230 results about "Defective pixel" patented technology

The invention relates to the technical field of defect detection, in particular to an efficient identification and detection method for printing defects on the surface of a metal plate. The method comprises the following steps: acquiring a difference characterization value and a suspected judgment index value of a pixel point to be detected, and acquiring a suspected defect pixel point according to the suspected judgment index value; clustering all the suspected defect pixel points according to the suspected judgment index values and the coordinate values of the suspected defect pixel points to obtain each cluster; according to the difference characterization value of the suspected defect pixel point, the gradient direction of the suspected defect pixel point in the cluster to which the suspected defect pixel point belongs and the gray value standard deviation and mean value of all the suspected defect pixel points in the cluster to which the suspected defect pixel point belongs, obtaining an abnormal degree characterization value of the suspected defect pixel point; and performing printing defect identification on the surface of the to-be-detected printed metal plate according to the abnormal degree characterization value. And the identification accuracy of the printing defect area on the surface of the printing metal plate can be improved.

The embodiment of the invention provides a defect detection method, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining the actual morphology data of one or more local regions of a target wafer and a global layout of the target wafer, and carrying out the global layout of the target wafer for each local region based on the mapping relation between the wafer morphology and technological parameters, determining a prediction process parameter corresponding to the actual morphology data of the local region, and predicting the wafer morphology of the global layout under the prediction process parameter of the local region for each local region based on a mapping relationship between the wafer morphology and the process parameter to obtain wafer morphology prediction data, and determining the defective pixel areas of the target wafer based on the predicted wafer morphology prediction data corresponding to each local area, determining a to-be-detected area from all the defective pixel areas, and scanning the to-be-detected area of the target wafer by using defect scanning equipment to obtain a defect detection result, so as to effectively improve the efficiency and precision of defect detection.

The invention provides a Mini led display screen dead pixel detection and positioning method, device and system based on deep learning, and the method comprises the steps: applying a preset driving signal sequence to a pixel array of a Mini led display screen line by line, obtaining the brightness feedback data of each pixel in different driving stages, obtaining a brightness response sequence, and carrying out the detection and positioning of the dead pixel of the Mini led display screen. Carrying out spatial recombination processing on the brightness response sequence according to a physical arrangement structure of the pixel array to generate a brightness response matrix, carrying out local region feature difference analysis on the brightness response matrix, identifying a brightness response abnormal region, generating a candidate dead pixel position set, and obtaining a candidate dead pixel position set; and calling a pre-trained dead pixel recognition network to carry out feature learning processing on the candidate dead pixel position set, outputting a dead pixel probability corresponding to each candidate dead pixel position, screening the candidate dead pixel position set based on the candidate dead pixel probability, removing candidate positions with the dead pixel probability lower than a preset condition, and generating a dead pixel positioning result set. According to the invention, the accuracy and reliability of detecting and positioning the defective pixels of the Mini LED display screen can be effectively improved.

The invention discloses a method and system for detecting surface defects of a sheet metal part before coating, and the method comprises the following steps: S1, multi-modal data collection: synchronously collecting three-dimensional point cloud data and a hyperspectral image of the surface of the sheet metal part through a laser three-dimensional contourgraph and a hyperspectral camera, and recording environment illumination and temperature parameters at the same time; s2, data preprocessing: performing denoising and smoothing processing on the three-dimensional point cloud, extracting surface contour features, and performing defective pixel repair, waveband selection and reflectivity correction on the hyperspectral image; according to the surface defect detection method and system before coating of the sheet metal part, through multi-modal data acquisition and fusion of the three-dimensional morphology and the hyperspectral features, compared with traditional single visual detection, the surface defects of the sheet metal part can be more comprehensively and accurately recognized, particularly, tiny defects and oxide layer defects which are difficult to distinguish by naked eyes, the recognition rate is remarkably increased, and the detection accuracy is improved. And by adopting the lightweight deep learning model, the detection precision is ensured, and the reasoning speed is improved at the same time.

