30 results about "Computer tomographic" patented technology

The present application relates to the technical field of image data processing, and discloses a corn kernel and embryo volume high-throughput visual analysis method and system based on deep learning, which can obtain at least one folder according to a file input path set by a user, and each folder includes a gray scale sequence obtained by computer tomography (CT) slicing of corn kernel groups in a horizontal direction. Based on a parallel pipeline processing mode, a set batch size and a deep learning segmentation model, the gray scale sequence in the folder is preprocessed and image segmented to obtain kernel binary segmentation mask sequences and embryo binary segmentation mask sequences, and then the kernel quantity and the volume related data of the kernel and the embryo are determined, and the related images and data are visually output. The present application can complete the processing of the high-throughput data of the CT slice sequence of the corn kernel, and the nondestructive measurement and visual display of the volume related data of the kernel and the embryo, and effectively improve the measurement efficiency.

This invention discloses a non-destructive testing method and system for via filling in glass substrates based on CT scanning, belonging to the field of advanced packaging inspection technology. The key technical points are: performing X-ray computed tomography (CT) scanning on a glass substrate with metal-filled vias to acquire a two-dimensional projection image sequence; performing three-dimensional reconstruction on the two-dimensional projection image sequence to generate three-dimensional volume data of the internal structure of the metal-filled vias; performing image segmentation on the three-dimensional volume data to distinguish the glass substrate, metal filler, and internal defect regions to obtain the segmentation result; and calculating three-dimensional quantitative parameters characterizing the filling quality of the metal-filled vias based on the segmentation result, including at least one of three-dimensional fill rate, three-dimensional void rate, or filling uniformity coefficient. This invention achieves a comprehensive leap in detection capabilities in spatial dimension, evaluation mode, and detection essence, laying a solid technical foundation for the research and development iteration and mass production quality control of advanced packaging glass substrates.

Embodiments of the present disclosure relate to a computer-implemented method for providing image data. The present disclosure relates to a computer-implemented method for providing image data based on raw image data of a dual-energy computed tomography apparatus, comprising: providing (10) raw image data by a dual-energy computed tomography apparatus comprising low-energy image data and high-energy image data; providing (11) a tissue classification model, wherein the tissue classification is based on a dual-energy ratio of the low-energy image data and the high-energy image data; and utilizing (12) the tissue classification model and providing image data, wherein at least the raw image data is input data of the tissue classification model.

An electrical connection material having a contrast agent infused within, and related systems and methods of detection thereof, are disclosed herein. Computer electronics such as printed circuit boards have electronic components attached to a substrate by an electrical connection material. The electrical connection material has at least one component infused with a contrast agent. The contrast agent is of a concentration to provide a visual distinction or highlight when imaged by an inspection system, such as an x-ray system of computed tomography (CT) scanning system. The presence of the contrast agent demonstrates that not all of residual electrical connection material has been cleaned away from the printed circuit board after manufacture.

This invention relates to the field of X-ray computed tomography imaging technology, and particularly to a multi-source linear CT reconstruction method and system based on projection fusion and depth unfolding networks. First, using at least three X-ray sources in conjunction with a single area array detector, the object under examination is controlled to translate linearly, and multiple sets of projection data sequences are acquired time-divisionally. Second, a mapping model is constructed based on spatial geometric relationships, fusing and rearranging the projection data into a two-dimensional sine graph with missing angles. Next, a cascaded network of sine graph completion and image reconstruction is constructed. First, a completion submodule fills in the missing data in the sine graph while retaining the true measurement values. Then, an intelligent reconstruction submodule with a depth unfolding architecture containing multiple iteration stages, combined with a weight-sharing backprojection operator and a residual regularization module, updates the image. Finally, an end-to-end joint training is performed using a composite loss function of the sine graph domain and the image domain. This invention achieves high-fidelity, artifact-free, and rapid reconstruction of CT tomographic images, balancing imaging quality and efficiency.

