131 results about "Image processing software" patented technology

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

The invention relates to a binding material single particle local spatial evolution analysis method, and belongs to the technical field of civil engineering binding material microstructure characterization. The method comprises the following steps: acquiring back scattering (BSE) and characteristic X-ray energy spectrum (EDS) images of a sample; selecting a target gel particle based on the BSE image and intercepting a local area; identifying the reaction edge of the target gel particle; performing equal-width stepped strip division inwards and outwards by taking the reaction boundary as a starting point, and storing the mask; carrying out image operation on adjacent masks to extract strips, and carrying out statistical analysis on gray feature and element feature changes of each strip; according to the method, surrounding phase interference is avoided through local analysis, whole-process analysis is realized by adopting unified image processing software, a programming basis is not needed, the technical threshold is reduced, the operation process is simplified, the uniformity of strip division and the reliability of an analysis result are ensured, and the method is suitable for large-scale popularization and application. And a simple, convenient and effective technical means is provided for revealing the reaction mechanism and quantitative reaction activity of the cementing material.

The invention provides a method for in-situ measurement of an internal stress state of an ultrathin film surface by using RHEED, and relates to the technical field of condensed state substance structure detection, and the method comprises the following steps: epitaxially growing an ultrathin film on a substrate by using film growth equipment; irradiating the ultrathin film by using an RHEED electron beam to obtain a diffraction pattern, and obtaining characteristic parameters of the diffraction pattern; obtaining the lattice constant of the ultrathin film through the characteristic parameters of the diffraction pattern; based on the lattice constant of the ultrathin film, the stress type and strain borne by the ultrathin film are determined. According to the method, the distance between diffraction fringes in a diffraction pattern is accurately extracted from a simple RHEED image, the lattice constant from the diffraction pattern is calculated, the stress state of the ultrathin film is accurately judged by comparing lattice constants in a stress-free state, existing equipment does not need to be greatly modified, and the method is simple and convenient to operate. The method can be realized only by using the existing RHEED electron beam and image processing software.

The invention provides a design method for checking dislocation between layers of a multilayer circuit board, which comprises the following steps of: designing an intelligent positioning identifier at a board corner of each layer, capturing an SPM high-definition image, transmitting the image to a central control system through a high-speed network, designing special image processing software to automatically identify the SPM, and extracting concentric circle and rectangular bar code information; the method comprises the steps of calculating relative position deviation between layers, preprocessing original image data, converting the original image data into structured offset data, establishing a real-time data analysis platform, generating a detailed interlayer offset report, setting a threshold value alarm mechanism, providing a visual interface to display the state and historical trend of a production line, and obtaining a real-time data analysis result based on real-time data analysis. A machine learning algorithm is adopted to predict an offset trend, subsequent process parameters are optimized, interlayer offset in a final finished product is reduced, a dynamic process control system is introduced, operation parameters of production equipment are automatically adjusted according to real-time feedback, and production stability and precision are ensured.

The invention discloses an OpenMC-based BNCT dose full-process automatic calculation output method, and particularly relates to the technical field of boron neutron capture therapy dose calculation, and the method comprises the steps: reading a DICOM-CT image, automatically completing HU value segmentation, material assignment and voxel grid modeling, and generating an OpenMC geometry and material input card; setting a neutron / photon source, an operation mode and a counting grid, and executing Monte Carlo transport calculation; an ICRP flux-dose conversion coefficient library is built in, and dose calculation is automatically completed; the dose field is written into an Rt dose file, and the Rt dose file can be directly imported into mature medical image processing software for visual evaluation and plan optimization. According to the method, end-to-end automation from the CT image to the clinical available dose file is achieved, manual intervention is not needed, the BNCT dose calculation efficiency, precision and standardization level are remarkably improved, and a reliable tool is provided for BNCT dose simulation research.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