In the embodiment, the location of the defective pixel can be determined by measuring the operating current of each LED of the pixel, and the sub-LED can be driven in response to the location information of the defective pixel, thereby implementing normal LED operation even in a pixel defect situation.

The invention relates to the technical field of dead pixel detection and compensation of a digital light processing projection system, in particular to a DLP dead pixel calibration and compensation method and system based on a Transform attention mechanism. According to the DLP dead pixel calibration and compensation method based on the Transform attention mechanism, a multi-scale feature pyramid is constructed, global features are extracted by using a layered multi-mode Transform encoder, and a dead pixel confidence coefficient heat map is generated in combination with a dynamic sparse mask multi-head attention mechanism; dynamically selecting compensation strategies for different types of dead pixels by adopting a dead pixel type-scene demand dual-drive time-space domain compensation pipeline; ambient light and partition temperature sensor data are integrated, and the influence of optical crosstalk and thermal drift is eliminated through a brightness adaptive calibration function; and finally, carrying out closed-loop verification and iterative optimization by adopting a loss function fused with HVS perception loss. According to the method, the defective pixel detection precision is improved from 82.3% to 99.2%, the PSNR after compensation is improved from 32.6 dB to 42.5 dB, the processing delay is reduced to 7ms / frame, and the visual quality and reliability of a DLP system are improved.

The invention relates to the technical field of infrared detection, and discloses an infrared detector dead pixel detection method, which comprises the following steps: acquiring a current scene image during the working period of an infrared detector and a plurality of frames of isothermal uniform surface background images acquired by the infrared detector at different working temperatures to form a background image sequence; performing singular point detection on each frame of image in the current scene image and the background image sequence by adopting an improved wavelet transform algorithm, screening out effective singular points, and calculating a singularity value of each effective singular point; based on the singular point detection result, the singularity value difference and historical background image data, static dead pixels, dynamic dead pixels and noisy points are distinguished through a multi-layer judgment rule, and a dead pixel detection result is obtained; and periodically evaluating the accuracy of the defective pixel detection result, and dynamically calibrating the detection parameters according to the evaluation result. Through collaborative analysis of the current working image and the multi-temperature background image sequence, dead pixels can be accurately detected in real time in the normal working process of the detector.

The present application discloses an image reconstruction method, an apparatus, a device, a medium, and a product. According to the image reconstruction method in the embodiments of the present application, all Swin Transformer modules of an encoding module are connected by means of a patch merging layer; all Swin Transformer modules of a decoding module are connected by means of a patch expanding layer; the encoding module and the decoding module are symmetrical in structure; and finally, an upsampled feature map is input into a reconstruction module so as to obtain an RGB image by means of conversion. By constructing a network on the basis of a U-Net structure, the present solution is able to restore a corresponding high-resolution RGB image from a feature map, and interpolate missing values and defective pixels in a RAW image captured by an event camera while performing demosaicing, thereby obtaining a high-quality RGB image. Moreover, the use of Swin Transformer architecture as a feature extractor allows for the effective capturing of long-range dependencies, and ensures that consistency of local and global information is maintained.

A display device includes: a display panel including a plurality of pixels; a sensing circuit to generate sensing values of the plurality of pixels by sensing characteristics of the plurality of pixels; and a panel defect normalizer to compensate for the sensing values, the panel defect normalizer including: a preliminary defective pixel detector to detect a preliminary defective pixel; a defective pixel detector to detect a defective pixel; a defective line detector to detect a defective line; a defective line compensator to compensate for a sensing value of the defective line; and a defective pixel compensator to compensate for a sensing value of the defective pixel.

