optical flow algorithms s...This paper focuses mainly on semi-strapdown image homing guided (SSIHG) system design based on optical flow for a six-degree-of-freedom (6-DOF) axial-symmetric skid-to-turn missile. Three optical flow algorithms suitable for large displacements are introduced and compared. The influence of different displacements on computational accuracy of the three algorithms is analyzed statistically. The total optical flow of the SSIHG missile is obtained using the Scale Invariant Feature Transform (SIFT) algorithm, which is the best among the three for large displacements. After removing the rotational optical flow caused by rotation of the gimbal and missile body from the total optical flow, the remaining translational optical flow is smoothed via Kalman filtering. The circular navigation guidance (CNG) law with impact angle constraint is then obtained utilizing the smoothed translational optical flow and position of the target image. Simulations are carried out under both disturbed and undisturbed conditions, and results indicate the proposed guidance strategy for SSIHG missiles can result in a precise target hit with a desired impact angle without the need for the time-to-go parameter.展开更多
With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automa...With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automatic collecting representative logo images from the internet without any human labeling or seed images. We propose multiple dictionary invariant sparse coding to solve this problem. This work can automatically provide prototypes, representative images, or weak labeled training images for logo detection, logo recognition, trademark infringement detection, brand protection, and ad-targeting. The experiment results show that our method increases the mean average precision for 25 types of Iogos to 80.07% whereas the original search engine results only have 32% representative logo images. The top images collected by our method are accurate and reliable enough for practical applications in the future.展开更多
Small or smooth cloned regions are difficult to be detected in image copy-move forgery (CMF) detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent (SI) algorithm ...Small or smooth cloned regions are difficult to be detected in image copy-move forgery (CMF) detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent (SI) algorithm is proposed. This method segments image into small nonoverlapping blocks. A calculation of smooth degree is given for each block. Test image is segmented into independent layers according to the smooth degree. SI algorithm is applied in finding the optimal detection parameters for each layer. These parameters are used to detect each layer by scale invariant features transform (SIFT)-based scheme, which can locate a mass of keypoints. The experimental results prove the good performance of the proposed method, which is effective to identify the CMF image with small or smooth cloned region.展开更多
A super-resolution enhancement algorithm was proposed based on the combination of fractional calculus and Projection onto Convex Sets(POCS)for unmanned aerial vehicles(UAVs)images.The representative problems of UAV im...A super-resolution enhancement algorithm was proposed based on the combination of fractional calculus and Projection onto Convex Sets(POCS)for unmanned aerial vehicles(UAVs)images.The representative problems of UAV images including motion blur,fisheye effect distortion,overexposed,and so on can be improved by the proposed algorithm.The fractional calculus operator is used to enhance the high-resolution and low-resolution reference frames for POCS.The affine transformation parameters between low-resolution images and reference frame are calculated by Scale Invariant Feature Transform(SIFT)for matching.The point spread function of POCS is simulated by a fractional integral filter instead of Gaussian filter for more clarity of texture and detail.The objective indices and subjective effect are compared between the proposed and other methods.The experimental results indicate that the proposed method outperforms other algorithms in most cases,especially in the structure and detail clarity of the reconstructed images.展开更多
The scale invariant feature transform (SIFT) feature descriptor is invariant to image scale and location, and is robust to affine transformations and changes in illumination, so it is a powerful descriptor used in m...The scale invariant feature transform (SIFT) feature descriptor is invariant to image scale and location, and is robust to affine transformations and changes in illumination, so it is a powerful descriptor used in many applications, such as object recognition, video tracking, and gesture recognition. However, in noisy and non-rigid object recognition applications, especially for infrared human face recognition, SIFT-based algorithms may mismatch many feature points. This paper presents a star-styled window filter-SIFT (SWF-SIFT) scheme to improve the infrared human face recognition performance by filtering out incorrect matches. Performance comparisons between the SIFT and SWF-SIFT algorithms show the advantages of the SWF-SIFT algorithm through tests using a typical infrared human face database.展开更多
文摘It is found that in some cases the complete and irreducible scale invariants given by Ref.[1] are not independent. There are some implicit functional relations among them. The scale invariants for two different cases are calculated. The first case is an arbitrary second order tensor. The second case includes a symmetric tensor, an antisymmetric tensor and a vector. By using the eigentensor notation it is proved that in the first case there are only six independent scale invariants rather than seven as reported in Ref.[1] and in the second case there are only nine independent scale invariants which are less than that obtained in Ref.[1].
