40 results about "Image Series" patented technology

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

A method for slide image registration includes receiving slide images, detecting features contained in the slide images, comparing pairs of the slide images using the detected features, creating a distance matrix that reflects a respective difference between each of the pairs of the slide images, ordering the slide images to create a slide image series using the distance matrix, determining transformation matrices for registering the slide images, where a respective transformation matrix rigidly aligns a first slide image (Ii) to a second slide image (Ii−1), wherein i is the position of a slide image within the slide image series, and the respective transformation matrix that rigidly aligns the first and second slide images is determined using a set of the detected features shared by neighboring slide images in the slide images series, and rigidly aligning the slide images using the transformation matrices.

A system and method for image series transformation for optimal compressibility with neural upsampling. It incorporates a novel AI deblocking network composed of convolutional layers for feature extraction and a channel-wise transformer with attention to capture complex inter-channel dependencies. Additionally, the system includes an angle optimizer to further enhance the compressibility of an image. The convolutional layers extract multi-dimensional features from the image, while the channel-wise transformer learns global inter-channel relationships. This hybrid approach addresses both local and global features, mitigating compression artifacts and improving image quality. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving crucial information for accurate analysis.

The invention discloses an image registration method and device, and relates to the technical field of image processing. The method comprises the following steps: converting a plurality of spatial domain images in an image series into corresponding first frequency domain amplitude diagrams through Fourier transform; superposing the first frequency domain amplitude images to construct a frequency domain amplitude summation graph; correcting each spatial domain image in the image series based on the set drift curve; all the corrected spatial domain images are superposed, and a spatial domain addition image is constructed; converting the spatial domain addition graph into a second frequency domain amplitude graph through Fourier transform; comparing the frequency domain amplitude summation graph with the second frequency domain amplitude graph; taking the adjusted drift curve as a set drift curve, and outputting a target drift curve; and performing image registration processing on the image series by using the target drift curve. According to the scheme, the image registration efficiency can be effectively improved, and consumption of computing resources by image registration is reduced.

The invention belongs to the field of plant disease prevention and control, and discloses a plant leaf spot diffusion prediction method and system based on a Markov model and a long-short memory time network, and the method comprises the steps: continuously collecting a grape leaf spot diffusion process image series, extracting the related leaf spot features of each image, and carrying out the prediction of the leaf spot diffusion; constructing features extracted from the series of images into a time sequence; training an LSTM (Long Short Term Memory) prediction model, so that the LSTM prediction model can predict a subsequent spot feature region; the method comprises the following steps of: converting a test picture into gray scale maps according to leaf surface features, regarding the change of pixels of each leaf surface gray scale map as a discrete Markov process, calculating a probability transfer matrix of the next step through leaf surface pixel features predicted by an LSTM network, calculating a next leaf surface gray scale map by adopting a discrete Markov model, and calculating a probability transfer matrix of the next step; and a final diffusion prediction map is obtained through image adjustment. The method predicts and simulates the diffusion process of leaf scabs to a certain extent, and the model has generalization and is easy to popularize to spot diffusion research of other plant disease species.

The embodiment of the invention provides an image series model-based image detection method and device, equipment and a medium, and the method comprises the steps: inputting a sample image into an image series model for detection, obtaining an output result of a first model and a detection result of a second model, calculating the output entropy of the first model according to the output result of the first model, and obtaining the output entropy of the second model; and updating a confidence coefficient threshold value of the first model based on the output entropy of the first model and a detection result of the second model, and carrying out image detection based on the updated image series model. The confidence threshold value of the first model is dynamically adjusted based on the output entropy of the first model and the detection result of the second model, the output stability of the first model can be improved, the output result of the second model is influenced by the output of the second model, and the output stability of the first model is improved. The final detection effect of the image series model can be improved.

Techniques are described for automatically detecting scan characteristics of a medical image series. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise an image generation component that generates a representative image of a medical image series comprising a plurality of scan images, and a series characterization component that processes the representative image using one or more characteristic detection algorithms to determine one or more characteristics of the medical image series. The system can further tailor the visualization layout for viewing the medical image series based on the one or more characteristics and / or automatically perform various workflow tasks based on the one or more characteristics.

