38 results about "Regular constraint" patented technology

The design of typable devices, in particular, touch-typable devices embodying ambiguous codes, presents numerous ergonomic problems. Solutions for these problems are herein disclosed. This invention teaches methods for the selection of ambiguous codes from the classes of strongly-touch-typable ambiguous codes and substantially optimal ambiguous codes for touch-typable devices such as computers, telephones, pagers, personal digital assistants, smart cards, television set-top devices and other information appliances, given design constraints such as the size, shape, and computational capacity of the device, the typical uses of the device, and conventional constraints such as respect of alphabetic ordering or Qwerty ordering.

The invention relates to an intelligent optimization algorithm based cloud manufacturing computing resource reconfigurable collocation method, in particular to a method for modifying relevant collocation attributes and algorithms online according to different collocation conditions on the basis of multiple intelligent optimization algorithms, which aims to realize flexible, extendible and efficient policy solution of massive computing resource collocation in the cloud manufacturing mode and flexible disintegration, integration and reconfiguration of model demands, input / output and policy operators in a modularization and servicisation manner, and solves the bottleneck problems of singleness and non-portability and the like caused by regular constraint, fixed models and regular algorithms in computing resource collocation. The intelligent optimization algorithm based cloud manufacturing computing resource reconfigurable collocation method has the following advantages that separation of collocation models and algorithms for the computing resources is realized, modularization reconfiguration inside the models and the algorithms is supported, integration is efficient, levels are clear and extendibility is high.

The invention discloses a sequence image self-adaptive regular super resolution reconstruction method and is directed to the field of image enhancement technology. According to the invention, based on the present regularization reconstruction method, improvements are carried out to an image reconstruction regularization object equation, an edge maintenance operator based on morphology is introduced to have an effect on a regular item, different regular constraints are adopted towards different geometrical structures, the constraint reconstruction of the image is enhanced at the edge of the image, that is, a small regularization parameter is employed and a large regularization parameter is adopted in the smooth area of the image to enhance the regularization. Besides, each time the acquirement of the edge maintenance operator is self-adaptive based on a latest iteration result with the ongoing of the iteration. Compared to the prior art, according to the invention, a smoothing effect in the reconstruction process can be effectively inhibited and the quality of the reconstructed high resolution image is improved.

The invention discloses a super-high-resolution three dimensional reconstruction method based on a global variation technology. The method comprises the following steps: low-resolution three dimensional geometrical model and a high-resolution surface normal graph of a scene to be constructed is obtained; a global optimization energy function is constructed and obtained according to the difference between the low-resolution geometrical model and the high-resolution normal graph; the minimum value of the global optimization energy function is solved, a depth value of each pixel point is obtained, and three dimensional reconstruction is carried out according to the depth values of all the pixel points. The super-high-resolution three dimensional reconstruction method based on non-local total variation regular constraint condition lowers dependence of a final reconstruction result on an original result effectively and raises the three dimensional reconstruction precision greatly.

The invention relates to a turbulence-degraded image blind restoration method based on edge prediction and sparse ratio regular constraints. The method is technically characterized by comprising the steps of predicating an effective edge in a current image to be restored, combining edge predication information with sparse prior information of a natural image edge to guide restoration of a point spread function, restoring the current target image according to a non-blind restoration algorithm, regarding the restored image as input of edge predication of the next time, and carrying out the iterative cycle in this way till a clear restored image is obtained. According to the method, by combining the prior information of an image with effective information contained in the degraded image, artifacts generated in the image restoration process can be effectively restrained, more details can be restored, and the restoration effect is better.

