2436 results about "Pixel based" patented technology

The invention relates to the technical field of image detection, in particular to a PCBA board defect detection method and system based on image processing, and the method comprises the following steps: carrying out the meshing calculation of a gray scale deviation after a gray scale image is subjected to Gaussian filtering denoising, generating change rate data, carrying out the statistics of a frequency number, constructing a histogram, combining with an Otsu algorithm, and generating a candidate mask; extracting pixels based on a mask, calculating a gradient modulus, screening edge candidate points, carrying out gradient direction connection and morphological processing to generate a complete edge structure, expanding a connected domain through a region growing algorithm, aligning the connected domain with a template contour, and outputting defect coordinates. According to the method, the defect identification sensitivity is improved through combination of gray level image gridding processing and dynamic threshold calculation, a candidate mask is generated through grid gray level change rate statistics and an Otsu algorithm to avoid over-segmentation missing detection, and the contour precision is improved through combination of gradient modulus difference screening and morphological closed operation optimization. The region growing algorithm and template dynamic alignment reduce deformation misjudgment, and staged dimension reduction and feature enhancement reduce calculation complexity and solve resource waste.

The invention discloses an image semi-supervised semantic segmentation method and system based on pixel-level correction, and relates to the technical field of computer vision and semantic segmentation, and the method comprises the steps: constructing a training data set which comprises a labeled image and an unlabeled image, and the labeled image is an image labeled with a pixel-level label; carrying out random diversity image enhancement to obtain a weakly-enhanced labeled image, a weakly-enhanced unlabeled image and a strongly-enhanced unlabeled image; constructing a teacher-student model; training a teacher-student model by using the training data set, constructing a total loss function based on a supervised loss function, a cross-image unsupervised loss function and an agent-related loss function, and optimizing and updating network parameters of the teacher-student model through the total loss function until the total loss function is minimized, so as to obtain the teacher-student model. Obtaining a trained teacher-student model; and inputting a to-be-segmented scene image into the trained student model, and obtaining and outputting a more accurate image semantic segmentation result.

The invention relates to the technical field of image data processing, and discloses a fine metal powder defect detection method and system based on image recognition, and the method comprises the steps: illuminating a metal powder region through a non-polarized light source, and collecting two images in an orthogonal polarization state through imaging equipment with a linear polarizer, according to the method, the defect morphological fingerprints are constructed through the polarization information entropy, the three-dimensional structure information is converted into light field order degree change for detection, the dimension limitation of traditional two-dimensional imaging is broken through, and the detection accuracy is improved. Hidden defects such as internal pores and aggregates can be accurately identified, and meanwhile, stable detection and material defect cross discrimination under a dynamic working condition are realized in combination with motion compensation and multiband entropy ratio verification.

The invention relates to the technical field of image processing, in particular to a high-voltage power supply element defect identification method based on computer vision. The method comprises the steps of collecting a surface image of a high-voltage power supply element; the method comprises the following steps: acquiring a grayscale image and a connected domain thereof, acquiring a main direction of the connected domain, constructing a width sequence based on a length perpendicular to the main direction, acquiring a width change coefficient according to the width sequence, and acquiring ambiguity of a pixel point based on a pixel point neighborhood grayscale value; constructing a window for the edge pixel points, obtaining the correlation of the edge pixel points according to the classification of the connected domains in the window, obtaining the similarity between the connected domains according to the Fourier descriptors of the connected domains, and obtaining the scratch integrating degree of the edge pixel points based on the similarity; and screening the edge points of the scratch area according to the scratch integrating degree of the edge pixel points and the ambiguity of the edge pixel points, and completing defect identification. According to the invention, the surface defect detection efficiency of the high-voltage power supply element is improved.