基金supported by the National High Technology Research and Development Program (863 Program) (2010AA7080302)
文摘On the basis of scale invariant feature transform(SIFT) descriptors,a novel kind of local invariants based on SIFT sequence scale(SIFT-SS) is proposed and applied to target classification.First of all,the merits of using an SIFT algorithm for target classification are discussed.Secondly,the scales of SIFT descriptors are sorted by descending as SIFT-SS,which is sent to a support vector machine(SVM) with radial based function(RBF) kernel in order to train SVM classifier,which will be used for achieving target classification.Experimental results indicate that the SIFT-SS algorithm is efficient for target classification and can obtain a higher recognition rate than affine moment invariants(AMI) and multi-scale auto-convolution(MSA) in some complex situations,such as the situation with the existence of noises and occlusions.Moreover,the computational time of SIFT-SS is shorter than MSA and longer than AMI.
基金supported by the Development Program of China and the National Science Foundation Project (60475024)National High Technology Research (2006AA09Z203)
文摘Stable local feature detection is a fundamental component of many stereo vision problems such as 3-D reconstruction, object localization, and object tracking. A robust method for extracting scale-invariant feature points is presented. First, the Harris corners in three-level pyramid are extracted. Then, the points detected at the highest level of the pyramid are correctly propagated to the lower level by pyramid based scale invariant (PBSI) method. The corners detected repeatedly in different levels are chosen as final feature points. Finally, the characteristic scale is obtained based on maximum entropy method. The experimental results show that the algorithm has low computation cost, strong antinoise capability, and excellent performance in the presence of significant scale changes.
基金the Science and Technology Project of State Grid Corporation of China(Grant No.5100-202199557A-0-5-ZN)。
文摘Real-world networks exhibit complex topological interactions that pose a significant computational challenge to analyses of such networks.Due to limited resources,there is an urgent need to develop dimensionality reduction techniques that can significantly reduce the structural complexity of initial large-scale networks.In this paper,we propose a subgraph extraction method based on the node centrality measure to reduce the size of the initial network topology.Specifically,nodes with smaller centrality value are removed from the initial network to obtain a subgraph with a smaller size.Our results demonstrate that various real-world networks,including power grids,technology,transportation,biology,social,and language networks,exhibit self-similarity behavior during the reduction process.The present results reveal the selfsimilarity and scale invariance of real-world networks from a different perspective and also provide an effective guide for simplifying the topology of large-scale networks.
文摘Relative radiometric normalization (RRN) minimizes radiometric differences among images caused by inconsistencies of acquisition conditions rather than changes in surface. Scale invariant feature transform (SIFT) has the ability to automatically extract control points (CPs) and is commonly used for remote sensing images. However, its results are mostly inaccurate and sometimes contain incorrect matching caused by generating a small number of false CP pairs. These CP pairs have high false alarm matching. This paper presents a modified method to improve the performance of SIFT CPs matching by applying sum of absolute difference (SAD) in a different manner for the new optical satellite generation called near-equatorial orbit satellite and multi-sensor images. The proposed method, which has a significantly high rate of correct matches, improves CP matching. The data in this study were obtained from the RazakSAT satellite a new near equatorial satellite system. The proposed method involves six steps: 1) data reduction, 2) applying the SIFT to automatically extract CPs, 3) refining CPs matching by using SAD algorithm with empirical threshold, and 4) calculation of true CPs intensity values over all image’ bands, 5) preforming a linear regression model between the intensity values of CPs locate in reverence and sensed image’ bands, 6) Relative radiometric normalization conducting using regression transformation functions. Different thresholds have experimentally tested and used in conducting this study (50 and 70), by followed the proposed method, and it removed the false extracted SIFT CPs to be from 775, 1125, 883, 804, 883 and 681 false pairs to 342, 424, 547, 706, 547, and 469 corrected and matched pairs, respectively.
文摘Systems using numerous cameras are emerging in many fields due to their ease of production and reduced cost, and one of the fields where they are expected to be used more actively in the near future is in image-based rendering (IBR). Color correction between views is necessary to use multi-view systems in IBR to make audiences feel comfortable when views are switched or when a free viewpoint video is displayed. Color correction usually involves two steps: the first is to adjust camera parameters such as gain, brightness, and aperture before capture, and the second is to modify captured videos through image processing. This paper deals with the latter, which does not need a color pattern board. The proposed method uses scale invariant feature transform (SIFT) to detect correspondences, treats RGB channels independently, calculates lookup tables with an energy-minimization approach, and corrects captured video with these tables. The experimental results reveal that this approach works well.