The invention discloses a design system for a human dynamic bone, comprising an initialization module, a node generation module, a bone constraint module and a collision constraint module, wherein the initialization module is used for initializing model data; the node generation module is used for generating and storing bone node data; the bone constraint module is used for performing regular constraint on a node in the change process; and the collision constraint module is used for performing regular constraint on a bone model in collision. The invention further discloses a design method for a human dynamic bone, comprising the steps of: initializing model data; generating and storing bone node data; performing regular constraint on a node in the change process; and performing regular constraint on a bone model in collision. The system and the method have the advantages of greatly shortening the time required for adjusting lattice vertex parameters by adopting a bone animation or a fabric system in the old scheme, physically simulating the motion and relevant constraints of fabrics and hair more truly and vividly, and efficiently processing the collision inside a fabric and between the fabric and other object.

The invention discloses a cross-media sparse Hash indexing method. The method comprises the steps of (1) performing unified modeling on incidence relations among data of a plurality of modes through hyper-graphs; (2) learning dictionaries of the plurality of modes simultaneously through a dictionary learning frame, applying regular constraint to sparse and hyper-graph incidence relations and learning data of each mode to obtain corresponding dictionaries; (3) using the learned dictionaries as Hash functions, and performing Hash encoding on new data through corresponding mode dictionaries; (4) converting the Hash codes into sparse code sets through corresponding Hash strategies to change sparse code similarity calculation problems into the set similarity calculation problems, and performing similarity calculation through a similar jaccard distance measurement mode.

The invention relates to a de-noising method based on external block autoencoding learning and internal block clustering. The method comprises learning block structure features from an external clean natural image block by using an autoencoding model in deep learning, reducing dimensions of a noise image by using the features, achieving block clustering within a whole image range by using a strategy from coarse to fine, constructing a lowrank regular constraint in each class, constructing a global constraint in all classes, establishing a total energy function, and de-noising the target image by means of energy minimization. The method assists internal block clustering de-noising of an image to be tested by using the external natural image block structure information, and solves a problem that a conventional de-noising method is not good in de-noising effect on natural images corroded by Gaussian white noise.

The invention discloses a time compression reconstruction method based on a multi-scale coded aperture and a multi-regular constraint, which utilizes the motion characteristic of a target scene as a fusion basis and adopts a multi-scale coded aperture and a multi-regular constraint reconstruction method to realize super-time resolution restoration of a compressed perceptual video sequence image ofa fast moving scene. This method can guarantee the definition of the moving foreground and static background of the target, and improve the efficiency of the reconstruction algorithm. According to the sparsity of the target scene, the algorithm uses the multi-scale observation matrix to realize the twice coding of the aperture, which can realize the fast reconstruction of CACTI. Using the sparseproperty of the target scene in transform domain as a priori knowledge, the reconstruction constraint is constructed, ADMM algorithm is more robust to noise and motion blur than the existing reconstruction algorithm, which can improve the reconstruction effect of video compressed sensing under high noise or high frame rate.

The invention provides a weighted Huber constraint sparse coding-based face recognition method. The method includes the following steps that: with a regression classifier adopted as a basis for face recognition, and L1 regular constraint introduced, sparsification is performed on the coding coefficients of query samples in a training sample set X, so that a sparse coding model is obtained; on thebasis of the sparse coding model, the Huber loss function is used to replace an L1 fidelity term or an L2 fidelity term, so that a sparse robust coding model is obtained; the weight of each pixel point in the training sample set is obtained according to the residuals of the training sample set and the query samples; on the basis of the sparse robust coding model, a weighted Huber constraint sparsecoding model is obtained through using the weights and the threshold of the Huber loss function; the residual vectors of the query samples in the training sample set X are obtained according to the coding coefficients of the query samples; and the recognition rate of the query samples in an occlusion environment is analyzed according to the residual vectors. With the method of the invention adopted, intra-class variation is effectively reduced, inter-class interference can be avoided, the effect of the weight vectors can be enhanced, and a recognition rate can be improved.

