374 results about "Image layer" patented technology

The invention relates to the technical field of image processing, in particular to an image segmentation system for medical diagnosis, which comprises a regional characteristic analysis module, a modal selection optimization module, an image local enhancement module, an edge characteristic analysis module and a boundary optimization adjustment module. According to the medical image segmentation method, the gray level distribution, the texture density and the structure contour of the tissue structure in the image layer are analyzed, the system is allowed to accurately measure the characteristic deviation between different modes, the accuracy of medical image segmentation is improved, especially on the processing of the complex tissue structure, the adjacent tissues with different properties can be better analyzed and distinguished, and the medical image segmentation accuracy is improved. Real-time evaluation and adjustment of local contrast enable details of the image to be clearer, image quality is improved, accuracy of edge recognition is improved, by analyzing edge curvature and morphological characteristics, the system can optimize edge trend and reconstruct a boundary path, overall performance of image segmentation is further improved, and image segmentation efficiency is improved. Therefore, the treatment and prognosis effects of the patient are ensured.

The invention relates to the field of defect detection, in particular to a wallpaper defect detection method and system based on machine vision. The method comprises the following steps: analyzing acquired to-be-detected wallpaper image data to obtain regional texture variance, edge density and brightness gradient indexes, and generating a scale image layer set; extracting salient edge points in each scale image and generating an edge anchor point set; analyzing the scale image layer set and the edge anchor point set to obtain a texture difference index, and generating a texture feature map set according to the edge anchor point set; processing the texture feature map set to generate a texture significance distribution map; based on the texture significance distribution diagram, main direction distribution is extracted, a direction residual error model is constructed, and a residual error diagram and a direction difference distribution diagram are generated; and establishing a region scoring matrix, and generating a wallpaper defect credibility distribution map and a defect classification image output set on the basis of the region scoring matrix. The wallpaper defect detection precision can be improved.

The invention provides an image restoration and generation method based on a conditional generative adversarial network, and the method comprises the steps: a camera APP obtains contour key point data of a user figure proportion through carrying out the high-resolution feature extraction of an input image, carries out the three-dimensional reconstruction of a waist line and a shoulder breadth size, and obtains a contour key point data of a user figure proportion; generating an initial feature mapping graph containing wrinkle density distribution and local deformation amplitude; according to the initial feature mapping graph, adopting a region segmentation technology to separate a body contour from a clothing region, extracting a texture stretching degree and contact point stress distribution, determining a distribution condition of clothing and body contact points, and generating a segmentation result for dynamic adjustment; and for the to-be-optimized detail area list, performing enhancement processing on the texture stretching degree of the contact points of the clothes and the body and the stress distribution of the contact points, obtaining wrinkle layer depth data of a local area, and generating an optimized image layer.

The invention discloses an image denoising method and system based on a differential equation and a deep learning network. The method comprises the following steps: inputting a noise image subjected to image preprocessing into a differential equation NODE model and an improved deep learning network UNet; extracting multi-level features of the noise image layer by layer through a multi-scale channel feature fusion module of an improved UNet network; attention is increased for shallow information in the network through an attention mechanism module; and carrying out continuous time dynamic modeling by using a NODE model, taking the improved UNet network as a neural network vector field in the NODE model, and simulating a continuous time evolution process through an ODE solver to obtain a clear image. Through the fusion of ODE modeling and the deep learning network, the dependence on large-scale annotation data is reduced, parameters are evolved and optimized by using continuous time characteristics, the generalization ability of the model to complex noise is improved, and a good denoising effect can be obtained under the condition of few sample training.

The invention provides an unmanned aerial vehicle image target detection method and device based on dynamic deformable convolution feature fusion. The method comprises the steps of inputting a to-be-detected unmanned aerial vehicle image for preprocessing; extracting multi-scale features from the input preprocessed image layer by layer to obtain an input feature map; inputting the input feature map into a DDCM-based multi-level fusion feature fusion network for feature fusion to obtain multi-level fusion features, and extracting target deformation features in each level structure of a multi-level fusion feature pyramid structure by using dynamic deformable convolution through a dynamic deformable convolution feature learning module, according to the dynamic deformable convolution, a global coordinate attention mechanism is adopted to fuse position information and global features, and a dynamic space offset and a modulation mask are generated; and inputting the multi-level fusion features into a multi-scale perception detection head for target detection. According to the invention, small target leak detection and deformation target positioning deviation can be reduced, and the detection precision and robustness are improved at the same time.