The application relates to a scanning electron microscope measurement method for the thickness of a metal compound layer, which comprises the following steps: obtaining a cross section containing the compound layer by wire cutting, and polishing after inlaying; observing under a scanning electron microscope, selecting a copper-tin alloy compound layer to be measured, selecting a backscattering electron probe to obtain a composition contrast image, adjusting the image contrast so that the measured object and the matrix have obvious differences; selecting a magnification of 2500 times matching the thickness of the metal compound layer, obtaining a high-definition backscattering electron image at a scanning speed of 28 seconds / frame; and quantitatively and finely measuring the thickness of the metal compound layer by using ImageJ software. The advantages of the application are as follows: the metal compound layer is extracted by using the ImageJ image processing software, the area is calculated to obtain the average thickness of the film thickness measurement method, not only the accurate alloy layer thickness information is obtained, but also the standard deviation value of the measured object is obtained to evaluate the uniformity of the measured object; the measurement method improves the accuracy and can be applied to detection and analysis practices.

This invention provides a method for determining the carbon dioxide huff and puff mechanism in fractured reservoirs, belonging to the technical field of determining the carbon dioxide huff and puff mechanism in fractured reservoirs. This invention establishes a unified digital core by selecting outcrop cores to create cast thin sections and employing multi-scale fusion reconstruction technology. Topological connectivity is evaluated based on a seepage topological invariant fracture network connectivity evaluation algorithm. During well shut-in, a diffusion-convection hybrid encoding / decoding model is used to predict migration in real time, and the model learning rate is adjusted by a dynamic learning rate adjustment function. After well shut-in, a feedforward-feedback composite control strategy is used to gradually reduce back pressure to complete the production stage. The experiment ends after cleaning the chip with anhydrous ethanol. Finally, the degree of crude oil recovery is statistically analyzed using image processing software. This invention solves the technical problem of not being able to predict the migration process in fractures and matrix of fractured reservoirs in real time during well shut-in.

This invention provides a method for measuring pulsed laser parameters based on titanium nanofilms, belonging to the field of pulsed laser parameter measurement methods. The method first prepares titanium nanoparticle ink; then, a titanium deposition layer is prepared by inkjet printing or spin coating; finally, the titanium deposition layer is placed within the laser scanning range, a single-point or line scanning mode is set, and images of the sintered titanium region are recorded. The corresponding laser parameters are obtained through image processing software analysis. This method can intuitively, conveniently, and cost-effectively obtain key pulsed laser parameters, and can accurately obtain parameters such as spot size and repetition frequency.

The invention relates to the technical field of fiber reinforced resin-based composite materials, and particularly discloses a quantitative characterization method for the wettability of a unidirectional fiber reinforced resin-based prepreg. The method comprises the following steps: cooling a prepreg sample in a refrigerant until the temperature is lower than the glass-transition temperature of a resin matrix by 50 DEG C or above, shooting and imaging by adopting a microscope, identifying and calculating the areas of a resin infiltration area and a resin non-infiltration area through image processing software, and further calculating the infiltration degree of the prepreg. According to the method, the defect that the infiltration degree is judged according to experience in the prior art is overcome, and key parameter support is provided for research and development of the prepreg.

The invention discloses a picture processing method based on rapid batch photographing and printing, and relates to the technical field of image processing and intelligent equipment manufacturing, and the method comprises the following steps: S1, building a picture processing folder, and presetting a picture processing execution action; s2, performing picture shooting through a camera, and performing serial number coding according to picture shooting information; s3, according to the serial number codes of the pictures in the step S2, carrying out preset processing on the pictures by utilizing image processing software; and S5, after the picture processing is completed, sending the picture data to the printing equipment, and executing the processing action of the next picture at the same time. The picture processing action is performed in real time in the picture data sending process, and the data of the next picture is processed in the time period when the picture data is sent to the printer for printing, so that the photographing, picture processing and printing efficiency is improved, the load balance of equipment is realized, and the picture data is acquired according to the photographing time. And orderly processing of batch pictures and data transmission are realized.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.