The invention discloses an image deconvolution method based on super laplace apriori constraint. The image deconvilution method comprises the following steps: firstly carrying out deconvolution on an image using a super laplace hypothesis apriori constraint deconvolution method to obtain a vivid image as a reference image Ig; secondly carrying out edge detection on the reference image utilizing a canny operator, and performing morphological dilation on the obtained image to obtain an image flat region and an image texture region; thirdly applying the standard a Richardson-Lucy algorithm to the texture region and applying the Richardson-Lucy algorithm of super laplace apriori regular constraint to the flat region to obtain an image If more vivid than the reference image; and finally carrying out bilateral filtering on the image If to obtain an image detail layer Id which is finally added to the vivid image If to obtain a vivid image I. With the adoption of the image deconvolution method, the ringing effect and further noise amplification can be restrained through the combination of the standard Richardson-Lucy algorithm and the super laplace apriori deconvolution method, and meanwhile much more image detailed information is kept.

The invention discloses an inconsistent image blind restoration method based on sparse representation. The method comprises steps of: creating an inconsistent image fuzzy degeneration model depending on a camera three-dimensional shaking model in combination with over-complete dictionary representation of a natural image; inputting a fuzzy image to be restored and an over-complete dictionary to solve an initial sparse coefficient and initializing a parameter; using the over-complete dictionary representation of the natural image sparsity of the fuzzy core and sparse coefficient as the regular constraint of the model, and transforming the resolution of the inconsistent blind image restoration model into multiple simple subproblems by using an alternate iteration method so as to achieve blind restoration of the fuzzy image y. The method has better restoration effect on the fuzzy image acquired on natural condition, achieves restored images with clear details, no distortion, and low noise, has better visual effects and extendibility.

The invention discloses a 3D face image reconstruction method, a 3D face image reconstruction device, a three-dimensional face image reconstruction hardware device and a computer-readable storage medium. The 3-D face image reconstruction method comprises the steps of acquiring real 2D face key points and predicting 2D face key points; iteratively optimizing the expression coefficients by solving the first loss function which is composed of the real 2D face key points, the predicted 2D face key points and the preset additional regular constraint terms. The expression coefficients are used to represent the real state of the face, and the 3D face image is reconstructed according to the expression coefficients. The expression coefficients are optimized iteratively by the first loss function which is composed of the predicted two-dimensional face key points and the preset additional regular constraint terms to constrain the expression coefficients, so that the expression coefficients can represent the real state of the face, and the 3D face image reconstruction technology can be optimized to obtain the real state of the face.

The invention discloses a modeling method and a modeling system for a reef type reservoir body. The method comprises the steps of based on seismic data, recognizing the reef type reservoir body development layer section of a single well, and determining the reef type reservoir body development layer section; based on the reef type reservoir body development layer section, obtaining a reef type reservoir body deposition microfacies plane distribution diagram; based on the reef type reservoir body development layer section and a vertical evolution sequence, obtaining a reef type reservoir body reservoir development mode, and establishing a reef type reservoir body configuration database; based on the reef type reservoir body deposition microfacies plane distribution diagram and a seismic inversion data body, obtaining a reef type reservoir body distribution probability body through combining geological stratification and seismic interpretation levels; and based on the reef type reservoirbody configuration database, the reef type reservoir body reservoir development mode and the reef type reservoir body distribution probability body, establishing a reef type reservoir body three-dimensional geological model. According to the invention, by reinforcing the geological mode and the regular constraint, the high-precision reef type reservoir body modeling is realized.

The invention provides a diffracted wave field extraction method and device, and relates to the technical field of diffraction field extraction. The method includes: obtaining a pre-stack common-offset gather data in an area to be processed, wherein the pre-stack common-offset gather data carries the stratum interface information in the area to be processed; on the basis of plane wave decomposition on the pre-stack common-offset gather data, transforming the local dip angle of a reflected wave by curvelet transform and then performing regular constraint by using the L0 norm so as to obtain thefirst objective function of the diffracted wave field to be extracted relative to the local dip angle of the reflected wave; and solving the target reflection wave dip angle by a trust region algorithm, wherein the target reflection wave dip angle is the reflection wave dip angle when the first objective function reaches the minimum; and determining the diffraction wave field to be extracted by combining the target reflected wave dip angle, the pre-stack common-offset gather data and the first objective function. The method and device alleviate a technical problem that the diffraction wave extracted by the traditional diffraction wave extraction method is poor in accuracy.