The application belongs to the technical field of laser additive manufacturing, nondestructive testing, computer vision and three-dimensional reconstruction, and discloses an AI-driven laser additive manufacturing internal defect identification and three-dimensional reconstruction method, which comprises the following steps: S1, voxel data set of a component is obtained by adopting X-ray computer tomography, and slicing and pretreatment are performed to eliminate noise; S2, a data set containing multiple types of internal defect information is constructed, transfer learning and fine tuning are performed based on a pre-trained visual large model, a laser additive manufacturing internal defect multi-modal identification large model is obtained, a multi-channel mask image sequence is obtained, and high-precision segmentation of multiple types of defects is realized; S3, three-dimensional reconstruction and abstract modeling are performed, all abstract internal defect models are combined, and a laser additive manufacturing internal defect model is obtained. The method can realize automatic identification, three-dimensional reconstruction and parameterized representation of laser additive manufacturing internal defects, and has high precision, high efficiency and good scalability.

This invention discloses a method for defect identification and quantitative analysis of composite materials based on deep learning. The method includes: first, acquiring three-dimensional X-ray computed tomography (CT) images of the interior of the composite material; then, using an adaptive image segmentation method to perform preliminary defect identification on the slices; processing the complete three-dimensional data using a deep learning-based component segmentation model to accurately obtain the three-dimensional spatial distribution of the matrix, fibers, and defects; after image optimization processing of the model segmentation results, reconstructing the three-dimensional defect model and extracting morphological and spatial distribution parameters; finally, achieving multi-scale quantification and statistical analysis of defects based on these parameters. This invention combines adaptive image processing with a deep learning model, overcoming the problems of strong subjectivity and insufficient accuracy in identifying minute defects in traditional methods, providing reliable data support for composite material process optimization and performance evaluation.

A communication apparatus, a slip ring device and a computerized tomography device, which relate to the technical field of optical communications. The communication apparatus comprises a first structure, a second structure, and an optical path structure that is disposed between the first structure and the second structure, wherein the first structure is provided with an electro-optical unit for converting an electrical signal, which is output by the first structure, into an optical signal; the second structure is provided with a photoelectric unit for converting the optical signal into an electrical signal; and the optical path structure is used for guiding the transmission of the optical signal to the photoelectric unit. By means of providing the optical path structure, the optical signal output by the electro-optical unit can be received by the photoelectric unit. Compared with an existing optical transmission solution in which the deployment of a plurality of light sources and / or a plurality of optical fibers is required, when the optical signal output by the electro-optical unit is transmitted under the guidance of the optical path structure and can be received by the photoelectric unit, the number of light sources and / or optical fibers can be reduced, thereby reducing the cost of the optical transmission solution.

The present application relates to the technical field of computer, and proposes a light-weight inner ear segmentation method based on channel-space decoupled non-local attention, which comprises: obtaining an ear computer tomography image to be segmented; inputting the image into an inner ear segmentation network to obtain a segmentation result of an inner ear structure; the inner ear segmentation network adopts an encoder-decoder structure, and in the encoding and decoding processes, feature processing is performed through a depth separable convolution containing a dynamic routing mechanism, and a channel-space dimension decoupled non-local attention operation is performed on the bottleneck layer between the encoding and decoding. While significantly reducing the model parameter quantity and the calculation overhead, the present application improves the accuracy of segmentation of the complex and tiny structure of the inner ear.

This invention discloses a method for activating geopolymer activity and designing mix proportions in high-moisture-content soil layers, relating to the fields of comprehensive utilization of bulk solid waste and green building materials using geopolymers. The method includes the following steps: Step 1, chemical composition and phase composition analysis of various solid waste raw materials are performed to generate a set of candidate mix proportions; Step 2, according to the candidate mix proportions in the set, cementitious raw materials, activators, and soil samples are mixed to prepare solidified soil samples and cured; Step 3, each solidified soil sample is subjected to microcomputer tomography and binarized, and Euclidean distance transformation is performed on the three-dimensional binary pore voxel data to generate a pore distance field. A multi-index ranking method is used to output the recommended mix proportion for the target moisture-content soil layer. This invention integrates macroscopic mechanical properties, microscopic phase composition, and three-dimensional pore topological characteristics into a unified evaluation system, realizing the systematic design and multi-dimensional coupled optimization of geopolymer mix proportions in high-moisture-content soil layers.