The invention relates to a conformity control installation (1a) for a manufacturing line of cast concrete segments comprising at least one mold (2) including a base (3) and side walls (4, 5) and means (30) for automated in-person and dimensional control of said mold (2) before the pouring of fluid concrete into it, said means comprising a movable digital image acquisition element (33) for extracting a plurality of predetermined control points, and a computer terminal (40) integrating image processing software that retrieves the plurality of captured points to generate a three-dimensional map of the inside of the mold in the form of a point cloud and then compares this map with a digital reference model in order to detect any geometric differences and indicate whether the mold conforms to said model. Figure for the abstract: Fig. 3

This invention relates to the field of building material ceramic performance testing technology, specifically a method and application for testing the wear resistance of glaze surfaces, comprising the following steps: S1, cutting out the glazed area as a sample, washing it, and drying it to constant weight; S2, pre-test photography: determining the measurement area on the sample, observing and photographing the measurement area using a microscope, and obtaining the initial dark area ratio η0 of the measurement area using image processing software; S3, grinding test; S4, sample post-treatment: after reaching the pre-adjusted rotation speed n, removing the sample, cleaning it, and drying it to constant weight; S5, post-test photography, obtaining the dark area ratio η of the measured area surface after grinding. n S6. Calculate the wear area ratio Δη of the measurement area, plot Δη against the grinding revolution number n, and take the lowest value among the grinding revolutions corresponding to the wear area ratio Δη reaching 33.3% or above as its wear resistance revolution number, so as to solve the problem that the current test of the wear resistance of glaze is difficult to quantify and has a large human error.

The invention belongs to the technical field of unconventional oil and gas development, and particularly relates to a gas-water-rock reaction and particle dissolution-migration in-situ visual quantitative determination method and device based on a micro-fluidic chip. The quantitative determination method comprises the following steps: firstly, designing a chip model containing a real rock core, wherein factors such as a strong heterogeneous structure of the compact conglomerate oil reservoir and strong difference of a pore throat structure are considered at the same time; then, the gas-water-rock reaction and the particle dissolution-migration process are recorded through an optical camera; and finally, analyzing contribution degrees of different minerals to a gas-water-rock reaction and judging different corrosion modes of the conglomerate by combining image processing software and a mathematical model. The method can be used for carrying out in-situ visual quantitative determination on gas-water-rock three-phase reaction, particle corrosion and a secondary migration process in the conglomerate reservoir under the conditions of oil reservoir temperature pressure and fluid chemistry.

The application discloses an integrated digital microfluidic plasmonic metasurface chip biological image detection system, and belongs to the field of microfluidic and metasurface biological image sensing. The system comprises a digital microfluidic chip, a plasmonic metasurface chip, a light source, a CMOS image sensor and a control circuit. The digital microfluidic chip is provided with a driving electrode array, a medium layer and a hydrophobic layer, and is used for constructing a liquid path and controlling droplets. The plasmonic metasurface chip is combined with the digital microfluidic chip to form a detection site, and is used for detecting biomolecules by using a plasmonic resonance effect. The light source is used for exciting plasmonic resonance. The CMOS image sensor is used for capturing images at the detection site. The control circuit is used for controlling electrodes of the digital microfluidic chip, and realizes construction of the liquid path and control of the droplets. The biomolecule solution to be detected can be accurately guided to the detection site of the plasmonic metasurface chip, the light source is used for exciting plasmonic resonance, and the CMOS image sensor is used for capturing images. Image intensity changes are analyzed by using image processing software, and a detection result of the biomolecules is obtained.

The invention provides a system and a method for measuring the relation between coal particle high-temperature shrinkage and carbon content based on in-situ observation, and belongs to the technical field of coal thermal conversion. The system comprises a microscopic imaging device which comprises a high-resolution microscope with a nanoscale resolution and a camera for shooting and recording the high-temperature shrinkage change of coal particles through the high-resolution microscope; the high-temperature protective gas electric heating device is provided with a sealable sample table for bearing coal particles, and the sample table is arranged in a focusing center area of the high-resolution microscope; the temperature and atmosphere control device is used for carrying out high-temperature heating on the coal particles under atmosphere protection; and the data acquisition and processing device is used for acquiring temperature, atmosphere parameters and microscopic image data in real time and constructing a relationship between high-temperature shrinkage of the coal particles and the carbon content through image processing software of the data acquisition and processing device. The method can be used for analyzing the carbon residue distribution of raw materials such as raw coal, coal gangue, coal gasification slag, fire coal ash and the like, and is beneficial to improving the coal resource utilization efficiency.