The invention discloses a method for constructing cost function by a compressed video super resolution reconstruction method; in the method, firstly, dividing MAP reconstruction cost function into three parts: a reconstruction error term, a regular constraint term containing distribution parameters of coefficient before quantification and a general constraint term; secondly, reckoning a precise quantification noise model; then, establishing a high resolution image reconstruction error item; afterwards, calculating DCT distribution parameter variance before quantification of low resolution image obtained from high resolution image degradation, minimizing the difference with the original distribution parameter variance, establishing the regular constraint term containing frequency domain coefficient distribution parameters; finally, constructing a reconstruction cost function containing double domains and double variants by the three items. The invention introduces frequency domain distribution coefficient into the calculation of the quantification noise model, so that the calculated quantification noise model is more precise, the cost function constructed based on the quantification noise degradation model is more precise, and the construction quality of compressed video supper solution is improved.

The invention relates to a semi-supervised audio event identification method based on depth mutual information maximization. A semi-supervised neural network model is used as a backbone, a depth mutual information maximization consistency-based regular constraint and a cross entropy classification constraint are designed, a semi-supervised learning model is constructed, a mutual information discriminator is designed to estimate mutual information between deep representation vectors of the model, the model mines potential relations between samples through global mutual information so as to enhance consistency and nonlinear correlation between global representations, and a semi-supervised audio event classification model with high robustness is obtained; and neural network model parameters are optimized by using a gradient descent method, and the audio event samples are classified. The method has the advantages of being small in error, high in robustness, high in precision and the like,the requirement for sound event classification can be met under the condition that label data is insufficient, and high application value is achieved.

The invention discloses an MVCT image texture enhancement method based on double regular constraints, and mainly solves the problem that MVCT image enhancement cannot be carried out in the prior art.According to the scheme, the method comprises the following steps: 1) acquiring a plurality of KVCT and MVCT images from the same part of a human body; 2) normalizing the obtained CT image data set, and taking blocks from each pair of CT images to obtain a CT image block data set; 3) establishing a 13-layer MVCT image texture enhancement network, using the CT image block data set as training data,and optimizing the network by using a gradient descent algorithm to obtain a trained network; and 4) inputting a complete MVCT image into the trained network, and outputting the enhanced MVCT image.According to the invention, while the image texture is enhanced, the edge and details of the image can be well maintained, the image quality is improved, a doctor can conveniently read and diagnose the MVCT image, the focus position error is corrected, and the radiotherapy accuracy is ensured.

The invention relates to the technical field of social network services, and discloses a symbol network community discovery method based on structural balance constraint. The method comprises the steps of representing a symbol network in a graph form, constructing a symbol network adjacent matrix, setting structural balance constraint information, constructing a community discovery model based onsemi-non-negative matrix decomposition, solving the community discovery model, and obtaining a community discovery result. According to the method, the structure balance constraint relation of nodes is obtained based on the structure balance theory; and then the structure balance constraint relation serving as a regular constraint term is incorporated into a symbol network community discovery model based on semi-non-negative matrix decomposition to solve the node community indication matrix, and finally, a community division result is obtained by judging the node community attribution intensity, so that the community discovery quality is further improved.

