Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
47results about How to "Sparse" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Sparse representation based short-voice speaker recognition method
InactiveCN103345923AAlleviate underrepresentation of personality traitsDealing with mismatchesSpeech analysisMajorization minimizationSelf adaptive
The invention discloses a sparse representation based short-voice speaker recognition method, which belongs to the technical field of voice signal processing and pattern recognition, and aims to solve the problem that the existing method is low in recognition rate under limited voice data conditions. The method mainly comprises the following steps: (1) pretreating all voice samples, and then extracting Mel-frequency cepstral coefficients and first-order difference coefficients thereof as characteristic; (2) training a gaussian background model by a background voice library, and extracting gaussian supervectors as secondary characteristics; (3) arranging the gaussian supervectors for training voice samples together so as to form a dictionary; and (4) solving an expression coefficient by using a sparse solving algorithm, reconstructing signals, and determining a recognition result according to a minimized residual error. According to the invention, the gaussian supervectors obtained through self-adaption can greatly relieve the problem that the personality characteristics of a speaker are expressed insufficiently due to limited voice data; through carrying out classification by using sparsely represented reconstructed residual errors, a speaker model mismatch problem caused by mismatched semantic information can be handled.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA
Method for super-resolution imaging of foresight array SAR based on sparse representation
InactiveCN103869316AQuality improvementOvercoming problems constrained by array lengthRadio wave reradiation/reflectionImaging algorithmMaximum a posteriori estimation
The invention discloses a method for super-resolution imaging of a foresight array SAR based on sparse representation. The method mainly solves the problems that an existing foresight imaging algorithm is difficult to achieve physically, and system cost is high. The method comprises the steps that (1) SAR echo data are received in a double-base mode, and echo signals are modified in a single-base mode; (2) range pulse compression and direction dimension unbinding and frequency modulation are conducted on the modified echo signals; (3) according to the observation scene and the sparse characteristic of an imaging target, a cost function of SAR imaging of the processed signals is established through the maximum posterior probability estimation method; (4) the updated quasi-Newton algorithm is used for solving the cost function, and then a super-resolution imaging result of the foresight array SAR is obtained. By means of the method, a high-resolution foresight imaging result can be obtained under the condition of a limited array length, the cost and complexity of a system are effectively lowered, and the method can be applied to target detection, topographic reconnaissance, guidance, city planning and environment surveys.
Owner:XIDIAN UNIV
Wave arrival direction estimation method under array error
ActiveCN104965188ASparseImprove accuracyRadio wave direction/deviation determination systemsDirection/deviation determining electromagnetic systemsOptimization problemEstimation methods
The invention relates to wave arrival direction estimation method under an array error. First the method utilizes sparsity of a matrix, expresses wave arrival direction estimation under the array error by solving an optimization problem, and then converts the optimization problem into an iterative algorithm to realize. Compared with an existing wave arrival direction estimation algorithm under an array error, the estimation method proposed by the invention has remarkably improved estimation performance under the condition of equivalent complexity, and has good application prospects in the field of direction estimation.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
Local binary CNN processing method, device, storage medium and processor
InactiveCN107491787AAvoid the problem of excessive performance degradationImprove parametersCharacter and pattern recognitionNeural architecturesData setConvolution
The invention discloses a local binary CNN processing method, a device, a storage medium and a processor, wherein the method comprises the steps of training a first convolutional neural network according to a preset data set, and obtaining a second convolutional neural network; replacing all convolutional layer units in the first convolutional neural network by a local binary convolutional unit, thereby obtaining a third convolutional neural network; replacing objective total connecting layers in the third convolutional neural network by a grouping connecting layer, thereby obtaining a fourth convolutional neural network, wherein the objective total connecting layers are all total connecting layers except for a bottom classification layer in the third convolutional neural network; initializing the fourth convolutional neural network, thereby obtaining a fifth convolutional neural network; and training the fifth convolutional neural network based on the second convolutional network and a preset data set, thereby obtaining an objective convolutional neural network. The local binary CNN processing method, the device, the storage medium and the processor settle a technical problem of relatively low operation efficiency in the local binary convolutional neural network in prior art.