The invention relates to a method for the automatic control and regulation of a heating and air conditioning system (700) of a vehicle (10) and / or a seat heating system (720) with at least one control unit (750), wherein the vehicle (10) has a sensor device (200) with at least one camera system (220) and temperature sensors (240) for measuring the outside and inside temperature of the vehicle (10) and is connected to a database (500), wherein facial feature data (520) and user profiles (550) of registered users with user-defined settings for the heating and air conditioning system (700) are stored in the database (500), comprising the following steps: - Taking at least one camera image of a user of the vehicle (10); - Processing the captured camera image using image processing software with facial recognition algorithms to identify the user's facial features; - Comparing the identified facial features with the stored facial feature data (520) to determine whether the user is a registered user with a stored user profile (550); - Loading the user profile (550) into the control unit (750); - Control and regulate the vehicle's (10) heating and air conditioning (700) and / or seat heating (720) using the settings stored in the user profile (550).

The invention discloses an information hiding anti-counterfeiting method based on a visual perception system and a printing method for a packaging box, and the information hiding anti-counterfeiting method comprises the steps: 1, inputting an original information image I, and carrying out the binarization processing, and obtaining a to-be-hidden information silhouette image B; 2, generating a salt and pepper noise image with the same size as the original information image I through image processing software or a computer programming language, and taking the salt and pepper noise image as an encrypted substrate binary dot image N; 3, copying an image N as a to-be-processed binary dot image N ', and performing pixel transformation on the image N' by taking the to-be-hidden information silhouette image B as a mask through image processing software or a computer programming language to obtain a transformed information hidden image H; and 4, superposing the encrypted substrate binary dot image N and the information hiding image H to obtain a target image C. The method is simple to operate, easy to implement and high in safety, and improves the anti-counterfeiting verification efficiency.

The invention provides a method for determining the organic matter surface porosity of the total area occupied by organic matter pores, which comprises the following steps: carrying out an electron microscope scanning experiment on a shale sample to obtain a first scanning electron microscope image of the shale sample; extracting all organic matter regions in the first scanning electron microscope image of the shale sample by using preset image processing software to obtain the total area fraction of organic matters on the surface of the shale sample; obtaining the average surface porosity of organic matter pores from the first scanning electron microscope image of the shale sample according to a preset fifth rule; and according to the total area fraction of the organic matters on the surface of the shale sample and the average surface porosity of the organic matter pores, obtaining the organic matter surface porosity of the organic matter pores in the total area according to a preset formula. The organic matter surface porosity of the organic matter pores in the total area can characterize the characteristics of the shale surrounding pore structure, reflect the shale organic matter thermal evolution process, and provide a basis for evaluating shale gas reservoir and dessert section optimization.

This invention provides a method for processing photovoltaic (PV) module EL images and calculating module power attenuation. The method involves capturing EL images of the PV module using a CCD camera (black and white images); converting the black and white images into a heatmap using image processing software; qualitatively observing light changes in the EL image within the heatmap; adding a standard ruler to the heatmap to directly compare light intensity in different areas of the EL image to determine the basic performance of the PV module; calculating the average fluorescence intensity of the Red Hot heatmap; and converting the fluorescence intensity data into PV module power attenuation data to determine the PV module's performance. This method allows for a direct, qualitative, and quantitative assessment of the basic performance of PV modules.