The invention provides a metal product surface flaw detection method and system based on machine vision, and belongs to the technical field of machine vision. The method comprises the following steps: constructing a multi-modal image data set through bright field image acquisition, dark field image acquisition and three-dimensional point cloud data acquisition of the surface of a detected metal product, and registering the multi-modal image data set; based on the registration multi-modal image data of pixel-level alignment, pixel-level defect segmentation is carried out by adopting a double-flow diffusion Transform model, and a defect segmentation map is output; and on the basis of the defect segmentation image and the registered multi-modal image data, through segmentation image binaryzation and region extraction, multi-dimensional defect feature extraction and quantification, defect classification and report generation, a final defect detection report is output, and the metal product surface defect detection method is completed. The invention effectively solves the core pain points of low precision, poor robustness and insufficient generalization ability for unknown defects in metal surface flaw detection, and provides an automatic detection method with high reliability and high precision.

The invention discloses a three-dimensional finite element model generation and numerical simulation method and system for a wading engineering composite material XCT digital image, and belongs to the technical field of finite element analysis. Comprising the steps of collecting a composite material XCT image in an initial state and performing preprocessing; performing statistical analysis on the two-dimensional microstructure parameters; a virtual XCT image is generated based on the Pix2PixHD style migration network; the method comprises the following steps of: accurately segmenting each component region of a real XCT (X-ray computed tomography) image based on a Swinin-Transformer network; completing contour feature extraction and smoothing of the segmented image based on a mapping relation between pixels and nodes; constructing a space coordinate system and carrying out discrete derivation on all yarn center points of each segmented image; grid division is carried out based on a multi-material moving cube algorithm in a CGAL library, and a global cohesion unit is inserted; completing material attribute and local material direction distribution; and customizing proper boundary conditions, and carrying out numerical simulation based on a finite element method.

The invention discloses a single-view three-dimensional dressed human body reconstruction method based on pixel and voxel feature fusion. The method comprises the steps of data set preprocessing, data set dividing, three-dimensional dressed human body reconstruction network construction, three-dimensional dressed human body reconstruction network training, three-dimensional dressed human body reconstruction network testing and reconstruction result displaying. In the pixel feature extraction network, the coordinate attention and the stacking hourglass network are combined, so that the pixel feature extraction precision is improved; in the voxel feature extraction network, a three-dimensional channel and space attention are introduced into the voxelization human body parameterization model network, and a multi-scale residual feature extraction module is combined to extract voxel features. And splicing the extracted pixels and voxel feature vectors, inputting the spliced pixels and voxel feature vectors into a multi-layer perceptron, and reconstructing a three-dimensional dressed human body model through Marking Cubes, thereby solving the technical problem of insufficient precision of the existing single-view three-dimensional dressed human body reconstruction method, and being applicable to the technical fields of artificial intelligence and computer vision.

The invention relates to the technical field of screen quality detection, and discloses a dead pixel detection method, system and device for a liquid crystal display screen and a storage medium, and the method comprises the steps: obtaining the pixel distribution information of a to-be-detected display screen, and marking the corresponding pixel coordinates of each pixel point based on the pixel distribution information; after the detection signal is received, pixel points of the display screen to be detected are divided into a plurality of pixel blocks based on the pixel coordinates, and each pixel block is marked with a block identifier; based on the pixel coordinates and the block identifiers, determining block coordinates of each pixel point, dividing each pixel point into a plurality of pixel groups based on the block coordinates, and marking group identifiers for each pixel group; setting a detection sequence based on the group identifier of each pixel group, and controlling each pixel group to display a preset detection image group one by one based on the detection sequence; obtaining display effect images of the display screen to be detected one by one and inputting the display effect images to a preset image dead pixel recognition model to generate dead pixel detection result information; the method has the effect of improving the dead pixel detection efficiency of the liquid crystal display screen.

The invention provides a detection system and method of a display control panel, equipment, a medium and a program product, and relates to the technical field of equipment detection, and the system comprises a test host, and a mainboard to be detected and a detection device which are connected with the test host; the mainboard to be tested comprises a display screen driving module; the test host is used for respectively outputting a test image signal to the mainboard to be tested and the detection device; the to-be-tested mainboard is used for performing signal conversion on the test image signal based on the display screen driving module to obtain a display screen driving signal and outputting the display screen driving signal to the detection device; and the detection device is used for carrying out pixel comparison on image data in the test image signal and the display screen driving signal, and determining a detection result of the mainboard to be detected based on a pixel comparison result. Based on the device, the test precision, efficiency and consistency of the display control panel can be effectively improved, the uncertainty caused by manual intervention is reduced, the test cost is reduced, and the device has high universality and adaptability.

