278 results about "Correlation matching" patented technology

Systems and methods for automatically and generically matching models are provided, such as may be provided in a matching application or matching component, or provided in a general purpose system for managing models. The methods are generic since the methods apply to hierarchical data sets outside of any particular data model or application. Similarity coefficients are calculated for, and mappings are discovered between, schema elements based on their names, data types, constraints, and schema structure, using a broad set of techniques. Some of these techniques include the integrated use of linguistic and structural matching, context dependent matching of shared types, and a bias toward subtree, or leaf, structure where much of the schema content resides.

A method and system are disclosed for generating content relevant to at least one participant based on data associated with the at least one participant. Profile data and behavior data may be captured in a database for the at least one participant. A processor may be employed to determine matches between the at least one participant and information including products, services, companies, persons and / or other data based on a set of criteria defined from the profile and behavior data of the at least one participant and attributes associated with each item of information.

A position detection apparatus of the electrostatic coupling type is provided, to detect not only a position of a pointer but also information other than the position information such as, for example, pointer pressure or side switch information. The pointer transmits two codes such that a pressure applied to a pen tip is associated with a time difference between the two codes. A position detector carries out a correlation matching operation between signals generated in reception conductors and correlation calculation codes corresponding to the two codes, to thereby detect a position on a sensor section pointed to by the pointer from a result of the correlation matching operation and based on at least one of the codes. The position detector further includes a pressure calculation circuit for detecting pressure applied to the pointer, which is associated with the time difference between the two codes, from the result of the correlation matching operation calculated by the correlation matching operation and based on the two codes.

The invention discloses a binocular stereo vision based intelligent three-dimensional human face rebuilding method and a system; the method comprises: preprocessing operations including image normalization, brightness normalization and image correction are carried out to a human face image; a human face area in the human face image which is preprocessed is obtained and human face characteristic points are extracted; the object is rebuilt by projection matrix, so as to obtain internal and external parameters of a vidicon; based on the human face characteristic points, gray level cross-correlation matching operators are expanded to color information, and a parallax image generated by stereo matching is calculated according to information including polar line restraining, human face area restraining and human face geometric conditions; a three-dimensional coordinate of a human face spatial hashing point cloud is calculated according to the vidicon calibration result and the parallax image generated by stereo matching, so as to generate a three-dimensional human face model. By adopting the steps, more smooth and vivid three-dimensional human face model is rebuilt in the invention.

Systems and methods for automatically and generically matching models are provided, such as may be provided in a matching application or matching component, or provided in a general purpose system for managing models. The methods are generic since the methods apply to hierarchical data sets outside of any particular data model or application. Similarity coefficients are calculated for, and mappings are discovered between, schema elements based on their names, data types, constraints, and schema structure, using a broad set of techniques. Some of these techniques include the integrated use of linguistic and structural matching, context dependent matching of shared types, and a bias toward subtree, or leaf, structure where much of the schema content resides.

A method, system and computer program product for transformation, normalization and correlation techniques that are effective for matching names of foreign origin that may be spelt in any number of ways. It addresses the problem of matching names that may belong to the same person but may be spelt differently. The main technique is to convert both strings to be matched into a representation of their original language, i.e., transform them into idealized (normalized) versions of themselves based on their true spelling in their original, native language. This process of idealization can be done either by employing a dictionary of standard, idealized names, or by implementing the idealization in real time by following a finite-state algorithm to convert the strings into their true representation in their original language. The idealization process can be viewed as a phonetic searching method, as it resolves the problem of vowel representations or their incorrect use as well as handling the representation of consonants that do not exist in the English language. Further probabilistic and elastic matching techniques, using a correlation function, can be invoked manually or automatically to match names where the quality of or the completeness of names may be suspect. A new approach to "probabilistic" and "sliding-elastic" matching (which give a level of confidence as a percentage against each match) can be used with or without the phonetic (idealized) searching function. The results of the search are displayed on the computer screen or printed, showing all the successful matches, together with the type of search that has been used to obtain the match. Results can be filtered by comparing attributes of the persons associated with the Suspect and Data names (such as age, country of birth, etc.) to minimize reporting on irrelevant matches.

An apparatus and method for ultrafast real-time optical imaging that can be used for imaging dynamic events such as microfluidics or laser surgery is provided. The apparatus and methods encode spatial information from a sample into a back reflection of a two-dimensional spectral brush that is generated with a two-dimensional disperser and a light source that is mapped in to the time domain with a temporal disperser. The temporal waveform is preferably captured by an optical detector, converted to an electrical signal that is digitized and processed to provide two dimensional and three dimensional images. The produced signals can be optically or electronically amplified. Detection may be improved with correlation matching against a database in the time domain or the spatial domain. Embodiments for endoscopy, microscopy and simultaneous imaging and laser ablation with a single fiber are illustrated.