The invention discloses a method and system for measuring the permeability of rock debris, and relates to the technical field of petroleum and natural gas exploration, and the method comprises the following steps: S1, selecting a homogeneous regular plunger core with known permeability; s2, cutting the periphery of the plunger core to obtain rock debris in an irregular shape; s3, the cut rock debris is subjected to CT scanning, and the tortuosity, throat radius or porosity data of each rock debris are calculated through image processing software; s4, performing calculation processing on the obtained tortuosity, throat radius or porosity data to obtain a correlation fitting formula; s5, performing CT scanning on the rock debris sample with the permeability to be measured, and processing through image processing software to obtain corresponding throat radius, tortuosity or porosity data; and S6, importing the corresponding throat radius, tortuosity or porosity data into the fitting formula to obtain the permeability. The method has no requirement on sample size and is suitable for various samples; meanwhile, the calculation method is simple and easy to popularize and use in a large range.

The invention discloses a method and system for quantitatively distinguishing pores and throats, and relates to the technical field of petroleum and natural gas exploration, and the method comprises the following steps: S1, carrying out CT scanning and image processing software processing on a sample subjected to oil washing and drying treatment to obtain volume information of all pores and throats in the sample; s2, measuring the wettability of the sample, and if the sample is a water-wetted sample, filling saturated alkyl bromide into the sample by using high-pressure filling equipment; if the sample is an oil wetting sample, filling the sample with an iodine-containing inorganic salt solution by using high-pressure filling equipment; s3, wiping the filled sample, standing, and carrying out CT scanning to obtain volume information of the brominated alkane or iodine-containing inorganic salt solution, so as to obtain pore volume and throat volume information; and S4, processing the information of the pore volume and the throat volume by using image processing software to obtain the pore volume, the radius, the throat volume and the radius. The method has no requirement on sample size and is suitable for various samples; meanwhile, the calculation method is simple and easy to popularize and use in a large range.

An imaging system is disclosed for automatically classifying and / or analyzing a sample through motion-blurred images. The system includes an imager with a light source that directs light onto a stage that contains the sample and an image sensor, wherein the stage and / or the imager components are configured to move continuously in a lateral (x, y) direction. Image processing software executed by a computing device acquires motion-blurred video of the sample while moving the stage and / or the imager in the lateral direction, wherein the image processing software is further configured to stitch motion-blurred video image frames or optionally generated motion-deblurred video image frames into a larger field-of-view (FOV) image containing the one or more samples. A trained machine learning model is executed by the computing device configured to receive the larger (FOV) image or portion(s) thereof and output a classification and / or an analysis of the one or more samples.

The invention relates to a molecular fluorography detection method combined with liquid chromatography, and belongs to the technical field of analysis and detection. The invention aims to solve the technical problems that the high sensitivity is difficult to maintain while the miniaturization of the existing liquid chromatogram fluorescence detector is realized, and a flexible and low-cost detection scheme is lacked. According to the technical scheme, the method is characterized in that after being subjected to liquid chromatography separation, a sample is conveyed to a silica gel coating preparation plate through a polyether-ether-ketone tube to form a detection area; exciting fluorescence by adopting a laser with a first narrow-pass optical filter; acquiring a series of fluorescence images by using an image acquisition unit with a second narrow-pass optical filter; and finally, extracting RGB (Red, Green and Blue) numerical values of a fixed pixel region through computer image processing software, and generating a chromatogram of which the fluorescence intensity changes along with time. The method is mainly used for rapid and high-sensitivity fluorescence detection in the fields of biomedical analysis, environmental monitoring, food safety and the like.

The invention relates to a method and equipment for manufacturing a human rib skeleton substitute of a composite 3D environment-friendly printing material, and a storage medium, and the method comprises the steps: S100, outputting rib data based on rib scanning of an injured part of a patient; s200, generating a rib three-dimensional model based on the rib data in medical image processing software; s300, optimizing the rib three-dimensional model through three-dimensional modeling software, wherein the optimization at least comprises model preprocessing, slice parameter adjustment, printing path planning and strategy filling; s400, polylactic acid and continuous fibers are fused and stacked to form a composite material, and the composite material serves as a 3D printing material of the human rib substitute; step S500, printing the rib three-dimensional model by adopting a 3D printing technology; and step S600, carrying out a mechanical experiment test on the printed human rib skeleton substitute.

Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.