Owner:珠海习悦信息技术有限公司
Low rank image denoising method
ActiveCN109064412AAvoid sparsityImprove stabilityImage enhancementImage analysisPattern recognitionImage denoising
The invention discloses a denoising method of a low-rank image, which is applied to the reconstruction of an image containing noise. By analyzing the correlation characteristics of the low-rank matrix, the denoising problem of the image is modeled as a non-linear constraint problem, and then the specific iterative steps are deduced by using an alternating direction multiplier method, thereby obtaining the image after denoising. The invention uses the truncated kernel norm to more accurately approximate the rank of the matrix and avoids the result deviation caused by the large singular value. In addition, the Frobenius norm is added to the model as a regular term, the Frobenius norm and the truncated kernel norm form an elastic network about the singular value, so that the final result is sparse and stable, so that better denoising effect can be achieved.
Owner:NANJING UNIV OF POSTS & TELECOMM
Embedded low power consumption convolutional neural network method
The invention discloses an embedded low-power convolution neural network method; for the two adjacent layers of the conv layer and the conv+concat layer, the idea of inception in GoogLeNet is adopted, and the volume of 1×1 and 3×3 The product kernels are arranged in parallel, and features on different scales are collected separately, and then the feature maps calculated by the two convolution kernels are spliced. For the conv+concat layer, the idea of ResNet is adopted. The splicing results of this network in the conv+concat layer The element-by-element addition operation of short cut connection was performed, and each layer was pre-pruned separately. The cut neurons accounted for 50% of the total, and the impact of each layer on the overall accuracy was tested. Reduce the convolution size of each layer of the multi-layer network, reduce the number of convolution kernels and the network has a certain degree of sparsity, so the number of multiplications required for each layer is very small. In specific calculations, it can be converted to have CSR The product of the sparse matrix and the dense matrix in the storage format, in order to achieve the purpose of small memory usage, fast calculation speed and high precision.
Owner:深圳互连科技有限公司
Domain transfer extreme learning machine method based on manifold regularization and norm regularization
ActiveCN106803124AAchieve overfittingPrevent overfittingMachine learningA domainManifold regularization
The invention discloses a domain transfer extreme learning machine method based manifold regularization and norm regularization. On the basis of a traditional extreme learning machine, the thought of semi-supervised learning and transfer learning is introduced, and a novel extreme learning machine model is built and consists of three parts: a manifold regularization term capable of excavating geometric distribution shapes of data samples with tags and without tags to realize semi-supervised learning; a loss function term considering error minimization of source domain data and target domain data to realize transfer learning; and norm regularizers constraining weight space. The domain transfer extreme learning machine method provide by the invention is combined with the source domain to process the problem of prediction of the target domain, thereby increasing the generalization capability and range of application of the extreme learning machine. Introduction of the manifold regularization term also enables the method proposed by the invention to still maintain a relatively good learning effect when data with tags are little, the restriction that a traditional machine learning method requires a large amount of data with tags is overcome, and the accuracy and robustness of prediction are also improved.
Owner:OCEAN UNIV OF CHINA
ACO-OFDM system channel estimation method based on compressed sensing
InactiveCN106911622AImprove reconstruction accuracyIncrease computing speedMulti-frequency code systemsCorrection algorithmCommunications system
The present invention provides an ACO-OFDM wireless optical communication system channel estimation method based on compressed sensing, and belongs to the field of intensity modulation optical communication. The channel estimation method is used to solve the problem that during pilot based channel estimation, a pilot symbol causes a bandwidth utilization rate to be reduced. According to the method provided by the present invention, channel estimation technology based on the compressed sensing is combined with the ACO-OFDM system. Firstly, the pilot is enabled to have Hermitian symmetry, a pilot allocation scheme is optimized by minimizing a DFT sub-matrix cross-correlation squared sum, and an ACO-OFDM system pilot allocation optimization algorithm is provided. Then, a channel response is estimated by using an improved variable step sparse degree adaptive matching tracking algorithm, the improved algorithm can improve estimation accuracy and calculation speed. Finally, an iterative correction algorithm is used to further improve the estimation accuracy. Compared with the traditional pilot based channel estimation method, the method can effectively reduce the number of pilot symbols, and improve the system bandwidth utilization rate.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
Low-rank decomposition and space spectrum constraint-based hyperspectral image time domain change feature extraction method
ActiveCN107609573AStrong Intraclass CorrelationHigh strengthCharacter and pattern recognitionComplex mathematical operationsTime domainMultiple forms
The invention relates to a low-rank decomposition and space spectrum constraint-based hyperspectral image time domain change feature extraction method. The method mainly comprises the following stepsof: calculating a difference image between two hyperspectral remote sensing images acquired at a same place and at different times; establishing a low-rank matrix decomposition model with a space spectrum constraint by utilizing internal data structural characteristics of the difference image; and solving each component of the model through an alternate iteration manner so as to extract a time domain change feature. According to the method, the low-rank matrix decomposition model with the space spectrum constraint and a solution algorithm of the model are disclosed by sufficiently utilizing internal structures of data, so that the time domain change feature is effectively extracted, multiple forms of noises are removed, real changes are strengthened and false changes caused by noises are suppressed, thereby improving the change detection precision of time domain change hyperspectral remote sensing images.
