16 results about "Line defects" patented technology

The invention provides an electric power line defect detection method and system based on visual identification, and relates to the technical field of line detection.The method comprises the steps that firstly, a visible light and infrared image dual-light registration and differential operation technology is adopted, and a fusion feature map capable of reflecting component thermal anomaly and material difference at the same time is generated; secondly, a black box type target detection model is abandoned in a part positioning link, but line segment screening and reconstruction are carried out by combining probability Hough transform with specific prior geometric knowledge of a power line, so that dependence on a large amount of labeled data is reduced, interpretability of a positioning process is enhanced, and the positioning accuracy is improved; according to the method, accurate areas of key components such as wire insulators can be extracted in a complex background, the concept of a probability saliency map is introduced in a defect identification core link, so that a defect area is enhanced and highlighted, and then a complete defect contour is determined by adopting an adaptive threshold segmentation and area growing algorithm; accurate mapping from pixel-level features to object-level defects is realized.

The invention discloses a periodic defect-based low-dielectric-loss monocrystal diamond preparation method, which belongs to the field of semiconductors, and comprises the following steps: providing a diamond substrate; the diamond substrate is subjected to photoetching treatment, so that a dot matrix pattern is formed on the upper surface of the diamond substrate through photoetching, and the distance between every two adjacent dots in the dot matrix pattern is equal to the wavelength corresponding to the frequency of the external electric field; an etching process or an ion implantation process is adopted, the area where each point in the dot matrix pattern is located is damaged, a diamond damaged substrate is obtained, and the upper surface of the diamond damaged substrate is provided with a periodic defect dot matrix structure; growing a single crystal diamond layer with periodic defects on the upper surface of the diamond damaged substrate, and adjusting a growth process to enable the defects on the single crystal diamond layer to be line defects penetrating through the single crystal diamond layer; and carrying out fragmentation treatment on the damaged diamond substrate and the monocrystal diamond layer to obtain a monocrystal diamond finished product with periodic defects.

Embodiments of the present application provide a method and device for detecting defects of a ground wire and a medium. The method comprises: acquiring a left view and a right view of a target region synchronously collected by a binocular imaging device; the target region includes a ground wire to be detected; based on the left view and the right view, a first depth map corresponding to the target region is acquired; pixel points outside a preset distance range in the first depth map are removed to obtain a second depth map; the left view, the right view and the second depth map are input into a pre-trained semantic segmentation model to obtain an image segmentation result; and based on the image segmentation result, a defect detection result of the ground wire to be detected is acquired. The method is used to improve the detection accuracy of defects of the ground wire.

The invention discloses a substrate with a prefabricated hole structure and a processing method and processing equipment thereof. The substrate with the prefabricated hole structure comprises a semiconductor substrate and the prefabricated hole structure formed on the semiconductor substrate. The edge of the processing area of the prefabricated hole structure is defined as an extension distance h from the processing boundary of the hole structure to the interior of the semiconductor substrate, wherein h is equal to the average radius of the hole structure / 10; the semiconductor substrate has no depth area defect, and the depth area defect is an observable line defect or surface defect extending to the interior of the semiconductor substrate along the edge of the processing area for more than h; taking any cross section of the semiconductor substrate, and observing the edge of a processing area by adopting SEM characterization; the prefabricated hole structure is directly formed by a laser processing method and is not subjected to a cleaning or post-treatment process. The substrate has no depth area defect, so that an expansion path of the depth defect in subsequent device manufacturing can be blocked from the source, the problems of substrate cracking and fragment caused by the defect are avoided, the damage rate of the substrate in the subsequent process is reduced, and the material utilization rate is improved.

The invention discloses a machine vision identification method and system for a zinc flow line defect of a galvanized sheet, and relates to the technical field of zinc flow line defect identification of the galvanized sheet, a Stokes vector method is adopted to perform polarization state decomposition on an original image sequence, diffuse reflection light and specular reflection light are separated, and an enhanced image is obtained; a dynamic contrast stretching algorithm is combined, a high-contrast flow line gradient map is obtained, a local direction field is calculated through a Hessian matrix according to the flow line gradient map, dynamic structure elements are generated based on the direction field, asymmetric closed operation is carried out, and a connected defect binary mask is obtained; according to the method, the structural elements are adaptively selected according to the actual direction of the zinc flow lines, it is guaranteed that important geometric information cannot be lost in the processing process, and the processing accuracy is improved. The existence of the defect can be identified, and the type and severity of the defect can be further judged.