The invention discloses an automatic collecting method of high-resolution satellite remote sensing traffic flow information. The automatic collecting method comprises the following steps of: A. pretreatment: registration of panchromatic images and a vector road network as well as panchromatic and multi-spectral images, road region division and double edge filtering strengthen; B. acquiring a vehicle sample characteristic value by visually judging a road region image obtained in the step one, and establishing a vehicle remote sensing image feature library; C. carrying out rough neural network vehicle extraction and fine facing objective vehicle extraction on the panchromatic images obtained in the step two; D. by utilizing a matching method relative to an image frequency domain, searching the vehicle position in fine extraction in the step three in multi-spectral images and carrying out matching; E. calculating a displacement amount of a same vehicle in the panchromatic and multi-spectral images according to the corresponding vehicle position obtained in the step three and the step four, thus estimating traffic flow parameter information; and F. verifying the traffic flow parameter information through precision evaluation. With the adoption of the method, static and dynamic traffic flow information in a large range series can be automatically and rapidly collected, the efficiency is high, and the method is simple and practicable.

The invention discloses a vision extensometer implementation method based on digital speckles. The method includes the first step of speckle and mark making, the second step of binocular camera calibration, the third step of speckle image acquisition, the fourth step of image subarea specifying, the fifth step of image correlation matching, the sixth step of three-dimensional coordinate reconstruction and the seventh step of deformation calculation. Through the operating steps, the vision extensometer implementation method based on the digital speckles can be used for accurately measuring the deformation of materials in the tensile experiment process and has the advantages of being convenient to operate, capable of achieving non-contact measurement, accurate and reliable in measuring result and the like.

The invention provides a medication information processing method, a system and a device. The method comprises: establishing a multidimensional attribute item dictionary; extracting medicament using element information; processing the medicament using element information according to the multidimensional attribute item dictionary; extracting patient medication-related element information; processing the patient medication-related element information according to the multidimensional attribute item dictionary; processing the correlation matching degree of attribute items in the medicament using element information and the patient medication-related element information; and generating medication reasonability information. With the medication information processing method, the system and the device of the invention, a great number of medication data can be analyzed and processed by informatization technology, and the medication reasonability is normalized.

The invention provides a method for counting passenger flow of buses in real time, which adopts means of machine learning, multi-target detection and tracking, target behavior analysis and the like, and belongs to the technical field of pattern recognition. The method comprises the following concrete steps: detecting passenger targets by analyzing shape information and texture information of passenger heads in video images, wherein a column diagram in a gradient direction is used for representing the shape information, and a column diagram in a local binary mode is used for representing the texture information; then, accurately positioning passengers by adopting the target tracking policy combining gray level cross-correlation matching tracking and mean translation algorithm searching tracking; and finally, judging the behavior characteristics of the passengers by analyzing the moving tracks of the passengers, thereby accurately counting the passenger flow of buses. The practice shows that the method provided by the invention can provide an accurate and reliable basis for realizing intelligent scheduling of buses for bus companies, analyzing the acceptability of mobile media advertisements in buses, and the like, and the invention has very high practical value.

The invention discloses a real-time infrared image target tracking method which comprises the following steps of: inputting an infrared image, carrying out strengthening treatment on the image and outputting a strengthened image; inputting n image templates and respectively carrying out correlation matching on the n image templates in a wave door area to obtain n correlation values and correlation matching positions, wherein n is a natural number which is larger than 1; updating n template images according to the correlation values and the correlation matching positions, deciding the final target matching position of the frame by combining the n correlation values, the n target matching positions and tracking calculation information and outputting a target matching position; maintaining the estimation on a target tracking state by utilizing a Kalman filter according to the target matching position and outputting a tracking wave door area; and inputting a new frame of image and returning to the first step. The invention has the advantages of strengthening the edge and detail information of an infrared image by using a sharpening filter, improving the definition of the infrared image and being beneficial to improving the target tracking stability by a plurality of templates.