Owner:DONGHUA UNIV
Method for obtaining sparse solution of robust least square support vector machine
InactiveCN106126482ASparseImprove the speed of solvingCharacter and pattern recognitionComplex mathematical operationsAlgorithmLeast squares support vector machine
The invention provides a method for obtaining a sparse solution of a robust least square support vector machine. The method is used for solving the technical problem of solution lack sparsity existing in an obtaining method of a solution of the robust least square support vector machine and comprises the implementation steps that training data is input; a robust least square support vector machine model is constructed; the robust least square support vector machine model is converted into a DC plan; the DC plan of the robust least square support vector machine model based on original space is constructed; the DC plan of the robust least square support vector machine model based on the original space is smoothed; a subset B and a matrix P are selected from a sample index set; the sparse solution of the smoothed DC plan of the robust least square support vector machine model based on the original space is obtained; whether an optimal solution is sought or not is judged. According to the method, the sparse solution of the robust least square support vector machine can be obtained, and the method can be applied to the fields of classification and regression of big data with noise.
Owner:XIDIAN UNIV
A facial expression recognition method based on convolution neural network
ActiveCN109033994AChange accuracySparseNeural architecturesAcquiring/recognising facial featuresIdentification rateWeight value
The invention provides a face expression recognition method based on a convolution neural network, which relates to the technical field of face expression recognition. At first, the method collects facial expression pictures and downloads the FER-2013 face database and CK + face database; the images are divided into a training set and a test set, then the collected images are preprocessed to obtain the 96*96 size gray-scale images, and the convolution neural network model is established; the training set is used for training and the error between the actual output result of training and the label value is calculated, and the difference value is transmitted from top to bottom through the back propagation algorithm, and the weight value is updated by the weight value update formula. After the training, the network model is saved, the image of the test set is inputted into the training model, and the recognition rate is calculated. In the invention, the face expression recognition methodis improved, the convergence speed of the model is improved, the recognition efficiency is improved, the accuracy rate of the convolution neural network is changed, and the face expression recognitionefficiency is improved to a certain extent.
Owner:LIAONING TECHNICAL UNIVERSITY
Nonorthogonal multi-carrier transmission method
Owner:TIANJIN UNIV
Compression acceleration method of deep convolutional neural network for target detection
PendingCN111105007AReduce storageSparseNeural architecturesPhysical realisationActivation functionAlgorithm
The invention discloses a compression acceleration method of a deep convolutional neural network for target detection. The method comprises the following steps: constructing and training a deep convolutional neural network for target detection; carrying out quantitative test on all weight values in the deep convolutional neural network and activation values of all layers except the last layer after passing through an activation function, testing the detection performance loss condition of the network from small to large in quantitative step size, and selecting the maximum quantitative step size in a set loss range; determining a truncation range of a weight value and an activation value in the neural network by utilizing the quantization step length, limiting the neural network and training the network; and truncating and quantifying the deep convolutional neural network, and compiling a forward code. According to the method, the quantization technology is adopted to reduce the networkstorage capacity, 32-bit floating-point number operation in the network is converted into 8-bit integer operation, and meanwhile, the sparsity of the network is utilized to convert the layer meetingthe sparsity condition in the network into sparse matrix operation, so that the purpose of compressing and accelerating the deep convolutional neural network is achieved.