The embodiment of the invention discloses a digital intelligent risk detection method and equipment for a high-conversion perovskite battery, and a medium, belongs to the technical field of battery detection, and solves the problems of energy waste and production interruption caused by maintenance after the high-conversion perovskite battery breaks down. Carrying out batch fusion on multi-scale image layers corresponding to the high-conversion perovskite battery image, and carrying out temperature labeling on the fused image through a temperature mapping algorithm to generate a defect thermodynamic diagram; performing feature vector extraction on the defect thermodynamic diagram to determine a defect grade corresponding to the high-conversion perovskite battery based on a feature vector; under the condition that the defect grade is greater than a preset grade threshold value, converting defect area information in the high-conversion perovskite battery into a control signal, and adjusting a shooting light source and a shooting angle so as to determine new defect area information; and performing path evolution on battery defects through a digital twinborn model, and obtaining risk prediction information of the high-conversion perovskite battery based on an evolution result.

Techniques according to the present disclosure may include receiving, at a computer, a command for performing an action on a first image layer of a first container repository. A second container repository is determined which has a dependency on the first container repository, based on a dependency graph storing dependencies of a plurality of container repositories. The action is performed on the first image layer of the first container repository and a corresponding action on a second image layer of the second container repository based on the command.

The invention provides a culture symbol transmission method and system based on Sichuan opera facial makeup art patterns, and particularly relates to the field of facial makeup digital transmission. According to the method, multi-level modeling of a Sichuan opera facial makeup pattern from a pixel layer to a component layer and then to a semantic layer is realized by fusing image processing, component contour matching, image structure modeling and an image neural network technology; according to the method, main and auxiliary color block areas and component information in an image can be automatically identified and structurally stored, a spatial semantic relationship of the image is learned through a graph neural network, a structural semantic code is output, and finally a multi-dimensional cultural label index capable of being filed, clustered and classified is generated; the method effectively overcomes the limitation that in the prior art, only stays at an image level and is lack of structure and semantic modeling, enables the Sichuan opera facial makeup pattern to have machine-readable component structure representation and semantic feature representation, and lays a foundation for cultural inheritance and intelligent propagation.

Disclosed herein are methods and system of implementing an AI-enabled high-fidelity occupancy network, allowing for the prediction of signed distances of voxelized objects in a 3D space surrounding an ego, thereby facilitating enhanced object shape refinement. Through the utilization of camera feeds only, an AI model accurately calculates signed distance values for various voxels in the 3D space. The predicted values can also be rendered by translating signed distance field values into image layers and subsequently stacking the layers to form a 3D representation of the space surrounding the ego. Furthermore, the system can predict and display various ground markings, expanding its functionality beyond traditional lane detection.

The invention relates to the technical field of image recognition, in particular to a urinary system CT image tumor benign and malignant identification method based on deep learning, which comprises the following steps: acquiring a urinary system CT image, constructing a map band sequence and extracting gray level distribution, identifying a heterogeneous edge and a texture mutation region, aggregating perturbation map blocks to form an abnormal structure, and identifying the benign and malignant tumors. And fusing multiple types of image layers to complete label integration, and generating a feature recognition image layer. According to the method, the extension recognition capability of the tumor edge external expansion region is enhanced by combining a graph band gray scale aggregation and sequence construction mode, the judgment precision of local heterogeneous change is improved by fusing gray scale kurtosis and migration analysis, and the texture disturbance trend is extracted based on direction vector included angle change. The block gray level fluctuation and gradient relationship supports abnormal structure aggregation identification, spatial coincidence and boundary difference combined screening realizes multi-feature region unified coverage, abnormal region expression definition and structure positioning accuracy are enhanced, and image layer consistency and identification stability are improved.