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

A system and method for achieving more accurate results when applying an image processing task to a series of medical images of a patient, without significantly increasing processing resource. The proposed system and method is based on receiving a plurality of image sequences of a particular anatomical region, each capturing cyclical movement of an anatomical object. Each image sequence is supplied to a classifier module which employs use of one or more machine learning algorithms to derive at least one score for each image sequence indicative of predicted success or quality of a result of the image processing task if applied to the given image series. This permits an assessment to be made in advance of which of the plurality of image series is most likely to result in the best (e.g. highest quality, or greatest amount of information) results from the image processing task. This allows maximization of the quality of image processing results, without the need to actually process each of the image series with the image processing task, which would consume a large amount of processing resource and consume time.

The invention provides an intelligent diagnosis device and method for internal defects of concrete. The intelligent diagnosis device comprises an electromagnetic exciter, an accelerometer, a multi-sensor array, a synchronous trigger circuit and a data processing unit, the electromagnetic exciter drives the firing pin with the specific mass, so that the impact energy and frequency are adjustable, the electromagnetic exciter adapts to different concrete strengths and thicknesses, and transient impact on the surface of the concrete is achieved. The accelerometer is used for directly measuring stress wave signals generated and returned by impact; the multi-sensor array comprises an acoustic sensor, a thermal infrared imager, a positioning and distance measuring module and a control and data acquisition unit, and the thermal infrared imager records the full-field temperature change of an impact point and a surrounding area to form a thermal image series; the control and data acquisition unit is internally provided with an embedded system and is responsible for controlling triggering of the electromagnetic exciter and synchronously receiving data of the accelerometer and the thermal infrared imager; and the data processing unit converts the acoustic signal into an acoustic time-frequency graph and converts the thermal image sequence into a time sequence thermal characteristic graph.

According to the binocular scanner high-speed three-dimensional fine matching and three-dimensional reconstruction system, a binocular 3D scanner optimization scheme for improving FPGA acceleration is provided, an image processing algorithm with a large bottom layer data volume is accelerated in hardware, continuous gray free combination light spots are adopted as structured light images for three-dimensional measurement, FPGA image filtering is improved, and the three-dimensional measurement precision is improved. The method comprises the following steps of: reducing data processing capacity by adopting an image series-connection type subtraction acquisition method, correcting epipolar lines of images to be horizontal by adopting an image binocular correction method, performing scale cost adaptive transformation on the images, accurately detecting edge and angular point features of the images, and reducing dependence on a central pixel by adopting scale cost adaptive transformation based on Gaussian distribution sampling; constructing a triangular mesh by adopting a hollow circular polar angle triangularization method, and describing the surface image of the three-dimensional object; a 3D scanning system platform is established, a three-dimensional curved surface is reconstructed according to a depth map returned by the improved FPGA, the improved FPGA realizes a coprocessor scheme based on a SoCKit development board, and real-time high-precision 3D scanning is realized.

The system includes an imager that improves the determination of club delivery parameters and captures an image sequence of the area where impact occurs between a golf club and a ball, wherein the imager is configured to take a series of pre-impact images from an initial time point before impact to a time point of impact and a series of post-impact images from a time point of impact to a final time point after impact; and a processor that determines ball launch parameters based on the post-impact image series. The processor performs the task of identifying a predetermined feature point on the golf club in each of the pre-impact images; determining pre-impact movement path data for the golf club based on the location of the feature point identified in the pre-impact images; and calculating club delivery parameters from a mechanical impact model based on the pre-impact movement path data.