The invention relates to the technical field of display screen detection, and discloses a display screen dead pixel positioning method based on image feature matching, and the method comprises the following steps: collecting image data of a display screen in different test modes to generate a feature matrix, and constructing a dead pixel detection template set; setting a reference parameter type, obtaining a pixel distribution characteristic, a brightness gradient and a chrominance offset of a historical image, and establishing a final matching degree associated equation; extracting a pixel distribution characteristic and a brightness gradient parameter of a current display screen, and generating a characteristic matching set and a brightness parameter set by combining equation optimization; and updating detection logic to generate a target positioning scheme, calibrating a pixel coordinate mapping relation, and carrying out binarization processing on calibrated coordinates to generate a dead pixel position marking matrix. According to the method, through multi-mode feature analysis, parameter dynamic association and coordinate calibration, the efficiency and accuracy of dead pixel positioning are improved, and the method is suitable for dead pixel detection of various display screens.

The invention discloses a pixel response inconsistency correction method and system. The method relates to the technical field of pixel response correction and comprises the following steps of pixel dynamic offset calculation, flat field coefficient acquisition, pixel-level comprehensive correction and dead pixel self-repairing secondary optimization. The method comprises the following steps: acquiring a dark frame image and real-time temperature data, and calculating a dynamic offset of a pixel by means of a temperature-time double-domain prediction model; a flat field coefficient is obtained by fusing a basic value calibrated by a laboratory miniature integrating sphere in a full spectrum band and an updated value obtained by in-orbit observation of a deep space and a cloud top and processing of dead pixel detection and the like; then combining a GPS, an attitude angle and a real-time temperature, and using an offset and a flat-field coefficient to carry out pixel-level correction; and finally, a gain compensation matrix is output by means of a deep reinforcement learning model containing a convolutional neural network and a long-short-term memory network, the image is secondarily optimized through a dead pixel self-repairing module, the pixel response inconsistency correction precision is improved, and the problem that in the prior art, the pixel response inconsistency correction error is large is solved.

Provided is a photodetection device capable of suppressing generation of defective pixels. Specifically, the photodetection device includes a semiconductor substrate on which a plurality of photoelectric conversion units is formed; and a plurality of optical filters disposed on a light incident surface side of the semiconductor substrate. Furthermore, each of the optical filters includes a metal structure including a metal material of the same kind. Moreover, the photodetection device includes, between the metal structures, a slit portion spatially sectioning the metal structures.

The invention provides a mask pattern optimization method, a medium, a product and equipment. The method comprises the following steps: acquiring a mask pattern to be corrected and a corresponding ideal photoetching pattern; calling an artificial intelligence model in the inversion photoetching tool to generate a photoetching simulation result according to the mask pattern to be corrected; calculating a cost value according to the photoetching simulation result and the ideal photoetching graph; correcting the mask pattern to be corrected based on the cost value by using an inversion photoetching algorithm to obtain a corrected mask pattern; and taking the corrected mask pattern as a to-be-corrected mask pattern, and repeatedly executing the step of calling the artificial intelligence model in the inversion photoetching tool to generate a photoetching simulation result according to the to-be-corrected mask pattern until a preset cycle ending condition is met, thereby obtaining an optimized mask pattern. Through the method, the inversion photoetching tool can be highly matched with an OPC tool of a corresponding manufacturer, so that a process window of a dead pixel area is effectively improved, and a solid foundation is laid for improvement of the overall yield of technical nodes.

The invention relates to a camera pixel dead pixel detection and correction method and system, a terminal and a medium, and relates to the technical field of image detection and correction, and the method comprises the steps: determining a plurality of light intensity points based on the maximum light intensity responded by a camera pixel, and controlling a uniform light source to irradiate a camera to obtain an image data set; calculating a plurality of response coefficients corresponding to each pixel based on the image data set; performing dead pixel discrimination on each pixel of the camera based on the first response coefficient matrix, the second response coefficient matrix and the goodness-of-fit matrix to generate a dead pixel matrix; and for each pixel, determining the type of the pixel based on a dead pixel matrix, and correcting the gray value of the pixel based on the type and position of each pixel and a preset dead pixel correction algorithm to obtain a corrected image data set. According to the invention, the dead pixel of the camera pixel can be accurately detected, the pixel gray value is effectively corrected, and the image quality is improved.