The present application relates to a kind of based on battery pack reconstruction image image segmentation method, belong to computer tomography imaging technical field, solve the poor segmentation effect of battery pack reconstruction image in prior art.The image segmentation method includes: according to the preset shell size, the initial reconstruction image of battery pack is divided into shell region, air region and internal region;Pseudo detection is carried out to internal region, and pseudo region and non-pseudo region are obtained;According to the attenuation coefficient of each pixel point in internal region, preset glue layer attenuation coefficient and preset battery attenuation coefficient, non-pseudo region is segmented, and battery region and glue layer region are obtained.The segmentation effect of battery pack reconstruction image is improved.

The present application relates to a kind of image iterative reconstruction methods suitable for a large number of not-through area scene, belong to computer tomography imaging technical field, solve the poor stability of the reconstruction effect in prior art when reconstructing for different to-be-reconstructed workpieces.The iterative reconstruction method includes: segmentation is determined to initial reconstruction image for artifact region, using preset attenuation coefficient replaces the attenuation coefficient value of other pixel points except artifact region in initial reconstruction image to obtain compensation reconstruction image;Determine penetration threshold according to original sinogram;Compensation weight sinogram is generated using penetration threshold, original sinogram and initial reconstruction image, and iteration termination condition is determined based on penetration threshold and original sinogram;Obtain final reconstruction image by several iterations.Improve the stability of the reconstruction image effect and reconstruction process for different to-be-reconstructed workpieces.

1. The name of the design product: computer tomography scanner kit. 2. The use of the design product: the product is used for medical scanning imaging. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: assembly state perspective view. 5. Kit description: kit 1 is the computer tomography scanner mainframe, and kit 2 is the computer tomography scanner scanning bed.

The application relates to a kind of intelligent detection and quantitative evaluation methods of residual powder of porous structure bone implant instrument based on visual identification, relate to nondestructive testing technical field, to solve the problem of low efficiency, limited precision, strong subjectivity of traditional residual powder detection technology, the following steps are innovated in the application: using high-resolution electron microscope (SEM) and dual-mode cooperative acquisition technology of computer tomography (CT), the pictures of surface topography features and internal residual powder state of porous structure are obtained, the images are preprocessed in batches using Matlab, the residual powder is positioned using Otsu method and U-Net model, the particle size distribution characteristics of residual powder are quantified, the geometric characteristics of porous structure, the multi-scale feature fusion is carried out on the preprocessed image, the accurate positioning of residual powder, lightweight preliminary screening, output high confidence residual powder distribution and feature map, finally, the spatial distribution, morphological characteristics and melting state of residual powder are quantified, and quality detection evaluation is output, the application can realize efficient identification and quality detection of residual powder of porous structure bone implant instrument.

Method for processing an initial image (I) of an object under investigation, wherein the initial image (I) was reconstructed from measurement data (pin) acquired during a relative rotational movement between a radiation source (C2, C4) of a computed tomography system (C1) and the object under investigation, wherein a frame rate splitting (Fk) of the initial image (I) into at least a first and a second image (Ik) is performed, the first image is modified by means of a first function (G1), wherein the first function (G1) causes a contrast increase within the first image, and the modified first image and the second image are combined (+), for the first image, before the frame rate splitting (Fk) is performed, wherein the non-linear function (Hk) causes a limitation of image values ​​with large absolute values, wherein the second image is modified by means of a second function (Gk).which effects noise reduction limited to an image value range of the second image, wherein the extent of the image value range is determined depending on the magnitude of the noise in the second image, and which includes pixel-dependent parameters so that adaptation to locally varying noise is achieved.