Owner:INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
Dense multipath signal angle estimation method based on impulse response compression sensing
ActiveCN109375153AWon't failHigh precisionRadio wave direction/deviation determination systemsImage resolutionDiscretization
The invention discloses a dense multipath signal angle estimation method based on impulse response compression sensing. A pseudo random sequence with the length of N as a baseband detection signal, aspatial channel impulse response model is determined, receiving array antennas that have the M same array elements and are arranged uniformly and linearly are generated, and a guide vector of the antenna array under a first path is determined; for receiving signals of from a first antenna element to an M antenna element, sliding correlation is carried out on the receiving signasl and a standard local pseudo-random sequence to obtain an observation impulse response, discretization processing is carried out to obtain an observation impulse response matrix, impulse response covariance matrixes ofeffective paths from the first one to the L one of the spatial channel are calculated respectively, a redundant dictionary for sparse reconstruction is constructed, and sparse vectors are calculatedto form an angular spatial spectrum, wherein the angle corresponding to the large value is the coherent path direct-of-arrival angle in the l-th path. Therefore, the direct-of-arrival angle estimationof lots of multi-path signals is realized; the estimation accuracy and the angular resolution are high; and the coherent paths are distinguished.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Image category detection method and system, electronic equipment and storage medium
PendingCN112085112AGood generalization performanceImprove classification accuracyPaper-money testing devicesCharacter and pattern recognitionMachine learningImaging Feature
The invention discloses an image category detection method, and the method comprises the steps: obtaining a training image set, and constructing a training sample according to the image features of each training image in the training image set; training a classification model by using the training sample, wherein the classification model is a model constructed by a sparse Fisher support vector machine classification algorithm, and the sparse Fisher support vector machine is a Fisher support vector machine based on an L1 norm; and inputting a to-be-detected image into the trained classificationmodel to obtain the image type of the to-be-detected image. The image classification accuracy can be improved. The invention further discloses an image category detection system, electronic equipmentand a storage medium, which have the above beneficial effects.
Owner:SUZHOU UNIV
Multi-path number estimation method based on channel observation impulse response model
ActiveCN109412982AHigh precisionHigh speedTransmission monitoringChannel estimationChannel impulse responseEstimation methods
The invention discloses a multi-path number estimation method based on a channel observation impulse response model. A pseudo-random sequence of length N is selected to be used as a baseband detectionsignal, the spatial channel impulse response model is determined, a receiving array antenna which has M identical array elements and is in uniform linear arrangement is generated, and a steering vector of an antenna array is determined; sliding correlation is carried out on received signals of first-to-M-th receiving antenna oscillators and the standard local pseudo-random sequence to obtain observation impulse response, discretization is carried out to obtain an observation impulse response matrix, multi-path number estimation is carried out on the observation impulse response matrix, inspection and estimation are carried out on first-to-K-th valid paths and coherence paths of spatial channels, and the multi-path number of the entire received signals and a corresponding correlation structure are obtained. According to the method, number estimation of the massive multi-path signals is realized, estimation accuracy is high, and the coherence paths can be distinguished.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Method for face recognition by adopting two-dimensional non-negative sparse partial least squares
InactiveCN103971132ASparseDoes not damage the internal structureCharacter and pattern recognitionPattern recognitionTest sample
The invention relates to a method for face recognition by adopting two-dimensional non-negative sparse partial least squares. The method comprises the following steps: firstly constructing a category matrix of a face training sample set, then constructing an objective function for realizing minimum loss of the amount of information in the projection of the face training sample set and the category matrix, afterwards adding non-negativity constraint and sparsity constraint into the objective function to obtain a convergent non-negative basis matrix, projecting the face training sample set on the basis matrix to obtain a test sample coefficient matrix, also carrying out the operation on a test sample to obtain a coefficient matrix of the test sample, determining that certain element matrices in the coefficient matrix of the test sample and the test sample coefficient matrix fall into the same category by using a nearest neighbor strategy, and then considering that a person on the test sample corresponding to the coefficient matrix of the test sample is the same person on the training sample corresponding to the element matrix. The method is high in recognition rate and robustness, and as only the basis matrix needs iterative solution, the operation is simplified, the time complexity is reduced, and the recognition speed is high.