The invention discloses an intelligent screenshot method, device and equipment for a digital pathological section and a storage medium, and relates to the technical field of medical data processing, the method is applied to front-end equipment, and the method comprises the steps that in response to a section screenshot instruction, viewport parameters of a target section image at a current viewport and size parameters of a screenshot visual area are captured; according to the viewport parameters, drawing the slice image layer locked at the current viewport, the first annotation rendering layer and the second annotation rendering layer to an off-screen synthetic canvas corresponding to the size parameters in sequence, and generating initial screenshot data; and according to the viewport parameter and the size parameter, superposing the scale data on the initial screenshot data to generate target screenshot data. According to the method, the section image, the multi-source labeling information and the dynamic scale can be automatically synthesized during digital pathological section screenshot, manual splicing is not needed, errors are reduced, pure front-end real-time screenshot is achieved, rear-end participation is not needed, the response speed is high, and the real-time interaction requirement is met.

The invention provides an airborne high-speed image hierarchical compression and encrypted storage method and system, electronic equipment and a storage medium, and relates to the technical field of airborne image processing and data security storage. The method comprises the following steps: acquiring an airborne high-speed image sequence, synchronously monitoring surface pneumatic pressure pulsation data of an aircraft, converting the surface pneumatic pressure pulsation data into a deformable mirror surface group curvature control signal, adjusting mirror surface deformation parameters to compensate optical path wavefront distortion, and generating a stable image; air vortex characteristics are extracted to calculate an intensity distribution diagram, turbulence levels are divided, and corresponding compression strategies are adopted; extracting vortex phase features of each level to generate a dynamic key, and encrypting the layered compressed data stream; according to the invention, layered high-efficiency compression and dynamic encryption storage of airborne high-speed images in a turbulent environment can be realized, and data processing effectiveness and storage security are guaranteed.

The invention discloses a resource usage amount statistical method and system oriented to an application mirror image, and belongs to the technical field of cloud computing and containerization. The method comprises the steps that duplicate removal and calculation are conducted on files of all mirror image layers according to the identification result of the files, and the file storage amount is obtained; collecting resource use state data of the application mirror image and inputting the data into the resource competition game model, so that the resource competition game model outputs the calling weight of each process in each mirror image layer and determines a resource occupation ratio by solving a Nash equilibrium strategy; dividing the current system resource usage data to each current process based on the corresponding relationship between each current process and each current mirror image layer, and determining the resource usage amount of each current mirror image layer according to each resource occupation proportion; and summarizing the resource usage amount and the file storage amount of each layer to obtain the total resource usage amount of the current application mirror image, so that accurate statistics of the resource usage amount can be realized.

The invention relates to the technical field of image processing, and discloses a user interface display method and electronic equipment, which are used for shortening the display time of a user interface and improving the image rendering efficiency. In the method, the electronic equipment comprises a container for bearing a client operating system and a host operating system of the electronic equipment. In the process that the container runs the first application, the container can send the generated interface drawing instruction to the host operating system, so that the host operating system executes the interface drawing instruction in the first window cache region to obtain the first image data. The host operating system can also render the first image data of the first window cache region to a layer of the first window so as to display the first user interface on the first window. Therefore, the host operating system can directly render the first image data to the image layer of the first window, only one time of memory copying is needed, the image rendering time is shortened, and the image rendering efficiency is improved.

The invention relates to the technical field of defect detection, in particular to a semiconductor chip surface defect detection method based on deep adversarial supervision, which comprises the following steps: acquiring a chip surface image, and inputting a pre-constructed defect detection model to obtain a defect segmentation result of the chip surface image; the defect detection model comprises an encoder, a decoder and a discriminator; the encoder is used for extracting multi-scale features of the chip surface image; the decoder is used for recovering the spatial resolution of the image layer by layer based on the multi-scale features and outputting a defect segmentation result of a corresponding scale; the discriminator is used for discriminating the difference between the defect segmentation result output by the decoder at the corresponding scale and the real label image at the corresponding scale; the method comprises the following steps: updating parameters of an encoder and a decoder by calculating semantic segmentation loss; and then adversarial training is carried out in combination with the discrimination result of the discriminator, and the parameters of the encoder, the decoder and the discriminator are jointly optimized, so that iterative updating of the parameters of the defect detection model is realized. The defect detection precision can be improved.