The invention provides an intelligent auditing system for serious illness medical insurance. The system includes a database module, an intelligent auditing engine and a basic information base management module, wherein the database module is used for obtaining serious illness medical insurance data, the intelligent auditing engine is used for performing auditing processing on the correlation matching degree of attribute items of the serious illness medical insurance data, the basic information base management module stores attribute information of basic data, and the intelligent auditing engine is connected with the database module and the basic information base management module and completes auditing processing of data of the database module and the basic information base management module. Through the technical content provided by the invention, medical insurance data can be audited rapidly, a deduction strategy can be executed automatically on illegal medical insurance data, and auditing personnel only needs to perform manual auditing on part of invoices where problems exist, thereby improving auditing efficiency.

The invention discloses a general video flexibility measurement system insensitive to ambient light. The general video flexibility measurement system comprises a black-and-white industrial camera (1), an industrial fixed-focus lens (2), an electronic theodolite (3), a distance measurement machine (4), a tripod (4), a high brightness monochromatic LED target (6), a narrow bandpass filter sheet (7) corresponding to monochromatic light source wavelength and a computer (8); a monochromatic LED target is installed on a tested point; a video flexometer with the narrow bandpass filter sheet installed on the lens is utilized to record the video image of the LED target in real time; and flexible data is obtained in real time through an image tracking algorithm on the basis of image gray correlation matching or characteristic points extraction. The general video flexibility measurement system is insensitive to the change of ambient light, can realize high precision measurement for displacement or flexibility at daytime or nigh, can calculate multiple object positions in one image, and realizes real-time dynamic measurement of displacement or flexibility of multiple detected points.

The invention relates to an image matching method, comprising the following steps: (1) collecting images to be matched by an image collector and extracting template images from an image processor; (2) reducing the images to be matched and template images by half in the directions of width and height; (3) repeating step (2) until the images to be matched and template images reach specified sizes and carrying out gray scale normalization cross correlation matching on the reduced images to obtain the optimal matching positions (x, y); (4) returning to the previous images which are reduced by half and carrying out further matching on 9 search positions within the range of ((2x-1)-(2x+1), (2y-1)-(2y+1)) to obtain new optimal matching positions (x, y); (5) repeating step (2) until returning to the primary image, namely the original image, and carry out final matching to obtain the optimal matching positions and matching values. The method features shorter matching time and smaller amount of calculation.

An apparatus and method for ultrafast real-time optical imaging that can be used for imaging dynamic events such as microfluidics or laser surgery is provided. The apparatus and methods encode spatial information from a sample into a back reflection of a two-dimensional spectral brush that is generated with a two-dimensional disperser and a light source that is mapped in to the time domain with a temporal disperser. The temporal waveform is preferably captured by an optical detector, converted to an electrical signal that is digitized and processed to provide two dimensional and three dimensional images. The produced signals can be optically or electronically amplified. Detection may be improved with correlation matching against a database in the time domain or the spatial domain. Embodiments for endoscopy, microscopy and simultaneous imaging and laser ablation with a single fiber are illustrated.

The invention discloses a correlation method of text information and geological information and a system. The method comprises the following steps: an original text is received, and the original text is of text information; the original text is undertaken the geological key word analysis so as to obtain a first geological key work information gather in the original text, and a second geological key word information gather is obtained through conflict verification; each geological key word information in the second geological key word information gather is searched one by one so as to obtain a geological element matching information gather; and the matching information with the highest matching degree is set up as the correlation of the geological key word information. The system comprises a receiver, an analysis device, a searching device and a correlation matching device. The correlation method and the system improve the expression richness of the text information with the geological characteristics.

The invention relates to an electronic image stabilizing method for digital videos, belonging to the technical field of digital image processing. The method comprises the following steps of: firstly, extracting characteristic points in two adjacent images in a video sequence by utilizing an SUSAN corner detection operator, matching the characteristic points by utilizing a relevant matching method and rejecting false matching point pairs; then selecting three pairs from the correct matching point pairs and solving for an affine transformation parameter between two images by utilizing a corresponding coordinate relation of the matching point pairs on a two-dimensional image; and finally, carrying out an affine inverse transformation on a next image according to an affine formula to obtain an image registered with a previous image in space so as to realize the electronic image stabilization of the digital videos. The electronic image stabilizing method of the digital videos can automatically eliminate jitters of the video images in real time, wherein the jitters comprise translations and rotating movements among images.