The present invention relates to a method, system and computer program element for progression monitoring of a series of X-ray images comprising the steps of receiving a series of X-ray images captured by an X-ray system from a patient, selecting a region of interest (ROI) from at least one image of the series of X-ray images, a selected ROI of each of the plurality of X-ray images is divided into spatial tiles using a processing unit, a respiratory cycle and a heartbeat cycle are determined from the tiles using the processing unit, the respiratory cycle and the heartbeat cycle are eliminated from the tiles using the processing unit, tiles of the ROI are compared to reference tiles, offset tiles that deviate from the reference tiles are determined, and the offset tiles are used to determine a selected ROI of each of the plurality of X-ray images. A visualization superimposed on the image of the series of X-ray images is generated from the offset tiles, and the visualization is displayed on an interface to the user.

An agricultural harvester. The agricultural harvester may comprise a self-propelled combine harvester having a control assembly that comprises an optical sensor device for recording image series of a continuous flow of harvested material, an evaluation device for determining a displayed value broken grain fraction and / or an displayed value non-grain fraction of the flow of harvested material based on an image analysis of the recorded image series, and a visualization device for displaying the displayed value broken grain fraction and / or the displayed value non-grain fraction. The harvester may further comprise a driver assistance system which includes an input unit and an adjustment assistant for adjusting a correction factor. The evaluation device may be configured to determine the displayed value broken grain fraction and / or displayed value non-grain fraction using the adjusted correction factor. Further, the adjustment assistant may determine the correction factor in a dialog with a plurality of dialog steps.

A method for water-fat separated magnetic resonance imaging (MRI) is provided herein. The method includes acquiring multi-echo MRI data from a subject using an echo planar time-resolved imaging (EPTI) pulse sequence, wherein echo spacing creates in-phase and out-of-phase relationships between water and fat signals. The method includes separating acquired data into odd echoes corresponding to in-phase data and even echoes corresponding to out-of-phase data, independently reconstructing the separated echoes to generate in-phase and out-of-phase images using subspace reconstruction, and generating separate water-only and fat-only multi-echo image series by performing water-fat separation using the in-phase images and the out-of-phase images.

The invention discloses a solidified soil damage mode recognition method and system based on digital speckles, and the method comprises the steps: obtaining a left group of speckle image series and a right group of speckle image series of measured solidified soil through a calibrated camera, and obtaining two groups of preprocessed image series; decomposing the reference image of the first group of preprocessed image series into first reference sub-region images through a sub-region matching algorithm; performing stereo matching on the second group of preprocessed image series based on a feature algorithm of scale invariant feature transformation to obtain a second reference subarea image; and performing time sequence matching on the first reference subarea image and the second reference subarea image to obtain an initial deformation displacement value of the solidified soil so as to confirm an identification damage mode of the measured solidified soil according to the displacement deformation value of the solidified soil. The method solves the problem that a traditional determination method of a traditional solidified soil damage mode mainly depends on analysis of a damage form and a stress-strain curve of cement solidified soil, but the analysis is only on a qualitative level, and the damage mode of the solidified soil is difficult to accurately identify.

To achieve deterioration restoration processing for an image series having time series represented by a video image in a more suitable mode.SOLUTION: A restoration error calculation unit 1003 calculates a restoration error related to restoration of a high-quality image 103 based on the high-quality image 103 restored from a degraded image 102 obtained by degrading a pre-degradation image 101 and at least either pre-degradation image 101 or degraded image 102. A score calculation unit 1007 calculates, based on the restoration error and a feature amount of a predetermined type extracted from the degraded image 102, a score according to the type of the feature amount. A sampling unit 1008 extracts the pre-deterioration image 101 to be used for creating a data set from a series of pre-deterioration images 101 based on the score.SELECTED DRAWING: Figure 5

Systems, methods, and apparatuses implementing a display optimization system are provided herein. In some embodiments, an example display optimization system may be configured to perform an optimal anchor-prior matching operation to identify optimal anchor-prior image pairs or series pairs from new medical imaging data (e.g., one or more anchor image series) and historical medical imaging data (e.g., one or more prior image series).