Owner:CHONGQING UNIV
Change detection method for remote sensing images based on multi-resolution nmf and treelet fusion
InactiveCN102831598BSparseFacilitate data interpretationImage analysisDisaster monitoringImage resolution
Owner:XIDIAN UNIV
Event camera target recognition method based on self-attention mechanism
ActiveCN113378917AImprove general expression abilitySparseInternal combustion piston enginesCharacter and pattern recognitionFeature extractionData acquisition
The invention discloses an event camera target recognition method based on a self-attention mechanism. The event camera target recognition method comprises the following steps: S1, initializing an event camera; s2, completing a data acquisition task by using the initialized event camera; s3, performing image conversion on the collected event camera data, so that the event camera data can be used for a target identification task; s4, performing feature extraction on the event camera data after image conversion by using the trained network to obtain depth features of the target; s5, inputting the extracted depth features into a self-attention mechanism model for self-attention calculation to obtain target types included in the event camera data at the current moment; and S6, performing result output on the features subjected to self-attention calculation, and taking a result with the highest confidence coefficient as a final result to be output. The method solves the technical problems that current event camera training data is insufficient, and a traditional deep learning method is weak in global perception capability of event camera data.
Owner:深圳龙岗智能视听研究院
Sparse transform-based handwritten digit recognition method
InactiveCN104850870ASparseEasy to calculateCharacter and pattern recognitionPattern recognitionNear neighbor
The invention discloses a sparse transform-based handwritten digit recognition method. The method includes the following steps of: pre-processing read training data; training the pre-processed training data with an objective function so as to obtain a transform matrix W; performing sparse transform on data to be detected to obtain a sparse representation coefficient x'; and based on a nearest neighbor rule, comparing the sparse representation coefficient x' of the data to be detected with various classifications of class tags, and finding a class tag most similar to a sample to be detected, and classifying the sample to be detected to a classification to which the class tag belongs, and finishing recognition of handwritten digits. With the sparse transform-based handwritten digit recognition method of the invention adopted, after being subjected to the sparse transform, the data to be detected has sparsity, and therefore, computation is simple, and operation efficiency can be improved.
Owner:XIAN UNIV OF TECH
Method and device for detecting abnormal articles in scene
ActiveCN111079671ASparseRepresentativeCharacter and pattern recognitionNeural architecturesPattern recognitionRadiology
The embodiment of the invention discloses a method and a device for detecting abnormal articles in a scene, and the method comprises the steps: respectively inputting a scene detection graph and a scene standard graph into corresponding sub-networks of a twin network, and respectively obtaining a feature graph of the scene detection graph and a feature graph of the scene standard graph; fusing thefeature map of the scene detection map and the feature map of the scene standard map to obtain a common feature map; calculating by adopting a plurality of hole convolution and the common feature maprespectively to obtain sub-feature maps of multiple types of articles in a scene encircled by a target frame; screening out sub-feature maps with abnormal articles from the sub-feature maps of the multiple types of articles in the scene through a full-connection network, calculating coordinates of the sub-feature maps with the abnormal articles, and circling the abnormal articles by using the target frame in the scene detection map. Through the abnormal article detection method provided by the embodiment of the invention, the abnormal article which should not appear in the scene originally can be detected, manpower is greatly liberated, and the life quality of people is improved.
Owner:北京智创数字科技服务有限公司
Rock debris type identification method and device, electronic equipment and storage medium
PendingCN114863187AWell formedCalculation speedNeural architecturesNeural learning methodsMining engineeringNetwork model
The invention relates to a rock debris type identification method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-identified rock debris image; inputting the to-be-identified rock debris image into a pre-trained rock debris type identification model to obtain an identification result of the to-be-identified rock debris image; wherein the rock debris type identification model is obtained by training based on a ResNet34 classification network model. By means of the method, the property information of the rock debris and the rock sample of the drilled stratum can be rapidly analyzed, an effective stratum geological section is established, the defect that geological logging interpretation must depend on a deep geotechnician is overcome, and the automation and intelligence level of a drilling and logging site is improved.