基金Supported by the National Natural Science Foundation of China(60905012)
文摘To improve the performance of the scale invariant feature transform ( SIFT), a modified SIFT (M-SIFT) descriptor is proposed to realize fast and robust key-point extraction and matching. In descriptor generation, 3 rotation-invariant concentric-ring grids around the key-point location are used instead of 16 square grids used in the original SIFT. Then, 10 orientations are accumulated for each grid, which results in a 30-dimension descriptor. In descriptor matching, rough rejection mismatches is proposed based on the difference of grey information between matching points. The per- formance of the proposed method is tested for image mosaic on simulated and real-worid images. Experimental results show that the M-SIFT descriptor inherits the SIFT' s ability of being invariant to image scale and rotation, illumination change and affine distortion. Besides the time cost of feature extraction is reduced by 50% compared with the original SIFT. And the rough rejection mismatches can reject at least 70% of mismatches. The results also demonstrate that the performance of the pro- posed M-SIFT method is superior to other improved SIFT methods in speed and robustness.
基金supported by the National Natural Science Foundation of China(61271315)the State Scholarship Fund of China
文摘Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are generally used to get SIFT descriptors in order to reduce the complexity. The regions which have a similar grayscale level but different hues tend to produce wrong matching results in this case. Therefore, the loss of color information may result in decreasing of matching ratio. An image matching algorithm based on SIFT is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. Experimental results show that the proposed algorithm can effectively differentiate the regions with different colors but the similar grayscale level, and increase the matching ratio of image matching based on SIFT. Furthermore, it does not introduce much complexity than the traditional SIFT.
文摘Scale Invariant Feature Transform (SIFT) algorithm is a widely used computer vision algorithm that detects and extracts local feature descriptors from images. SIFT is computationally intensive, making it infeasible for single threaded im-plementation to extract local feature descriptors for high-resolution images in real time. In this paper, an approach to parallelization of the SIFT algorithm is demonstrated using NVIDIA’s Graphics Processing Unit (GPU). The parallel-ization design for SIFT on GPUs is divided into two stages, a) Algorithm de-sign-generic design strategies which focuses on data and b) Implementation de-sign-architecture specific design strategies which focuses on optimally using GPU resources for maximum occupancy. Increasing memory latency hiding, eliminating branches and data blocking achieve a significant decrease in aver-age computational time. Furthermore, it is observed via Paraver tools that our approach to parallelization while optimizing for maximum occupancy allows GPU to execute memory bound SIFT algorithm at optimal levels.
基金Sponsored by the Scientific Research Common Program of Beijing Municipal Commission of Education(Grant No. KM201010772021the National High Technology Research and Development Program of China (863 Program) (Grant No. 2006AA74105)the National Natural Science Foundation of Chi-na(Grant No. 60803103)
文摘To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.
基金Supported by the National Natural Science Foundation of China (No.61571222)the Natural Science Research Program of Higher Education Jiangsu Province (No.19KJD520005)+1 种基金Qing Lan Project of Jiangsu Province (Su Teacher’s Letter 2021 No.11)Jiangsu Graduate Scientific Research Innovation Program (No.KYCX21_1944)。
文摘The results of face recognition are often inaccurate due to factors such as illumination,noise intensity,and affine/projection transformation.In response to these problems,the scale invariant feature transformation(SIFT) is proposed,but its computational complexity and complication seriously affect the efficiency of the algorithm.In order to solve this problem,SIFT algorithm is proposed based on principal component analysis(PCA) dimensionality reduction.The algorithm first uses PCA algorithm,which has the function of screening feature points,to filter the feature points extracted in advance by the SIFT algorithm;then the high-dimensional data is projected into the low-dimensional space to remove the redundant feature points,thereby changing the way of generating feature descriptors and finally achieving the effect of dimensionality reduction.In this paper,through experiments on the public ORL face database,the dimension of SIFT is reduced to 20 dimensions,which improves the efficiency of face extraction;the comparison of several experimental results is completed and analyzed to verify the superiority of the improved algorithm.