The invention relates to a regular auto-encoding text embedded expression method for local topic probability generation and belongs to the field of natural language processing and machine learning. The method comprises the steps of firstly, implementing construction of a text set neighbor graph, which includes calculation of similarity weight of any text word pair, search of a maximum weighted matching distance of the text pair, calculation of the similarity of an averaged maximum weighted matching distance (NMD) and selection of a k-nearest neighbor according to an NMD result and constructionof the neighbor graph with the NMD result as an edge weight; then, constructing a sub-space through a transductive multi-agent random walk process through the neighbor graph to determine the sub-space; and finally generating a pseudo-text by use of an LDA (Latent Dirichlet Allocation) model of the sub-space, taking the pseudo-text as a regular constraint item, taking the pseudo-text and a real text as a reconfiguration object of an auto-encoding network, guiding the encoder network to confront the change of a local neighbor text topic probability generation structure so as to construct smoothaffine mapping. According to the regular auto-encoding text embedded expression method for local topic probability generation, the smoothness of the local neighbor text topic probability generation structure can be effectively kept, thereby constructing a smooth affine mapping function, enhance intra-class compactness and inter-class separation of an out-of-sample text embedded representation vector and improving application effects such as text classification and clustering.

The invention discloses a traffic big data filling method based on a tensor train decomposition model. The method comprises the following steps: constructing a five-dimensional tensor model containingfive traffic data dimensions; constructing an initial filling model based on a tensor train decomposition model through L2 regular constraint; performing conjugate gradient optimization on the filling model to obtain an optimized filling model of each kernel vector; or performing trace norm optimization on the filling model to obtain a final filling model; and performing traffic big data fillingthrough the first filling model and / or the second filling model. According to the method provided by the invention, the data filling precision can be improved, and the filling stability can be maintained at a high loss rate.

The invention relates to an adaptive target tracking method based on PSPCE. A target to be tracked is determined in a tracking sequence, the current frame of the target is the tth frame, and the method comprises the following steps: S1, defining a search box according to the area position of the target in the previous frame, and calculating the feature map of an image block in the search box; s2,calculating the response of the filter and the feature map, and determining the target position of the current frame; s3, updating a PSPCE confidence sample filter queue according to the PSPCE coefficient to obtain a PSPCE confidence sample of the current filter; s4, adaptively updating the parameters of the current filter based on PSPCE regular constraints; and S5, repeating the steps S1 to S4 frame by frame until tracking of the tracking sequence is completed. According to the method, the correctness of the adaptive filter in the updating process can be ensured, the high-confidence filter can be selected on the time axis to update the PSPCE confidence sample, the situation that the filter suddenly changes under various changes of the appearance of the target is effectively prevented, andthe accuracy of target tracking is ensured.

The invention discloses a fine-grained image recognition method based on multi-target Lagrange regularization, and the method comprises the steps: extracting an image feature X of an input image through a neural network, and obtaining a corresponding bilinear image A; obtaining a regularization feature Y from the bilinear image A, and constructing a target function containing a matrix square root,a low rank and a sparse constraint item; introducing two auxiliary variables to weaken the relevance among the three constraint items, converting the target function into an augmented Lagrange form,and alternately optimizing each matrix constraint item to obtain a global approximate optimal solution; and utilizing the global approximate optimal solution to carry out image identification and classification. The method only comprises matrix multiplication, so that the method can be well compatible with a GPU (Graphics Processing Unit), a higher recognition speed is achieved, regular constraints of square root, low rank and sparsity can be effectively carried out on bilinear image expression at the same time, and the recognition accuracy is greatly improved.

The invention relates to a self-encoding document representation method using random walk, belonging to the field of natural language processing and machine learning. The goal is to solve the text topic modeling problem. A self-encoding network is adopted; for a given text set, we first use a sparse self-encoding network to construct sparse topic coding of text; then we construct a text neighbor graph based on text similarity measure, generate a random walk structure by applying low rank constraint to the text neighbor graph, and calculate weighted coefficients of the local neighbor text by aconditional access probability of the random walk structure; finally, the sparse topic encoding of the local neighbor text is utilized to perform weighting and embed an intrinsic geometric structure for characterizing the text manifold, to serve as a regular constraint term to fuse into the training of the self-encoding network, and a parameterized topic coding network is established to perform topic modeling on external text of a sample. The self-encoding document representation method has the advantages of being high in accuracy and operation efficiency and capable of modeling the external topics of the text. The method is suitable for the field of text topic modeling which requires high precision, has a great impetus for the development of text representation, and has a good applicationvalue and promotion value.