The invention discloses a remote sensing image pseudo label generation method based on prototype perception learning, and a weak supervision change detection model training and detection method, and belongs to the field of remote sensing image change detection. The invention aims to solve the problem that a category activation graph is incomplete in existing remote sensing image weak supervision change detection and the problem that an obtained detection model is unstable in change recognition. According to the method, feature maps of different scales before and after change are extracted from remote sensing images before and after change through a pseudo label generation model, change features are obtained, a class activation mapping map and a class activation mapping map of an unchanged class are obtained, and the class activation mapping map is segmented into response area masks through a threshold value and used for performing weighted aggregation on fusion features to obtain a class prototype; generating an enhanced class activation mapping graph based on the fusion feature and the class prototype, and selecting the class with the highest similarity as a pseudo tag of the pixel; and training based on the pseudo label data of the pixels to obtain a change detection model, wherein the model is used for remote sensing image change detection.

The invention relates to the technical field of power equipment state monitoring, and particularly discloses a transformer fault diagnosis method and system based on image recognition, and the method comprises the steps: collecting a transformer multi-mode image sequence in real time, and carrying out the definition and part integrity evaluation and screening to form an initial image set; performing multi-scale space registration on the initial image set and a transformer normal state standard template to generate a reference image, and reversely deriving a displacement vector field based on pixel-level difference; carrying out smooth optimization and geometric reconstruction on the displacement vector field under the geometric constraint of the transformer structure, and generating a correction image with a real structure; fault feature enhancement is carried out in a gradient domain of the corrected image, a fault area is identified through matching of multichannel feature extraction and a transformer typical fault feature library, and a diagnosis report integrating fault types, confidence coefficients and geometric parameters is generated; according to the method, the problem of image geometric deformation caused by shooting condition differences is effectively solved, and the accuracy and reliability of fault identification are improved.

The invention discloses a dynamic scene reconstruction method and device based on a multi-scale Gaussian sphere, and relates to the field of computer vision, and the method comprises the steps: employing a motion recovery structure algorithm to carry out the processing of a to-be-reconstructed video frame sequence, generating a sparse point cloud, carrying out the initialization of the sparse point cloud, and generating a 3D Gaussian sphere set; processing the 3D Gaussian ball set by adopting a double-domain deformation model and an adaptive timestamp to obtain a deformed 3D Gaussian ball set; performing multi-scale Gaussian processing on the deformed 3D Gaussian ball set to generate a multi-scale Gaussian ball set; gaussian screening based on the pixel coverage rate is carried out on the multi-scale Gaussian ball set, and an optimized multi-scale Gaussian ball set is obtained; and performing Alpha hybrid processing based on the optimized multi-scale Gaussian ball set, and reconstructing to obtain an anti-aliasing dynamic rendering scene image. According to the method, the problems of high calculation overhead, aliasing effect and the like of the current dynamic scene reconstruction are solved.

The invention relates to the technical field of data processing, and discloses a visual data comprehensive processing method for automobile industrial data based on digital twinning. The method comprises the following steps: performing recursive quartering on a three-dimensional space of an automobile general assembly workshop through a workshop process pixel quadtree index algorithm, performing process type marking on multi-source heterogeneous data according to a process identification mapping rule, and allocating a workshop real-time data set to a quadtree index structure according to space coordinates to perform process state aggregation, and according to the viewport pixel mapping relation, performing weighted aggregation calculation on the process state aggregation matrix to obtain a pixel comprehensive display value, and based on the pixel comprehensive display value, performing layered rendering processing on the workshop multi-process parallel scene. According to the invention, the visual processing efficiency and the user interaction response speed of the digital twin system in the automobile industry are improved.