The invention discloses a recognition method based on a brain wave, and belongs to the technical field of biological recognition. The method directly achieves the matching of an original brain wave signal with a user based on a deep learning frame, and also can achieve the brain wave signal recognition of the motion of a user at the same time, removes the existing signal processing and feature extraction operations, and greatly simplifies a conventional brain wave identity recognition model. Meanwhile, the brain wave signal is taken as the model input after cutting, thereby reducing the depthand dimension of a data input model. Because the brain wave signal is an unstable signal, a self-adaption moment estimation optimization algorithm is selected as an optimization algorithm so as to reduce the adverse impact in the performances of the algorithm from the unstable brain wave signal. An LSTM (Long Short Term Memory) model in an RNN (Recurrent Neural Network) is introduced to a deep learning model for achieving user correlation matching, and a convolution neural network model is employed for achieving the motion classification of the brain wave. The method greatly reduces the computing complexity of brain wave verification under the condition that the recognition accuracy is guaranteed.

The invention discloses a fast tracking recognition method for overlapped fruits by a picking robot. The fast tracking recognition method comprises the following steps: continuously collecting the latest ten frames of overlapped apple images through a camera; segmenting the collected first frame of image, and removing a background; determining the position of the circle center of overlapped apples by calculating the maximal value of the minimal distance from points in a circle to the edge of an outline; calculating the distance from the circle center to the edge of the outline to determine a radius; intercepting a subsequently matched template according to the circle center and the radius; determining the circle centers of overlapped apples in the continuously collected latest tens frames of images, and carrying out fitting and pre-judging on the motion path of the robot according to the circle center of each frame of image; determining the positions of overlapped apples in a next frame of image by synthesizing the radius and the pre-judging path, and intercepting the area of the overlapped apples; finally carrying out matching recognition by adopting a rapid normalized cross-correlation matching algorithm. According to the method, tracking recognition of near-spherical overlapped fruits such as the overlapped apples can be achieved; the running time is short; the picking efficiency of the picking robot can be effectively improved.

The invention discloses a highway real-time traffic monitoring method based on mobile phone signaling. The method comprises the following steps: first, performing wireless network coverage test along a highway, carrying out 'virtual monitoring point' modeling, and obtaining base station positioning reference data along the highway; then, acquiring and parsing Mc interface signaling data, obtaining call behavior information of users, and establishing a single-user traffic event tracking model; and using a highway user recognition model to screen out highway user data, performing correlation matching on the highway user traffic event tracking result and the base station positioning reference data to calculate the average driving speed of highway users, and outputting highway traffic monitoring results according to road sections. According to the method, by introducing network measured data in model correction, the accuracy of highway real-time traffic calculation based on the signaling positioning technology is greatly improved, fusion of the mobile communication technology and intelligent highway management is realized, and convenient and accurate real-time traffic information is provided for highway traffic and management.

Methods and systems for 3D shape retrieval are described herein. An embodiment includes receiving a query 3D model, extracting a plurality of features of the query 3D model, comparing the features of the 3D query model against a plurality of features of one or more 3D models in a repository, calculating a similarity score based on the comparing step, ranking the 3D models based on the similarity score and returning one or more 3D models based on the ranking step. The embodiment further includes generating a representation of the query 3D model, calculating a correlation matching function between the representation of the query 3D model and representations of 3D models in the repository, determining a plurality of matching scores between the query 3D model and the 3D models in the repository for each rotational alignment of the 3D models and selecting the highest score from the plurality of matching scores based on the determining step.

The invention belongs to the technical field of digital communication, and particularly relates to a method for automatically detecting asynchronous serial port communication protocol on the basis of level sampling. The method includes firstly sampling level signals of asynchronous serial port communication, and detecting asynchronous serial port communication Baud rate according to the relation of the asynchronous serial port communication Baud rate and average time span of a single low level of the sampled signals; secondly, determining data frame bit digits and data frame positions of target signals which are the detected level signals by Baud rate by means of stop bit correlation matching algorithm; thirdly, analyzing in-frame data and inter-frame bit distance to determine data bit digits, checking manners and stop bit digits of the target signals; and finally determining a data coding manner of the target signals by Bayes policy method on the basis of the minimum error rate. The method can be applicable to communication protocol detection of communication and data transmission equipment utilizing the asynchronous serial port communication protocol.

The invention discloses a vehicle speed matching method based on linear array CCD image, including the following steps that: two linear array CCD video cameras are respectively arranged on two sections positioned on a road at intervals; both linear array CCD video cameras face downwards and are provided with infrared ray laser source; the frame rate of each CCD video camera is more than 1,000 frames per second, and the resolution is more than 1,024 lines; correlation matching computation of the image sequences obtained by both linear array CCD video cameras is carried out to obtain the time difference of the same object in two image sequences; finally, by means of the time difference and the distance between both cameras, the driving speed of an object vehicle can be obtained according to the velocity formula V=s / t. The invention is suitable for vehicle speed measurement at a traffic station, etc.