The invention discloses a non-negative image data dimension reduction method based on Hessian regular constraint and A optimization. The method includes the steps that step1, a sample feature matrix is constructed; step2, a Hessian regular matrix is calculated; step3, a basis matrix and a coefficient matrix are iteratively output so as be analyzed in a clustered mode. An A optimization regular item and a Hessian regular item are added into a target function so that a data expression obtained through decomposition can keep inherent features included in the manifold-shaped structure of original data while guaranteeing a small prediction error; through dimension reduction, redundancy information in the high-dimension data is removed, the low-dimension expression capable of accurately expressing the semantic structure of the data is extracted, and therefore clustering analysis performed on the high-dimension data becomes simpler and more effective.

The invention discloses a method for constructing cost function by a compressed video super resolution reconstruction method; in the method, firstly, dividing MAP reconstruction cost function into three parts: a reconstruction error term, a regular constraint term containing distribution parameters of coefficient before quantification and a general constraint term; secondly, reckoning a precise quantification noise model; then, establishing a high resolution image reconstruction error item; afterwards, calculating DCT distribution parameter variance before quantification of low resolution image obtained from high resolution image degradation, minimizing the difference with the original distribution parameter variance, establishing the regular constraint term containing frequency domain coefficient distribution parameters; finally, constructing a reconstruction cost function containing double domains and double variants by the three items. The invention introduces frequency domain distribution coefficient into the calculation of the quantification noise model, so that the calculated quantification noise model is more precise, the cost function constructed based on the quantification noise degradation model is more precise, and the construction quality of compressed video supper solution is improved.

The invention relates to a trusted verification method for uniform function and performance of a combinational internet of things service, which comprises the following steps: a. According to the requirements of the combinational internet of things service, performing task partitioning and constructing a candidate service library; b. Designing a combinational service script based on extended BPEL,dividing a state space according to service execution conditions, calculating parameters, and converting the script description into a continuous time Markov return process; c. Describing verification properties of uniform function and performance based on the extended asCSL temporal logic; d. Converting the regular expression in a logic formula into a non-deterministic finite automaton, seekinga product model of the non-deterministic finite automaton and the continuous time Markov return process of the combinational internet of things service, and marking a path set satisfying a regular constraint; e. In the product model, using the model detection technique to perform reachability analysis, and calculating a probability value, so as to obtain a satisfiable state set. The trusted verification method for uniform function and performance of a combinational internet of things service in the invention can provide a credible guarantee for uniform function and performance of the combinational internet of things service at the time of design.

The invention provides an incremental learning method and device, electronic equipment and a machine readable storage medium, and the method comprises the steps: initializing an incremental model according to an initial model in an incremental training process, and obtaining an initialized incremental model; according to incremental training data and the initial training data, training the initialized incremental model to obtain a trained incremental model; wherein in the incremental training process, regular constraint is carried out on the initial model and the incremental model according to a regular strategy; the regular constraint comprises a regular constraint of a feature level and / or a regular constraint of a parameter level. The method can relieve the forgetting of old knowledge in the incremental learning process.

The invention provides a neural network processing method and device, a storage medium, and an electronic apparatus, wherein the method comprises: determining an objective function in a convolution neural network, wherein each layer of the objective function corresponds to an initial network weight value, and the convolution neural network is applied to at least one of face recognition, vehicle detection, and object recognition; processing the initial network weights according to preset regular constraint coefficients to obtain target network weights; using the target network weights and input values to an output value in the objective function. The invention solves the technical problems of slow convergence and low precision of convolution neural network in the prior art.

The invention discloses a query expansion method based on multisource positive and negative external feedback information. An expansion risk is reduced by introducing a regular constraint into a processing of fusing external query information; therefore, new query can be rapidly and effectively built, and thus a search result more conforms to user needs. Compared with a traditional feedback search method, the technical scheme of the method provided by the invention has the effect of significantly enhanced performance.