The invention discloses an image denoising and self-adaptive enhancement method based on pixel discretization and illumination guidance, and relates to the technical field of image processing, and the method comprises the steps: carrying out the down-sampling and noise reduction of an input image, and obtaining a preliminarily denoised image through the deconvolution operation, fuzzy pixel discretization and residual serialization; estimating an illumination component from the preliminarily denoised image by using an illumination estimation network; calculating a reflection image based on the estimated illumination component and the preliminarily denoised image according to an image enhancement theory; based on a dynamic splicing mechanism, splicing the reflection image and the illumination component in the channel dimension to obtain a spliced image; and with keeping of image details and brightness information as a criterion, denoising and enhancing are carried out on the spliced image through a reflection denoising network, and a denoised and enhanced image is output. According to the invention, high-quality recovery of low-illumination images is realized, and the intelligent level of an electric power inspection system is improved.

The invention provides an anomaly detection method and device for image data and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: carrying out the feature extraction of the image data, fusing the spectrum and spatial features to obtain a joint feature matrix, and inputting an anomaly detection model; the model adopts an alternating direction multiplier algorithm to solve a low-rank sparse decomposition problem, and an objective function comprises a data fidelity item, a regularization item and a waveband weight item; the regularization item comprises a low-rank constraint and a sparse constraint, and the wave band weight item acts on the low-rank constraint in a weighting form; updating a background low-rank tensor, an abnormal sparse tensor, a Lagrange multiplier, a sparse constraint weight, a wave band weight item and penalty parameters of an algorithm by adopting an iteration mode in a solving process; and repeating iteration until a preset termination condition is reached, calculating an abnormal score graph pixel by pixel based on the abnormal sparse tensor, and comparing to determine an abnormal target. The problem that an abnormal target is difficult to accurately recognize in a complex scene can be solved, and detection precision and efficiency are improved.

The invention relates to the technical field of image processing, in particular to an intelligent recognition and positioning system for battery support welding defects. Obtaining defect degrees and edge pixel points of the pixel points according to gradient features and neighborhood gray features of the pixel points in the welding image; obtaining change complexity according to the change characteristics of the local edges of the edge pixel points; edge sharpness is obtained according to the local gradient features and the gray level change features of the edge pixel points; obtaining local uniformity according to the local gray level distribution characteristics of the edge pixel points; obtaining a confidence coefficient according to the change complexity, the edge sharpness and the local uniformity; and obtaining an adjustment factor of the edge pixel point according to the confidence coefficient and the defect degree. The method comprises the following steps: adjusting a weighting coefficient in a high-lift filtering algorithm according to an adjustment factor to obtain a self-adaptive weighting coefficient; performing image enhancement and defect identification according to the adaptive weighting coefficient; and the accuracy of image enhancement and defect identification is improved.

The invention discloses an image acquisition method, which comprises the following steps that: a control unit sends an image acquisition control signal to each pixel unit through a first control pin, generates a first analog signal based on the pixel control signal, and sends the first analog signal to a first data output line through a first column line; the even-numbered row pixel units generate a second analog signal based on the pixel control signal and send the second analog signal to a second data output line through a second column line; the reading circuit sends the first analog signal, the second analog signal and the state signal to the image processing unit through the data pin and / or the first control pin; and the image processing unit obtains a target acquisition image according to the first analog signal and the second analog signal. According to the invention, the photosensitive analog signals from the pixel matrix can be transmitted to two different multiplexing pins in parallel through the two data lines of the readout circuit, and the frame rate of signal transmission is improved under the condition that a clock is not changed.

The invention belongs to the technical field of image processing, and particularly relates to an oil and gas engineering supporting facility intelligent detection method based on machine vision, and the method comprises the steps: constructing a structure tensor matrix based on the gradient of pixel points, calculating a local linear structure response value according to two feature values of the structure tensor matrix, and calculating a local linear structure response value; according to the direction alignment degree of the feature vectors of the pixel points on the local path, the crack continuity of the pixel points is calculated, the morphological significance values of the pixel points are comprehensively obtained and used for adjusting basic contrast parameters, anisotropic diffusion processing is carried out on the to-be-detected image of the oil and gas facility based on the obtained self-adaptive contrast parameters, and the to-be-detected image of the oil and gas facility is obtained. An enhanced image is obtained through multiple times of iterative updating, and a defect detection result graph is obtained through edge detection. According to the method, the problem that false defects are easily misjudged as cracks in a traditional method is solved, and the detection accuracy and reliability are remarkably improved.