The application discloses a multi-dimensional PWQ method for BEOL process defect hotspot detection of an integrated circuit, which comprises the following steps: 1) adopting a traditional PWQ method to detect and screen out weak patterns within a process window range of a target metal layer; 2) for the weak patterns within the process window range, calling a GDS of a same layer of the target metal layer, a via hole GDS of an upper layer of the target metal layer and a via hole GDS of a lower layer of the target metal layer to form three-layer GDS; 3) aligning and measuring original image data obtained by EP5 shooting with the three-layer GDS to complete multi-dimensional D2DB processing; 4) calculating a landing coverage ratio of a via hole on a line of the target metal layer, combining a defect detection result of a line of the same layer to judge a connection condition of the target metal layer and the via holes of the upper and lower layers; and 5) generating a detection report containing line defect information of the same layer and the landing coverage ratio of the via hole. The application can realize defect detection of a same layer wiring, obtain information of connection holes of upper and lower layers and evaluate the connection condition of the same layer metal and the connection holes / via holes of the upper and lower layers.

The invention discloses a line defect detection method and device, a storage medium and a product, and relates to the technical field of defect detection.The method comprises the steps that a first binarization image obtained after an original image is subjected to preliminary binarization processing is obtained, and all independently-connected first areas in the first binarization image are determined; performing ellipse fitting on each first region in the first binary image and filling the ellipse regions to obtain a second binary image; determining each independently connected second region in the second binary image; determining a weighting coefficient of a global threshold value and a local threshold value according to a first region and a second region in the global region; and carrying out weighted summation on the global threshold and the local threshold according to a weighting coefficient to obtain a self-adaptive binarization threshold, carrying out binarization processing on the global region by adopting the self-adaptive binarization threshold to obtain a third binarization image, and carrying out detection based on the third binarization image to obtain a line defect detection result. The detection accuracy of the line defect of the display screen or the optical lens is improved.

The invention provides a manufacturing method of a blank EUV mask substrate. The method comprises the following steps: step 1, providing a transparent substrate; 2, depositing a preset number of Bragg pairs on the surface of one side of the transparent substrate to form a reflection stacking layer; 3, scanning the reflection stacking layer by adopting a laser confocal microscope and a white light interferometer respectively, and analyzing whether the reflection stacking layer has defects according to detection results of the laser confocal microscope and the white light interferometer; 4, when the reflection stacking layer does not have defects, the step 2 and the step 3 are executed repeatedly until all the logarithm Bragg pairs are deposited and defect detection is completed, and a Bragg reflection layer without defects is formed; and 5, when the reflection stacking layer has defects, returning to the step 1. The method not only can effectively detect the surface defect and the embedding defect of the blank EUV mask substrate, but also can accurately position the defect depth, has cost effectiveness, and is suitable for non-destructive online defect detection.

This invention relates to an online defect detection system and method for refractory material sintering. It obtains a standard sequence of body temperature and an ambient temperature standard sequence based on the heating curve. The time-series thermal imaging image of the refractory material sintering process is segmented into a body image based on the refractory material stacking area and an ambient image based on the surrounding environment. An ambient temperature sequence is extracted from the ambient image. Based on the ambient temperature sequence and the ambient temperature standard sequence, the range of suspected defects is determined based on the obtained defect features. The range of suspected defects is extracted from the body image, and a temperature feature sequence of the suspected defect range is obtained. The degree of deviation between the temperature feature sequence and the temperature standard sequence is obtained. Based on the degree of deviation, it is determined whether a defect exists in the suspected defect range. Furthermore, time-series synchronization analysis is used to distinguish between physical defects and thermal interference. This invention improves detection efficiency and reliability through environment-oriented and localized focusing strategies, making it suitable for online detection needs.