A defect prediction method based on a multi-feature parallel multi-stage neural network (MF-PMSNN), includes: obtaining a trajectory dataset, and preprocessing data of a defect of a workpiece in additive manufacturing (AM); building an MF-PMSNN, and evaluating an output classification result based on evaluation indicators; and performing real-time defect prediction, and deploying a trained MF-PMSNN model to a production environment. The present disclosure combines and effectively matches thermal imaging-based in-situ monitoring data and X-ray computed tomography (XCT)-based in-situ monitoring data to ensure temporal and spatial consistency between the thermal imaging-based in-situ monitoring data and the XCT-based in-situ monitoring data. In this way, a molten pool status and a pore of the workpiece can be captured more comprehensively. The MF-PMSNN is proposed to obtain a molten pool status and the porosity distribution in the data and perform defect prediction.

An end-to-end differentiable image-processing pipeline for spectral Computed Tomography (CT) systems, including both Photon Counting (PCCT) and dual-energy (DECT) configurations, is provided. In the disclosed framework, spectral data acquired from a detector across two or more distinct X-ray energy spectra or energy bins are processed through a sequence of differentiable operators, including one or more differentiable preprocessing operators, a differentiable material-decomposition operator, and a differentiable image-reconstruction operator. The material-decomposition operator can be implemented using an unrolled iterative solver, an implicit-differentiation formulation, or a trained empirical proxy model. An image-domain loss between reconstructed and reference images, or other differentiable regularization criteria, is backpropagated through the pipeline to update parameters of the preprocessing operators, the material-decomposition operator, and / or a forward detector model. This enables automatic physics-informed calibration that improves quantitative image fidelity, reduces artifacts, and eliminates dependence on manual recalibration or Monte Carlo reference data.

The application provides a kind of strong dynamic under warhead charge damage test characterization method and system, comprising: preparation warhead test piece, wherein the inert charge is loaded in the inside of the warhead test sample;The warhead test piece is simulated in the process of warhead penetration;The soft recovery is carried out to the simulated warhead test piece;The industrial computer tomography and image processing are carried out to the soft recovery warhead test piece, and the CT slice image and three-dimensional image of the internal damage of inert charge are obtained;According to the CT slice image and three-dimensional image, the damage characterization parameter of inert charge is calculated, and according to the damage characterization parameter, the comprehensive damage variable of inert charge is obtained. To realize the accurate test and scientific characterization to the internal damage of charge.

The present disclosure relates to the fields of physics and computers, and particularly relates to the application of physics and computer technology in the field of radiation medicine. Provided are a model training method and apparatus, a method and apparatus for determining the elemental density distribution of a constituent, and an electronic device and a storage medium. The model training method comprises: acquiring respective characteristic parameters of M scanning energy spectra of a computed tomography (CT) device; on the basis of the M characteristic parameters and elemental density distributions of N sample materials, determining M sample CT images of each of the N sample materials under the M scanning energy spectra, so as to obtain M×N sample CT images; on the basis of the M sample CT images and the elemental density distribution of each of the N sample materials, constructing a sample data set; and using the sample data set to train an initial model, so as to obtain a target model corresponding to the CT device, wherein the target model is used for determining an elemental density distribution on the basis of CT images obtained by means of scanning performed by the CT device.

The application discloses a waveguide antenna weld defect detection method, device, equipment and medium. The method comprises the following steps: X-ray scanning is performed on a waveguide antenna weld area to obtain a plurality of first data; computer tomography reconstruction is performed on the plurality of first data to obtain a plurality of second data; weld area segmentation is performed on the plurality of second data to obtain third data corresponding to each second data, which indicates the area where the waveguide antenna weld exists; according to the plurality of second data, the third data corresponding to each second data and a preset defect feature, the second area of each second data and the corresponding defect type are determined; according to the second area of each second data and first information, the third area of each second data, i.e. the area where the defect exists inside the waveguide antenna weld, is determined; and according to the third area of each second data and the defect type corresponding to each third area, a defect detection report of the waveguide antenna weld is generated. The application can improve the accuracy and reliability of waveguide antenna weld defect detection.