The invention discloses a local citation recommendation system and method based on deep correlation matching. The method carries out the embedded representation of a word through a pre-trained multilayer language model, obtains the more contextualized representation of the word, and solves a problem that the word embedded representation is not abundant enough in a conventional method. According tothe invention, the problem of semantic fuzziness in a deep semantic matching method is solved. The interactive matrix learning is established for the citation context and the candidate paper content,so that the problem of great influence of a traditional model recommendation effect caused by great text length difference is solved. According to the method, the author network is innovatively constructed, the problem that the use characteristic is single in a traditional local citation recommendation method is solved, author information with the highest influence and correlation is fused into the model, and author characteristics and correlation characteristics are fully combined. According to the method, the same MLP network is used for learning each correlation feature, so that neural network parameters are effectively reduced, and the possibility of model over-fitting is reduced.

The invention discloses a method for positioning a tiny crack on the surface of concrete, which is based on a related technique of a digital image. Correlation matching is carried out on two surface images of a concrete structure before and after deformation under the action of a certain load, so as to obtain the spatial position of each point before and after deformation on the surface in a full field; the change of the spatial position is a placement field; accurate stress field distribution can be obtained through fitting optimization and differential processing on the curved surface; and the features of the stress field distribution can be automatically identified by a computer so as to judge a strange region, thus the position of the crack is judged. The method disclosed by the invention can be used for identifying the position of the tiny crack on the surface of the concrete; as for the sample the maximum three-dimensional size of which is 10m, the tiny crack the width of which is more than 10 microns can be identified, and the advantages of no contact and no damage on the sample can be achieved.

The invention discloses a train wheel set bearing fault transient characteristic detection method based on a parametric Doppler transient model. The method comprises the following steps: building a parametric cycle model based on a unilateral Laplace wavelet; building a parametric Doppler transient model according to the Doppler effect; performing correlation matching between the parametric Doppler transient model and a train bearing fault detection signal, and calculating the correlation coefficient; optimizing the cycle parameter T, damping coefficient zeta and discrete frequency f by taking the correlation coefficient between the built parametric Doppler transient model and a real train bearing fault signal as a quantitative means, and building an optimal periodic transient model and a Doppler transient model thereof; and finally, judging the fault type based on the model optimal parameters and bearing motion parameters. By using the method, a train bearing signal under the influence of the Doppler effect can be processed, and the fault of the bearing can be diagnosed accurately.

The present invention relates to a frequency modulated continuous wave speed measurement and distance measurement method. The method comprises the steps of S1 transmitting a frequency modulated continuous wave signal of which the frequency changes along a combined waveform modulating signal to N targets, and obtaining a corresponding beat signal; S2 carrying out the one-dimensional FFT processing of a fast time domain on the beat signals within a cycle TTa and a cycle TTb to extract the spectral peak frequencies corresponding to the N targets in the cycle TTa and the cycle TTb; S3 calculating to obtain the corresponding distance speed matrixes in the cycle TTa and the cycle TTb; S4 finishing the correlation matching of multiple targets to obtain the distance r and the unambiguous inaccurate speed v corresponding to each target; S5 calculating to obtain the ambiguous accurate speed vapre corresponding to each target; S6 calculating to obtain the unambiguous accurate speed vpre corresponding to each target. According to the present invention, by utilizing an improved modulating signal and combining a two dimension FFT method, the purpose of high-precision speed measurement and distance measurement can be achieved under a smaller FFT point number.

The invention discloses a hyperspectral remote sensing image target detecting method based on variable end members, comprising the following steps of: selecting a remote sensing image to be processed by target detection; acquiring prior information required for detection, wherein the prior information comprises spectral information of target end members and spectral information of background end members; traversing the remote sensing image to be detected by utilizing a cross correlation matching technique to determine the types of background end members in each pixel in the remote sensing image to be detected; carrying out spectral decomposition on the remote sensing image to be detected in a completely restricted least square way to acquire the component information of target end members and various background end members in each pixel in the remote sensing image to be detected; establishing a detector based on the GLRT (Generalized Likelihood Ratio Test); and traversing the remote sensing image to be detected by adopting the detector to acquire the detection function value of each pixel in the remote sensing image to be detected, thereby judging whether targets exist in each pixel in the remote sensing image to be detected or not. The method of the invention has the characteristics of strong structuration, high adaptability, self-organization and self-learning.