A system and method for detecting a cybersecurity issue in a software container layer and mitigating the same is presented. The method includes: detecting a software container including a plurality of layers; associating a first layer of the plurality of layers with a first image of the software container, and associating a second layer of the plurality of layers with a second image of the software container; inspecting each of the plurality of layers for a cybersecurity issue; detecting a cybersecurity object on the first layer, wherein the cybersecurity object indicates the cybersecurity issue; initiating a remediation action on the first image, in response to detecting the cybersecurity object on the first layer.

The invention discloses an image processing method and electronic equipment, and belongs to the technical field of electronics, and the method comprises the steps: carrying out the fuzzy processing of a layer in a first image through employing a GPU, obtaining a fuzzy processing result, and storing the fuzzy processing result in a first cache, the stable image layer is the image layer which has the same size in the continuous multi-frame image and the same position in the image and carries fuzzy attribute information, obtaining a target image layer required for synthesizing a second image, and the second image comprises the stable image layer; a hardware synthesizer (HWC) is utilized to synthesize the fuzzy processing result stored in the first cache and the target layer, so that the second image can multiplex the fuzzy processing result of the first image, and fuzzy processing does not need to be performed through a GPU. Therefore, the power consumption of the electronic equipment caused by layer synthesis and fuzzy processing through the GPU is reduced, and the performance of the electronic equipment is improved.

Methods and systems are provided herein for generating a morphology-based recomposition based on 3-dimensional input image data including an image stack of 2-dimensional (2D) images, the morphology-based recomposition being a final image generated by performing one or more white top hat (WTH) transforms on each 2D image, generating two or more image layers based on two or more WTH transformed images, and scaling adjacent image layers based on one or more scaling factors, each scaling factor being based on an estimated point spread function (PSF), two structure element sizes, and standard deviations of the estimated PSF and image data.

The invention provides a tomato detection method and system based on multi-view parallel three-dimensional modeling, and the method comprises the steps: synchronously obtaining original images under N view angles on an assembly line, extracting a view field image, and distributing a unique view angle code; dividing each visual angle image with the unique visual angle code into a plurality of image blocks distributed with unique block position codes, extracting features of each visual angle image layer by layer by adopting a hierarchical multi-visual-field visual converter, and then performing fusion to obtain a fused multi-visual-angle joint feature sequence; outputting a global three-dimensional point diagram by the global solution head according to the multi-view joint features, and calculating to obtain a tomato size detection result; and outputting a local three-dimensional point diagram by the local solution head according to the multi-view joint features, and obtaining a tomato defect detection result according to the local three-dimensional point diagram and the local semantic information so as to generate a tomato detection result. The method has the beneficial effects that the real-time performance is high, the detection accuracy is high, and the assembly line tomato detection with continuous treatment can be realized.

The invention provides a circuit board defect detection method and system based on deep learning, and the method comprises the steps: firstly obtaining a layered image set of a to-be-detected circuit board, which comprises a welding spot imaging layer, a line imaging layer and an element imaging layer; calling a pre-trained circuit board defect hierarchical detection model, inputting the hierarchical image set into a model defect pre-association layer, and generating a hierarchical defect association map which marks the position mapping relation of the same defect in different imaging layers; on the basis of the layered defect correlation map, extracting defect area exclusive features of each imaging layer to form a layered exclusive defect feature set, and inputting a model hierarchical feature enhancement layer to generate a hierarchical enhanced defect feature set. And finally, calling the model scene adaptive classification layer to carry out defect type matching, and generating a circuit board defect detection report containing defect types, hierarchical positions and association relationships in combination with the position mapping relationship, so that the circuit board defects can be comprehensively and accurately detected, and the detection efficiency and quality are improved.