Provided is a computer tomographic image generation method and a learning model generation method capable of reducing blurring due to rotation of an object in tomographic image data. The computer tomographic image generation method includes: a step of acquiring a plurality of rotational projection image data (30) by performing X-ray imaging while rotating an object (90); a step of acquiring tomographic image data (31) by performing reconstruction processing based on the acquired plurality of rotational projection image data (30); and a step of inputting the tomographic image data (31) to a model (40a) as input image data (44), thereby acquiring corrected tomographic image data (32) in which blurring due to rotation of the object (90) in the tomographic image data (31) is corrected as output image data (45).

The present application relates to a kind of computer tomography-based durians meat rate detection method and system, its method, including collecting multiple CT tomogram of durian, obtain multiple scan images;Respectively, pulp image in multiple the scan image is segmented, obtain multiple pulp scan images;According to multiple the pulp scan image constructs pulp three-dimensional graph;According to the pulp three-dimensional graph, calculate pulp volume;According to the pulp volume and pulp density, calculate pulp quality;According to pulp quality and whole durian mass, calculate out meat rate;The present application can detect the meat rate of durian without damaging durian, and computer tomography is used, can realize the detection of each durian, to estimate the meat rate of each durian, compared with the sampling method in prior art, the present application provides meat rate calculation error smaller, higher calculation accuracy.

The present application relates to a kind of image reconstruction methods based on resolution progression, belong to computer tomography imaging technical field, solve the problem of low efficiency when the prior art iterative reconstruction.The image reconstruction method includes: by the acquisition sinogram of the workpiece to be reconstructed of detector obtains acquisition sinogram, to acquisition sinogram is down sampled and obtains at least two resolution levels of original sinogram;According to the order from low to high of resolution level, in turn, each resolution level of original sinogram is iteratively reconstructed, and the reconstructed image of highest resolution level is regarded as final reconstructed image.It improves the reconstruction efficiency when iterative reconstruction.

The present application relates to a kind of image reconstruction methods, belong to computer tomography imaging technique field, solve the poor effect of image reconstruction in prior art for not penetrating scene under the problem of carrying out.The image reconstruction method includes: by detector acquisition the original sinusoidal image of the workpiece to be reconstructed, obtains initial reconstruction image by reconstructing to original sinusoidal image;Initial reconstruction image is segmented to determine artifact area, using preset attenuation coefficient replaces the attenuation coefficient value of other pixel points except artifact area in initial reconstruction image to obtain compensation reconstruction image, and the compensation reconstruction image is orthogonally projected to obtain compensation sinusoidal image;According to initial reconstruction image, original sinusoidal image and compensation sinusoidal image are fused to obtain fusion sinusoidal image;The final reconstruction image is obtained by reconstructing to fusion sinusoidal image.It improves the reconstruction image effect of the workpiece to be reconstructed.

The present disclosure provides a linear array detector, a computer tomography device and a projection imaging device; wherein the linear array detector comprises a circuit board and a plurality of pixels arranged on the circuit board; the plurality of pixels are arranged into N columns along a first direction and M rows along a second direction, N>M≥2 and N and M are integers, the first direction and the second direction intersect; each pixel comprises a silicon photomultiplier and a scintillation crystal coupled with the silicon photomultiplier, the scintillation crystal being used for converting X-rays into scintillation light; in any two adjacent rows of pixels, at least part of the silicon photomultipliers are arranged in a staggered manner in the first direction. The linear array detector can further improve the spatial resolution without further reducing the physical size of the silicon photomultiplier.

The present application provides a kind of shale oil reservoir schistosity seam and matrix pore percolation contribution quantification method, belong to oil and gas field development technical field, including micron level and nanometer level computer tomography to same shale core sample, by image fusion and three-dimensional reconstruction, construct the three-dimensional digital core model including matrix pore and schistosity seam structure;Based on the three-dimensional digital core model, by numerical simulation, calculate its absolute permeability under original state, only keep pore state and only keep fracture state, and according to this, quantitatively calculate the contribution ratio of fracture system and matrix pore system to total percolation capacity.The present application adopts the above-mentioned shale oil reservoir schistosity seam and matrix pore percolation contribution quantification method, solves the technical problem that traditional method causes large reservoir evaluation deviation due to quantitative ambiguity, and lacks scientific optimization basis for development scheme.