The application relates to the fields of image processing and smart grid maintenance technology, and discloses a power transmission line defect image intelligent identification and grading method, which acquires high-dimensional visual features, preliminary classification confidence and a space mask matrix of an original image; calculates the topological risk weight of a target defect; splices the visual features and the topological risk weight to perform database retrieval, acquires a search prior grade and an evolution anchor point image; when the preliminary classification confidence is lower than a threshold value, decoupling interpolation and cross-level judgment are performed on the original image and the anchor point image in a latent space based on the mask matrix, and a gradient jump point is output; finally, the search prior grade, the topological risk weight and the gradient jump point are fused to calculate a comprehensive risk score, and a defect severity grade is output by comparing the threshold value. The application fuses historical experience, spatial mechanics attributes and evolution trend multi-dimensional parameters, solves the problem that a critical state defect is easily misjudged by single feature grading, and improves the reliability of the grading result.

The invention provides a photomask plate defect detection method of a photoetching machine. The photomask plate defect detection method of the photoetching machine comprises the following steps: irradiating a photomask plate through a light source of the photoetching machine, and obtaining a photomask plate image by a camera of the photoetching machine; performing line defect detection on the photomask image through a spatial domain Gaussian function and a gray domain Gaussian function; performing block defect detection by performing adaptive threshold binarization and morphological closed operation on the photomask image; and carrying out two-dimensional Gaussian kernel-based image convolution and Laplacian convolution on the photomask image to carry out fuzzy particle defect detection. Therefore, the detection effect of the photomask plate defect of the photoetching machine can be improved by detecting the line defect, the block defect and the fuzzy particle defect on the basis of the photomask plate image in a targeted manner.

The application discloses a line defect detection method and device of a display panel, and the method comprises the following steps: dividing a first pixel driving circuit column with a line defect into N pixel driving circuit groups; cutting off the positions of a data line and a compensation signal line connected by the first pixel driving circuit column between two adjacent pixel driving circuit groups in the direction from the display area to the binding area; when the cutting-off position is between the i-th pixel driving circuit group and the i+1-th pixel driving circuit group, if the light-emitting element corresponding to the first pixel driving circuit column in the driving stage does not display a dark line, and / or the line defect detection signal in the badness detection stage is less than the detection threshold, then the defect position of the line defect is located in the i-th pixel driving circuit group; the line defect detection signal is the difference between the sensing signal before a set time period and the sensing signal after the set time period. The technical scheme provided by the application can accurately lock the short-circuit line defect position of the display panel.

This application discloses a method, apparatus, and storage medium for detecting point and line defects in display screen images, which improves the accuracy of display screen defect detection. The method involves: acquiring an image of the display screen to be tested; randomly selecting location pixels from the image and generating a location circle region based on these pixels; calculating the gray-level gradient vector from the sample pixels within the location circle region to the corresponding location pixels, and calculating the mean of the gray-level gradient vector; calculating the Euclidean distance between the sample pixel located at the mean of the gray-level gradient vector and each location pixel to generate an abnormal contour region; performing region filtering on the image, and generating a difference image based on the mean gray-level of the remaining region and the image; pre-segmenting and extracting the difference image to generate the defect region to be tested; applying an array projection estimation algorithm to the defect region to be tested to generate a suspected line defect region; and performing feature filtering on the suspected line defect region to generate a set of point defects and line defects.

1. The name of the design product: power distribution line defect detector. 2. The use of the design product: for power distribution line defect detection. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view 1.

The present disclosure relates to a micro LED display apparatus, and to a display apparatus capable of stably driving a gate driver in a gate in active (GIA) circuit. According to the present disclosure, a gate driver in the GIA circuit of a display apparatus can be stably driven without the appearance of horizontal line defects.

This invention provides a method and system for detecting power line defects based on visual recognition, belonging to the field of power line detection technology. Firstly, this invention employs dual-light registration and differential computation techniques using visible light and infrared images to generate a fused feature map that simultaneously reflects component thermal anomalies and material differences. Secondly, in the component localization stage, it abandons the black-box target detection model and instead utilizes probabilistic Hough transform combined with prior geometric knowledge specific to power lines for line segment selection and reconstruction. This not only reduces the dependence on large amounts of labeled data but also enhances the interpretability of the localization process, enabling the extraction of precise regions of key components such as conductors and insulators from complex backgrounds. In the core defect identification stage, the concept of a probabilistic saliency map is introduced, enhancing the prominence of defect areas. Subsequently, adaptive threshold segmentation and region growing algorithms are used to determine the complete defect contour, achieving accurate mapping from pixel-level features to object-level defects.