The invention discloses a wafer surface defect detection method fusing multi-scale dynamic perception and feature decoupling. The method comprises the steps that wafer defects are collected and marked; performing layer-by-layer processing on an input image by using a dynamic convolution module, extracting multi-scale features, and capturing edge and texture information; the input sensing module is used for improving feature discrimination capability through converter coding modeling space dependence; up-sampling and down-sampling are utilized to unify the sizes of feature maps with different scales, and bidirectional information fusion is carried out through a feature enhancement module after splicing; inputting the fused multi-scale feature map into an anomaly detection decoding module, discriminating and positioning an abnormal region through an attention mechanism and a position query mechanism, and outputting a prediction result map containing categories and positions; and entering a reasoning mode to obtain the identified abnormal target area in the wafer image. The method provided by the invention not only improves the detection precision and real-time performance of the model in an early stage, but also effectively reduces the diffusion risk of defects in subsequent processes.

The invention relates to an abnormal phased array radar echo image restoration method based on a generative adversarial network, and the method mainly comprises the following steps: carrying out the preprocessing of radar echo image data, and generating a missing region mask; then, constructing a generative adversarial network model based on a double-flow encoder-decoder, extracting features of input image data and masks through a double-flow encoder, and performing feature fusion; then, a strong echo color correction module and a local detail enhancement module are utilized to perform enhancement processing on the fusion feature map, and detail textures of a shielding region and a strong echo region are restored; reconstructing the image layer by layer through a double-current decoder, and generating a repaired complete image; and finally, carrying out adversarial training by adopting a double-flow discriminator, optimizing a generator, and ensuring the authenticity and accuracy of the repaired image. According to the method, the abnormal region, especially the strong echo region, in the radar echo image can be effectively restored, and the image restoration precision and efficiency are improved.

The invention provides a real-time video image stabilization method and system for performing intra-frame motion compensation based on an IMU (Inertial Measurement Unit). The method comprises the following steps: S1, preprocessing data; s2, track smoothing processing is carried out; s3, performing intra-frame motion compensation: S3.1, initializing line exposure delay time; s3.2, calculating the time difference between the current vth line and the middle line exposure in the current frame image; s3.3, acquiring the smoothed virtual camera pose of the current frame and the real camera pose of each layer; s3.4, acquiring a motion compensation matrix for compensating the line of image to the virtual pose of the frame of image; s3.5, acquiring an image frame perspective transformation matrix according to the camera internal reference matrix K and the motion compensation matrix; s3.6, performing intra-frame motion compensation on the image layers to obtain an initial motion compensation matrix queue; s3.7, carrying out black edge removal processing on the motion compensation matrix queue; obtaining a motion compensation matrix queue after black edge removal; and S4, image transformation output. The system comprises a data preprocessing module, a track smoothing module, an intra-frame motion compensation module and an image transformation output module. The operation efficiency is improved, and the anti-shake real-time performance is improved.

The invention discloses an aluminum foil surface defect detection system based on visual identification, and relates to the technical field of aluminum foil detection, and the system comprises a data acquisition module which is used for obtaining image data and environment data in a detection area; the data processing module is used for processing the obtained image data to obtain a region fusion layer; the image layer optimization module is used for carrying out image layer boundary optimization on the obtained region fusion image layer and splitting the region fusion image layer after boundary optimization to obtain an aluminum foil feature image layer; the defect identification module is used for carrying out surface defect analysis on the aluminum foil characteristic pattern layer and outputting a surface defect analysis result; according to the method, environment data including various standards are set, dynamic matching and layer fusion are performed during detection, and a self-adaptive image analysis reference is constructed, so that imaging quality fluctuation caused by environment illumination change is reduced, and the detection accuracy and reliability in a changeable industrial field are remarkably improved.