The invention relates to the technical field of image processing, solves the technical problems of low detection precision, poor correction effect and poor applicability in dead pixel detection and correction of an image sensor in the prior art, and particularly relates to a dead pixel detection and correction method and system for an image sensor. The method comprises the following steps: acquiring L original images of all pixels of an image sensor under different radiation quantities, calculating the optimal fitting slope and intercept of each pixel point in the L original images, forming a parameter matrix which has the same size as the original images and contains statistical information, judging dead pixels in the pixels based on the statistical information of the parameter matrix, and judging whether the dead pixels are defective pixels or not. And generating a dead pixel table corresponding to the original image. According to the invention, the image quality can be effectively improved, the image distortion is reduced, and the image processing result is improved. Especially under the condition that the image content is complex, dead pixels can be detected and corrected more accurately, and the detection precision and the correction effect are improved.

The embodiment of the invention discloses an interface interaction method which comprises the steps that drawing attribute information of all components in source codes of a target interface and interaction event information corresponding to all the components are read, and the source codes are written in a component form; generating an interface canvas based on the drawing attribute information of each component, the interface canvas containing each component of the target interface; generating an interaction canvas based on the position attribute information and the size attribute information of each component; based on the interface canvas, rendering the target interface in the browser page; in response to the monitored event triggered based on the target interface, determining a pixel coordinate of an event triggering position in the interaction canvas; and based on the pixel coordinates, obtaining a target component for the event, and executing a response operation of an interaction event corresponding to the target component. According to the embodiment of the invention, the consistency of the user interfaces in the browser pages of the terminals can be realized, so that the consistency of event interaction response is ensured.

The invention discloses a pressure damage classification system based on image processing, which belongs to the technical field of image processing and comprises a pressure damage image acquisition module, a pressure damage image preprocessing module, a pressure damage classification model construction module and a pressure damage classification module. According to the method, a comprehensive noise characteristic value is obtained based on a pixel variance, an LBP value variance and a distance weight, an adaptive filtering weight is calculated, bilateral filtering and Gaussian filtering are fused for denoising, a detail enhancement factor is generated in combination with a local entropy value and a Sobel gradient amplitude, detail enhancement is carried out, the local contrast is enhanced, and the image quality is remarkably improved; according to the method, multi-scale features are extracted and fused, a space-channel attention mechanism is introduced to obtain a global weight, global enhanced fusion features and local enhanced fusion features are obtained, and comprehensive features are generated through fusion, so that the capability of identifying stress damage in different stages is remarkably improved.

The invention relates to the technical field of pattern classification, in particular to a pattern classification method and system based on a regional label, and the method comprises the following steps: extracting a local label threshold based on a pixel gray range, analyzing the regional difference of a pattern image, screening a change optimal group as a reference, analyzing a gradient direction and amplitude mutation, and screening layered breakpoints. And integrating the regional features, and judging category attribution to obtain a discriminant quantity. According to the method, detailed pixel relation analysis and regional structure feature extraction are executed step by step, label affiliation accurate adjustment is achieved based on local statistics and spatial attribute association synchronization, boundary anomaly is judged through gradient and label change multiple parameters, layering is carried out, nodes are automatically positioned according to attribute mutation, and category affiliation is decided by multi-dimensional attribute interaction. Layered and partitioned analysis of high-detail and complex patterns is realized, hierarchical attribution requirements under multiple scenes are adapted, the region classification accuracy is enhanced, and the response capability to the internal differential and hierarchical relationship of the pattern structure is improved.