文摘A general operational protocol which provides permanent macroscopic coherence of the response of any stable complex system put in an ever-changing environment is proposed. It turns out that the coherent response consists of two parts: 1) a specific discrete pattern, called by the author homeostatic one, whose characteristics are robust to the statistics of the environment;2) the rest part of the response forms a stationary homogeneous process whose coarse-grained structure obeys universal distribution which turns out to be scale-invariant. It is demonstrated that, for relatively short time series, a measurement, viewed as a solitary operation of coarse-graining, superimposed on the universal distribution results in a rich variety of behaviors ranging from periodic-like to stochastic-like, to a sequences of irregular fractal-like objects and sequences of random-like events. The relevance of the Central Limit theorem applies to the latter case. Yet, its application is still an approximation which holds for relatively short time series and for specific low resolution of the measurement equipment. It is proven that the asymptotic behavior in each and every of the above cases is provided by the recently proven decomposition theorem.
文摘This paper proposes a new set of 3D rotation scaling and translation invariants of 3D radially shifted Legendre moments. We aim to develop two kinds of transformed shifted Legendre moments: a 3D substituted radial shifted Legendre moments (3DSRSLMs) and a 3D weighted radial one (3DWRSLMs). Both are centered on two types of polynomials. In the first case, a new 3D ra- dial complex moment is proposed. In the second case, new 3D substituted/weighted radial shifted Legendremoments (3DSRSLMs/3DWRSLMs) are introduced using a spherical representation of volumetric image. 3D invariants as derived from the sug- gested 3D radial shifted Legendre moments will appear in the third case. To confirm the proposed approach, we have resolved three is- sues. To confirm the proposed approach, we have resolved three issues: rotation, scaling and translation invariants. The result of experi- ments shows that the 3DSRSLMs and 3DWRSLMs have done better than the 3D radial complex moments with and without noise. Sim- ultaneously, the reconstruction converges rapidly to the original image using 3D radial 3DSRSLMs and 3DWRSLMs, and the test of 3D images are clearly recognized from a set of images that are available in Princeton shape benchmark (PSB) database for 3D image.
基金supported by the Open Foundation of State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Beijing (No. GPMR200842)
文摘The "theory of self-similar oscillatory finite-time singularities" of Sornette reflects accurately the spatio-temporal evolution and trends of development of events and processes in complex systems approaching to the singularities, and the effect of prediction for catastrophic events has been tested to be satisfactory. The authors take the contents of the chemical element tungsten as the carrier of positive feedback (or activator) in the ore formation, then try to apply the theory to studying and analyzing the onset and development of ore formation in the Dajishan (大吉山) tungsten ore area, Jiangxi (江西) Province, China. The results of the study show that during the spatio-temporal evolution from outside the ore area to its center, the contents of the chemical element tungsten and their loga- rithmic derivatives (local fractal dimension) manifest an obvious regularity: by way of the process of oscillation and the transition to power-law accelerating growth, they eventually approach the center of ore formation. The regularity makes clear that in the complex ore-forming system of the Dajishan tungsten ore deposit, the chemical element tungsten plays the role of carrier of positive and negative feedback, and by competing with each other, approaches to singularity in finite time by virtue of self-similar log-periodic oscillations and succeeded by power-law accelerating growth. In this way the onset of ore formation is realized. This regularity reflects correctly the dynamic process of ore formation of the studied ore deposit. The authors hold that Sornette's theory can be further applied to the prediction of perspective areas.
文摘Gabor filters are generally regarded as the most bionic filters corresponding to the visual perception of human. Their filtered coefficients thus are widely utilized to represent the texture information of irises. However, these wavelet-based iris representations are inevitably being misaligned in iris matching stage. In this paper, we try to improve the characteristics of bionic Gabor representations of each iris via combining the local Gabor features and the key-point descriptors of Scale Invariant Feature Transformation (SIFT), which respectively simulate the process of visual object class recognition in frequency and spatial domains. A localized approach of Gabor features is used to avoid the blocking effect in the process of image division, meanwhile a SIFT key point selection strategy is provided to remove the noises and probable misaligned key points. For the combination of these iris features, we propose a support vector regression based fusion rule, which may fuse their matching scores to a scalar score to make classification decision. The experiments on three public and self-developed iris datasets validate the discriminative ability of our multiple bionic iris features, and also demonstrate that the fusion system outperforms some state-of-the-art methods.