The utility model discloses an anti-counterfeit label which comprises a release paper layer, an adhesive layer, a first image-text layer and a lens layer which are sequentially stacked, the first image-text layer comprises a first image-text area, the lens layer comprises a lens area, the first image-text area and the lens area correspond to each other up and down, a pre-deformed original image-text is printed on the first image-text layer, and the pre-deformed original image-text is printed on the lens area. And the lens area is used for enabling the first image-text area to be deformed after passing through the lens area and presenting an original image-text. When a consumer observes the undeformed original image-text through the lens area, normal cognition of the consumer is not affected, a imitator cannot obtain the original image-text with the accurate size and shape, and due to the fact that the image-text printed on the first image-text layer is the printed pre-deformed original image-text, the original image-text can not be directly copied. Even if a counterfeiter obtains the pre-deformed original image-text after damaging the anti-counterfeit label, the difficulty of a consumer in obtaining the specific shape and parameters of the lens area is higher, the counterfeiting difficulty is improved, and the anti-counterfeit effect is improved.

Disclosed herein are methods and system of implementing an AI-enabled high-fidelity occupancy network, allowing for the prediction of signed distances of voxelized objects in a 3D space surrounding an ego, thereby facilitating enhanced object shape refinement. Through the utilization of camera feeds only, an AI model accurately calculates signed distance values for various voxels in the 3D space. The predicted values can also be rendered by translating signed distance field values into image layers and subsequently stacking the layers to form a 3D representation of the space surrounding the ego. Furthermore, the system can predict and display various ground markings, expanding its functionality beyond traditional lane detection.

Methods, systems, and non-transitory computer readable storage media are disclosed for generating visualizations of mask correlations for a layer of a digital image. The disclosed system determines one or more bounding boxes corresponding to one or more hidden areas or one or more visible areas of a layer of a digital image according to a raster mask or a vector mask corresponding to the layer. The disclosed system determines display attributes for the one or more bounding boxes in response to determining that the one or more bounding boxes correspond to the one or more hidden areas or the one or more visible areas. The disclosed system generates, for display with the layer within a graphical user interface, one or more boundary highlights representing the one or more bounding boxes with the display attributes.

A system and method for detecting a cybersecurity issue in a software container layer and mitigating the same is presented. The method includes: detecting a software container including a plurality of layers; associating a first layer of the plurality of layers with a first image of the software container, and associating a second layer of the plurality of layers with a second image of the software container; inspecting each of the plurality of layers for a cybersecurity issue; detecting a cybersecurity object on the first layer, wherein the cybersecurity object indicates the cybersecurity issue; initiating a remediation action on the first image, in response to detecting the cybersecurity object on the first layer.

The invention provides an edge cloud cache configuration method and device based on tensor complementation, and relates to the technical field of containerization deployment in an edge cloud network, the method comprises the steps of decomposing mirror image layer prefetching into prediction of mirror image layer cache and mirror image layer pre-scheduling, combining tensor complementation, an iTransform model and a CP decomposition algorithm, and after the tensor is complemented, obtaining an edge cloud cache configuration result. The iTransform model captures non-stationary dependence among dimensions of tensors through an inverted time sequence attention mechanism of the iTransform model while keeping high efficiency of parameters, steady inference on current time information is realized, so that an accurate mirror image layer prefetching task is supported, a CP decomposition algorithm performs tensor reconstruction on each selectable tensor to calculate a score of each selectable tensor, and the score of each selectable tensor is calculated to obtain a pre-fetching task of the mirror image layer. And finally, taking the selectable tensor with the highest score as a target tensor. Based on the method, efficient prefetching and cache optimization of the AI micro-service mirror image layer can be realized, so that challenges caused by resource limitation in an edge cloud environment are effectively relieved.

The present invention discloses a transparency adjustment method and device, a storage medium, and an electronic device, wherein the method includes: monitoring the sliding distance of a carousel image on a target page; when the sliding distance is greater than a preset threshold, increasing the transparency of a first background image according to a first preset interval, and reducing the transparency of a second background image according to a second preset interval, so that the transparency of the first background image reaches a maximum transparency value, and the transparency of the second background image reaches a minimum transparency value, wherein the first background image is a background image to be disappeared from the target page, and the second background image is a background image to be displayed on the target page, and the first background image and the second background image are stacked. The above technical solution solves the problems of the background image switching method in the prior art, such as the switching process being relatively stiff and the page flickering being prone to occur.