The invention relates to an agricultural harvesting machine, in particular a self-propelled combine harvester (1), with a control arrangement (2), wherein the control arrangement (2) comprises an optical sensor device (3) for recording image series of a passing crop stream, an evaluation device (4) for determining a display value broken grain portion (20) and / or a display value non-grain portion (21) of the crop stream based on an image analysis of the recorded image series and a visualization device (5) for displaying the display value broken grain portion (21) and / or the display value non-grain portion (21), wherein the harvesting machine comprises a driver assistance system (22) which comprises an input unit (24), wherein the driver assistance system (22) comprises a setting assistant (25) for setting a correction factor (26), wherein the evaluation device (4) is configured such thatso that it determines the display value broken grain fraction (20) and / or the display value non-grain fraction (21) by means of the set correction factor (26), wherein the setting assistant (25) determines the correction factor (26) in a dialogue with several dialogue steps.

A method for the non-invasive determination of physical data from a living organism using an EIT measuring device for measuring a measure of blood flow through at least one organ within the organism is described, comprising the following method steps: a) Creating an EIT image series comprising a multitude of EIT images generated sequentially by means of the EIT measuring device attached to an extracorporeal area of ​​the organism, each consisting of image pixels, each of which is assigned a signal value corresponding to an electrical impedance, b) Selecting organ-specific EIT image sections from all EIT images that are identical in position, c) Determining a regional impedance curve based on all selected EIT image sections, d) Determining times at which the regional impedance curve has a local minimum, e) Selecting those EIT images from all generated EIT images that can each be assigned to one of the specific time points, f) Determine a reference image for each of the selected EIT images, g) Subtracting the reference image determined for each selected EIT image from it to obtain a difference image, or instead of the procedure steps e) to g), the following procedure steps e') to g'). e') Selecting those selected EIT image sections from all selected EIT image sections that can each be assigned to one of the specified time points, f') Determine a reference image for each of the selected EIT image sections, g') Subtracting the reference image determined for a selected EIT image section from it to obtain a difference image in each case, h) Selecting at least one difference image to obtain an EIT result image or averaging at least two difference images to obtain an EIT result image and i) Correlating the signal value assigned to each pixel of the result image with a measure of blood flow through at least one organ within the organism.

The present invention relates to a method for authenticating the authenticity of digital individual or moving images, in which an individual authentication key (1.5) is assigned while recording an image series (1.6) of individually recorded individual images or while recording an image sequence in the form of moving images. The method according to the invention is characterized in that at least one camera setting and / or at least one recording setting on the camera is changed in a controlled manner from individual image to individual image during recording for the purpose of assigning the authentication key (1.5) and / or creating or incorporating the authentication key (1.5) in the image series (1.6) or is changed in a controlled manner from moving image to moving image during recording for the purpose of assigning the authentication key (1.5) and / or creating or incorporating the authentication key (1.5) in the image sequence.

Systems, methods, and apparatuses implementing a display optimization system are provided herein. In some embodiments, an example display optimization system may be configured to perform an optimal anchor-prior matching operation to identify optimal anchor-prior image pairs or series pairs from new medical imaging data (e.g., one or more anchor image series) and historical medical imaging data (e.g., one or more prior image series).

A system for MRI is provided. The system may obtain a plurality of sets of under-sampled k-space data corresponding to a plurality of frames. Each set of under-sampled k-space data may be acquired simultaneously from a plurality of slice locations of a subject in one of the frames using an MRI scanner. The system may reconstruct a plurality of reference slice images based on the sets of under-sampled k-space data of the plurality of frames. Each of the reference slice images may be representative of one of the slice locations in more than one frame of the frames. The system may further reconstruct a plurality of image series based on the sets of under-sampled k-space data and the reference slice images. Each image series may correspond to one of the slice locations and include a plurality of slice images of the corresponding slice location in the plurality of frames.

The present invention discloses an image registration method and device, which relates to the field of image processing technology. The method includes: converting multiple spatial domain images in an image series into corresponding first frequency domain amplitude maps through Fourier transform; superimposing each first frequency domain amplitude image to construct a frequency domain amplitude sum map; correcting each spatial domain image in the image series based on a set drift curve; superimposing each corrected spatial domain image to construct a spatial domain sum map; converting the spatial domain sum map into a second frequency domain amplitude map through Fourier transform; comparing the frequency domain amplitude sum map and the second frequency domain amplitude map; and using the adjusted drift curve as the set drift curve to output a target drift curve; and performing image registration processing on the image series using the target drift curve. This solution can effectively improve the efficiency of image registration and reduce the consumption of computing resources for image registration.