The invention provides a light spot position detection method, an automatic focusing method, a related system and a storage medium. A first light source is controlled to emit a first light beam to irradiate a to-be-detected sample, and a focusing sensor is controlled to receive the first light beam reflected from the to-be-detected sample; acquiring pixel data generated when the focusing sensor senses a light spot, formed on the focusing sensor, of the first light beam, and determining the center pixel position of the light spot based on the pixel data so as to determine the position of the light spot. According to the invention, the position of the light spot can be determined, so that the automatic focusing system can perform automatic focusing based on the position of the light spot, and the image definition is improved. Besides, in the invention, the light spot position is determined by using the central pixel position in the pixel data sensed by the focusing sensor, and the central pixel position can represent the central position of the light spot, so that the light spot position determination accuracy can be relatively high by determining the light spot position based on the central pixel position; therefore, the accuracy of automatic focusing and the image definition are improved.

The invention provides a spinal medical image registration method and system based on semantic reconstruction. Constructing spinal column 3D-CT image data and corresponding 2D image data of the spinal column 3D-CT image data; providing a 2D-3D reconstruction model, and reconstructing the 2D image data to obtain a 3D feature map b; providing a 3D-3D feature extraction model, and taking 3D-CT image data as input to obtain a feature map s with the same dimension as the 3D feature map; providing a parallel double-U-shaped network model based on cross attention, and fusing and registering the feature map b and the feature map s; a multi-weight loss function based on pixel and semantic information is adopted for optimization; and training to obtain a registration model, and performing spine medical image registration by using the registration model. According to the method, the information and precision loss caused by dimension reduction is avoided, the 2D / 3D information fusion capability is improved, the attention weight of the key semantic region is improved, and accurate spine image registration can be realized while the image shooting times can be reduced.

The invention relates to the field of image processing, in particular to a circuit board microsection image defect detection method, which comprises the following steps: acquiring a circuit board microsection image, calculating local direction energy of each pixel point in the image in a preset scratch direction, and generating a direction energy diagram; calculating a direction continuity index of each pixel point by analyzing neighborhood energy distribution of each pixel point in the preset scratch direction; according to the direction continuity index, constructing a spatially adaptive scratch similarity for each pixel point; and on the basis of the scratch similarity, executing spatial adaptive anisotropic filtering processing on the circuit board microsection image so as to realize accurate detection of circuit board defects. According to the method, by intelligently recognizing the structural difference between the scratches and the defects, the background scratches are accurately removed, meanwhile, the contour integrity of the real defects is kept, and the accuracy and reliability of microsection defect detection are remarkably improved.

An imaging system can include a plurality of imaging sensors configured to receive light reflected by a tissue region in at least a first predetermined waveband and one or more processors configured to cause the image sensors to capture images of the tissue region and identify corresponding sets of pixels in the captured images, each set comprising a pixel of a first image captured by a first image sensor and a pixel of a second image captured by a second image sensor. The processor can determine distance or depth values associated with the individual corresponding sets of pixels based on pixel desparities for the pixels of the corresponding sets of pixels and a baseline distance between the first and second image sensors, and generate a 3D model of the tissue region based at least in part on the distance values.

Methods and systems for providing multi-plane viewing of a digital image of a subject matter which do not require viewing multiple images taken at multiple image planes. Pseudo-focus images are generated from a flattened, merged image of a three-dimensional subject matter. The merged image is generated by merging a plurality of images taken at different focal planes of the subject matter which form a through-focus image stack. The merged image comprises the best focus pixels originating from different respective image planes. A depth map is also generated from the multiple images which associates each best focus pixel with a pixel depth value. A plane of interest (POI) is selected from the image planes. A pseudo-focus image is then generated using the merged image and pixel depth map by generating a blurred focus value for each best focus pixel based on the focus offset of each pixel from the POI.

Methods and systems are disclosed for using machine learning models to perform pixel-based deformation of fashion items using N-flows estimation. The methods and systems receive one or more images depicting a first person in a first pose and receive a source image depicting a target fashion item worn on a portion of a body of a second person in a second pose, the target fashion item comprising a plurality of parts. The methods and systems process, using one or more machine learning models, the one or more images together with the source image to generate a set of data comprising a plurality of flow fields each associated with a different one of the plurality of parts of the target fashion item. The methods and systems modify a portion of the one or more images to overlay the target fashion item on the first person in the first pose.