Owner:BC P INC CHINA NAT PETROLEUM CORP +1
Domain Transfer Extreme Learning Machine Method Based on Manifold Regularization and Norm Regularization
ActiveCN106803124BAchieve overfittingPrevent overfittingMachine learningLearning machineSupervised learning
The invention discloses a domain transfer extreme learning machine method based manifold regularization and norm regularization. On the basis of a traditional extreme learning machine, the thought of semi-supervised learning and transfer learning is introduced, and a novel extreme learning machine model is built and consists of three parts: a manifold regularization term capable of excavating geometric distribution shapes of data samples with tags and without tags to realize semi-supervised learning; a loss function term considering error minimization of source domain data and target domain data to realize transfer learning; and norm regularizers constraining weight space. The domain transfer extreme learning machine method provide by the invention is combined with the source domain to process the problem of prediction of the target domain, thereby increasing the generalization capability and range of application of the extreme learning machine. Introduction of the manifold regularization term also enables the method proposed by the invention to still maintain a relatively good learning effect when data with tags are little, the restriction that a traditional machine learning method requires a large amount of data with tags is overcome, and the accuracy and robustness of prediction are also improved.
Owner:OCEAN UNIV OF CHINA
Large-scale mimo beam domain robust precoding transmission method and system
ActiveCN111193533BSolve universal problemsSparseRadio transmissionPrecodingChannel state information
The invention discloses a large-scale MIMO beam domain robust precoding transmission method and system. This method is based on the base station side and user side refined sampling steering vector matrix, and considers the influence of channel aging caused by mobility. The obtained channel state information is refined beam domain posterior statistical channel information including channel mean and variance information. In the present invention, the base station uses the refined beam domain a posteriori statistical channel information to perform robust precoding transmission, and the channel model on which the refined beam domain a posteriori statistical channel information depends is based on the adoption guidance corresponding to the refined sampling space angle. The channel model of the vector matrix, the statistical channel information used is more sufficient and accurate, can solve the problem of the universality of massive MIMO to various typical mobile scenarios under the limitation of antenna size, and achieve high spectral efficiency, the proposed robust precoding The design utilizes the sparsity of the beam domain channel and the structural characteristics of the sampled steering vector matrix, which can greatly reduce the computational complexity.
Owner:SOUTHEAST UNIV
A Method of Illumination Equalization of Two-Dimensional Code Image Based on Compressed Sensing
The invention discloses a compressed-sensing-based restoration method of a two-dimensional code image with non-uniform illumination. The method comprises the following steps that: a same two-dimensional code image is collected to obtain two two-dimensional code images and sparsity analysis is carried out on the two-dimensional code images; Fourier transform is carried out on the two two-dimensional code images to obtain spectrum images X1 and X2, a non-correlation sampling matrix is set according to the Fourier features of the two-dimensional code images, wherein the non-correlation sampling matrix is formed by a cross and a concentric circle and the sampling cross width and concentric circle dimension can be adjusted properly, and spectrum sampling is carried out on the spectrum images X1 and X2 at the Fourier zone so as to obtain a Y1 and a Y2; linear fusion is carried out on the Y1 and Y2 to obtain a new Fourier spectrum Y; and quick soft threshold iteration is carried out on the Fourier spectrum Y by using a fast iterative shrinkage-thresholding algorithm (FISTA) to obtain a Y', Fourier transform is carried out on the Y' to obtain a restored image f, and binarization processing is carried out on the image f and a two-dimensional code image is identified. With the method, equalized illumination can be realized; a processing speed of an image with non-uniform illumination can be accelerated; and an original two-dimensional code image can be restored accurately.
Owner:SUN YAT SEN UNIV +1
A Depth Map Super-resolution Reconstruction Method Based on l1-l2 Penalty Function
InactiveCN105354797BQuality improvementSparseGeometric image transformationColor imageImage resolution
The invention discloses a depth map super-resolution reconstruction method based on L1-L2 penalty functions. The method comprises the following steps: a first step, calculating an initial estimated depth: mapping a low-resolution depth map to a high-resolution color image coordinate plane; a step 2, calculating a mask matrix: constructing a diagonal matrix, if the ith pixel point is located on a mapping coordinate of the low-resolution depth map on a high-resolution color image, the ith diagonal element is 1, and otherwise, the ith diagonal element is 0; a third step, calculating a neighbor matrix: constructing the neighbor matrix by means of the color similarity of pixel points of the high-resolution color image on a YCbCr space; a fourth step, constructing a depth super-resolution reconstruction model: establishing an energy model of depth super-resolution reconstruction; and a fifth step, resolving the energy model to obtain a reconstructed high-resolution depth map. The depth map super-resolution reconstruction method disclosed by the invention has the advantages that an object edge of the depth map can be enhanced while keeping the smooth transition of the depth in an object.