The invention relates to multi-frame consistency for automated magnetic resonance imaging prescriptions. A computer-implemented method for performing a scan of a subject with a medical imaging system includes acquiring, via a processing system including one or more processors, a series of images of a region of interest of the subject with the medical imaging system. The computer-implemented method also includes automatically identifying, via the processing system, one or more anatomical features in the region of interest in the series of images. The computer-implemented method also includes automatically refining, via the processing system, the one or more anatomical features for generating a prescription for subsequent scans of the region of interest with the medical imaging system. The refinement of the one or more anatomical features is based on positional consistency of the identified one or more anatomical features.

The application discloses a pointer intelligent iterative positioning method and system combined with a multi-modal large language model, relates to the technical field of pointer positioning, and comprises the following steps: performing semantic analysis on a natural language instruction of a user to obtain a task structure body; collecting a screen image and historical execution information to obtain a screen image series and a track abstract series; extracting interface layout features and performing interface coherence discrimination; if the coherence discrimination result is coherent, performing alignment discrimination and pointer movement instruction generation based on a multi-modal large language model; and executing the pointer movement instruction and iteratively collecting the screen image to update the pointer position. The technical problems of the prior art, such as limited semantic understanding ability of complex natural language instructions, easy deviation of pointer positioning under a dynamic interface and lack of an effective interface coherence discrimination mechanism, are solved.

At least some example embodiments of methods and systems for generating display data of a medical image data set include identifying, for a target medical image series of a patient at a first point in time, a reference medical image series of the patient taken at a second point in time different from the first point in time. In particular, the selection may be based on a comparison of respectively depicted body regions of the patient. Further, methods and systems may be directed to generating display data to cause a display device to display a rendering of the reference medical image series based on a registration between the target medical image series and the reference medical image series.

Image series transformation for optimal compressibility with neural upsampling, by collecting a plurality of images; training a machine learning model using one or more parameters to transform the plurality of images to improve compressibility; determining optimal transformation parameters based on the trained machine learning model; transforming the plurality of images based on the determined parameters; processing the transformed images to generate compressed data; reconstructing images from the compressed data using the transformation parameters; and refining the reconstructed images using a neural network upsampling model, wherein the refined images include more information than the reconstructed images.

The invention discloses a typhoon cloud picture sequence super-resolution reconstruction method based on fluid dynamic constraints, and belongs to the field of image super-resolution reconstruction. The method comprises the following steps: acquiring an original typhoon cloud picture sequence of a satellite observation area, and preprocessing the typhoon cloud picture sequence to obtain a low-resolution image sequence; building a super-resolution reconstruction network model based on fluid dynamic constraints, and training and optimizing the super-resolution reconstruction network model through the training set; and inputting the low-resolution image sequence in the verification set into the trained super-resolution reconstruction network model to obtain a reconstructed high-resolution image. The method can effectively maintain the structural continuity and dynamic continuity of the typhoon cloud atlas, is suitable for the generation and analysis of a high-precision cloud atlas sequence in the fields of weather forecast, satellite remote sensing and the like, and has relatively high practical value and popularization prospect.

To provide a sign language symbol string generation device capable of receiving input of a natural language sentence corresponding to a sign language video to generate a sign language symbol string with high recognition accuracy by solving a problem that the natural language sentence (such as a Japanese text) cannot be used for recognition of the sign language video in a conventional technique.SOLUTION: A sign language symbol string generation device includes a decoder function unit. The decoder function unit performs decoding processing on the basis of encoding result information corresponding to a natural language sentence and encoding result information corresponding to a sign language image series to output a sign language symbol string.SELECTED DRAWING: Figure 1