基金supported by the Armament Research Fund of China (No.9020A02010313BQ01)
文摘This paper focuses mainly on semi-strapdown image homing guided (SSIHG) system design based on optical flow for a six-degree-of-freedom (6-DOF) axial-symmetric skid-to-turn missile. Three optical flow algorithms suitable for large displacements are introduced and compared. The influence of different displacements on computational accuracy of the three algorithms is analyzed statistically. The total optical flow of the SSIHG missile is obtained using the Scale Invariant Feature Transform (SIFT) algorithm, which is the best among the three for large displacements. After removing the rotational optical flow caused by rotation of the gimbal and missile body from the total optical flow, the remaining translational optical flow is smoothed via Kalman filtering. The circular navigation guidance (CNG) law with impact angle constraint is then obtained utilizing the smoothed translational optical flow and position of the target image. Simulations are carried out under both disturbed and undisturbed conditions, and results indicate the proposed guidance strategy for SSIHG missiles can result in a precise target hit with a desired impact angle without the need for the time-to-go parameter.
基金National Key Basic Research and Development(973)Program of China(Nos.2012CB316301 and 2013CB329403)National Natural Science Foundation of China(No.91120011)+1 种基金Tsinghua University Initiative Scientific Research Program(No.20121088071)Basic Research Foundation of Tsinghua National Laboratory for Information Science and Technology(TNList)
文摘With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automatic collecting representative logo images from the internet without any human labeling or seed images. We propose multiple dictionary invariant sparse coding to solve this problem. This work can automatically provide prototypes, representative images, or weak labeled training images for logo detection, logo recognition, trademark infringement detection, brand protection, and ad-targeting. The experiment results show that our method increases the mean average precision for 25 types of Iogos to 80.07% whereas the original search engine results only have 32% representative logo images. The top images collected by our method are accurate and reliable enough for practical applications in the future.
基金Supported by the National Natural Science Foundation of China(61472429,61070192,91018008,61303074,61170240)the National High Technology Research Development Program of China(863 Program)(2007AA01Z414)+1 种基金the National Science and Technology Major Project of China(2012ZX01039-004)the Beijing Natural Science Foundation(4122041)
文摘Small or smooth cloned regions are difficult to be detected in image copy-move forgery (CMF) detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent (SI) algorithm is proposed. This method segments image into small nonoverlapping blocks. A calculation of smooth degree is given for each block. Test image is segmented into independent layers according to the smooth degree. SI algorithm is applied in finding the optimal detection parameters for each layer. These parameters are used to detect each layer by scale invariant features transform (SIFT)-based scheme, which can locate a mass of keypoints. The experimental results prove the good performance of the proposed method, which is effective to identify the CMF image with small or smooth cloned region.
基金This work is supported by the National Key Research and Development Program of China[grant number 2016YFB0502602]the National Natural Science Foundation of China[grant number 61471272]the Natural Science Foundation of Hubei Province,China[grant number 2016CFB499].
文摘A super-resolution enhancement algorithm was proposed based on the combination of fractional calculus and Projection onto Convex Sets(POCS)for unmanned aerial vehicles(UAVs)images.The representative problems of UAV images including motion blur,fisheye effect distortion,overexposed,and so on can be improved by the proposed algorithm.The fractional calculus operator is used to enhance the high-resolution and low-resolution reference frames for POCS.The affine transformation parameters between low-resolution images and reference frame are calculated by Scale Invariant Feature Transform(SIFT)for matching.The point spread function of POCS is simulated by a fractional integral filter instead of Gaussian filter for more clarity of texture and detail.The objective indices and subjective effect are compared between the proposed and other methods.The experimental results indicate that the proposed method outperforms other algorithms in most cases,especially in the structure and detail clarity of the reconstructed images.
文摘The scale invariant feature transform (SIFT) feature descriptor is invariant to image scale and location, and is robust to affine transformations and changes in illumination, so it is a powerful descriptor used in many applications, such as object recognition, video tracking, and gesture recognition. However, in noisy and non-rigid object recognition applications, especially for infrared human face recognition, SIFT-based algorithms may mismatch many feature points. This paper presents a star-styled window filter-SIFT (SWF-SIFT) scheme to improve the infrared human face recognition performance by filtering out incorrect matches. Performance comparisons between the SIFT and SWF-SIFT algorithms show the advantages of the SWF-SIFT algorithm through tests using a typical infrared human face database.