Owner:NINGBO UNIVERSITY OF TECHNOLOGY
Handwritten Digit Recognition Method Based on Sparse Transformation
InactiveCN104850870BSparseEasy to calculateCharacter and pattern recognitionPattern recognitionNear neighbor
The invention discloses a sparse transform-based handwritten digit recognition method. The method includes the following steps of: pre-processing read training data; training the pre-processed training data with an objective function so as to obtain a transform matrix W; performing sparse transform on data to be detected to obtain a sparse representation coefficient x'; and based on a nearest neighbor rule, comparing the sparse representation coefficient x' of the data to be detected with various classifications of class tags, and finding a class tag most similar to a sample to be detected, and classifying the sample to be detected to a classification to which the class tag belongs, and finishing recognition of handwritten digits. With the sparse transform-based handwritten digit recognition method of the invention adopted, after being subjected to the sparse transform, the data to be detected has sparsity, and therefore, computation is simple, and operation efficiency can be improved.
Owner:XIAN UNIV OF TECH
Method and system for automatic identification of pavement disease images
ActiveCN107230202BRealize automatic identificationLow gray valueImage analysisCharacter and pattern recognitionRadiologyRoad surface
The invention discloses an automatic identification method and system for road surface disease images. The method includes: preprocessing the captured road surface image, including Gamma grayscale correction, Gaussian filter enhancement and local adaptive binarization; performing edge detection on the binarized image; performing connected domain contour detection on the image after edge detection , to obtain the number of connected domains and the circumscribed rectangle of the connected domain outline; judge the area where the road surface crack is located according to the shape of the circumscribed rectangle of the connected domain outline; extract the image of the crack area from the image after edge detection according to the location information of the area where the pavement crack is located , and superimposed the black template to form a crack feature image with the same size as the original image; the crack feature image is classified based on the convolutional neural network. Compared with the prior art, the present invention has very excellent detection efficiency for crack location in pavement disease, and has good robustness performance for crack images with different characteristics.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY
MRI glioma segmentation method and system based on sparse Bayesian model and multi-map fusion
ActiveCN110503655AClear boundariesSparseImage enhancementImage analysisPattern recognitionBoundary contour
The invention discloses an MRI glioma segmentation method and system based on a sparse Bayesian model and multi-map fusion, and the method comprises the steps: receiving MRI, carrying out the preprocessing, and obtaining an image which is jointly registered to a unified anatomy template through all modes of the MRI and is provided with an auxiliary diagnosis segmentation label; segmenting different modes of the MRI by adopting a sparse Bayesian model to obtain different mode segmentation result tags; and fusing segmentation results of different modes in MRI by adopting a multi-map fusion method to obtain a final glioma segmentation result with a clear boundary contour.
Owner:SHANDONG NORMAL UNIV
Channel detection method and device in large-scale antenna system
ActiveCN104113396BReduce overheadOverhead AccurateRadio transmissionChannel estimationEngineeringMultiple input
The present invention relates to a channel detection method and device in a system having a large number of antennas. In an embodiment, a method used in a base station having N transmitting antennas in a multiple input multiple output (MIMO) system is provided, which includes: determining NBF orthogonal pilot patterns and other M orthogonal pilot patterns; performing beamforming on NBF subspaces, and sending a pilot signal on each beam, where pilot signals on the beams of the NBF subspaces are sent respectively over the NBF pilot patterns; and sending pilot signals over at least a part of the M pilot patterns through each of the N transmitting antennas, in a manner that sub-directions in each subspace use the orthogonal pilot patterns, where a value of NBF is 10%~15% of N, and a value of M is 15%~50% of N. By using channel sparsity of the system having a large number of antennas, pilot overhead is reduced, and at least equivalent system performance can be achieved.
Owner:ALCATEL LUCENT SHANGHAI BELL CO LTD
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com