The invention relates to the technical field of liquid crystal screen detection with a defective pixel classification function, and discloses a liquid crystal screen detection method and device with the defective pixel classification function, and the device comprises a classification base, a conveying belt arranged at the top of the classification base, a second conveying belt arranged at the top of the classification base, and a third conveying belt arranged at the top of the classification base. The surface of the classification base is fixedly connected with a support, a cleaning and detecting device is arranged above the classification base, a classification device is arranged above the classification base, and a collecting device is arranged on the surface of the classification base. When the conveying belt is started, the liquid crystal display above the conveying belt can be driven to move, when the liquid crystal display passes through the position below the cleaning soft brush, the cleaning soft brush can clean dust above the liquid crystal display, and it is avoided that the accuracy of machine detection is affected by the dust; and dust cleaned by the cleaning soft brush can enter a dust collection box through a dust collection cover through a dust collection pipe, and collection work is carried out.

The invention discloses an adaptive gradient descent optimization image dead pixel compensation method and system, and relates to the technical field of image processing, and the method comprises the steps: intercepting image frames of a received image data stream collected by a short wave infrared sensor according to a preset interval; calculating a gradient descent iteration value of the image group by adopting a self-adaptive gradient descent iteration algorithm; traversing each pixel point of each image frame in the image group, pre-estimating a pre-estimated pixel value corresponding to each pixel point according to the gradient descent iteration value, and calculating a decision factor according to a difference value between the pixel value of each pixel point and the pre-estimated pixel value corresponding to the pixel value; and judging whether each pixel point is a defective pixel or not according to a comparison result of the judgment factor of each pixel point and a preset threshold value, and if the pixel point is the defective pixel, replacing the pixel value of the defective pixel with the estimated pixel value. The self-adaptive gradient descent decision factor of each pixel is calculated in real time, and the dead pixel is identified by judging the difference between the estimated value and the actual value, so that real-time, self-adaptive and high-precision identification and compensation of the dead pixel are realized.

A display device comprises a plurality of first LEDs disposed in a first passivation layer. Each first LED has a first electrode disposed on the respective first LED and a second electrode that is electrically coupled to a control device. A contact of at least one second LED is directly bonded to the first electrode of at least one first LED. The second LED and the first electrode of the at least one first LED are disposed in a second passivation layer. An electrode of the second LED is electrically connected to a same control device that the second electrode of the at least one first LED is connected to.

An inspection apparatus includes: a memory; an image sensor configured to obtain a luminance image of the display apparatus comprising a plurality of pixels; and a processor configured to recognize a defective pixel based on the obtained luminance image, configured to recognize location information of the recognized defective pixel, and configured to control the memory to store the recognized location information of the defective pixel.

The application discloses a display panel, a repairing method thereof and a display device. The display panel comprises a substrate, a conductive layer and a pixel unit, and the pixel unit is arranged in an array in a first direction and a second direction. The substrate comprises a substrate, an array layer and an electrode layer, the pixel unit comprises a light emitting device, the light emitting device is connected between a first pad and a second pad of the electrode layer, and the light emitting device is used for emitting light. In the pixel unit, an in-situ area and a redundant area are arranged side by side in the second direction, the light emitting device can be arranged in the in-situ area or the redundant area, when the light emitting device in the in-situ area is damaged, the conductive layer in the in-situ area and the redundant area can be removed at the same time when the damaged light emitting device is removed, so that the first pad and the second pad are exposed in the in-situ area and the redundant area, and then the intact light emitting device is moved into the in-situ area or the redundant area and connected between the first pad and the second pad, so that the bad point repairing is realized.

The invention discloses a vehicle machine screen two-dimensional coupling detection method and system, and belongs to the technical field of computer vision and industrial automation detection. Obtaining a vehicle machine screen image stream through a multi-source video access layer; the vehicle machine screen image flow is input into a pre-trained YOLOv5-Heat multi-mode model, a screen abnormity type is recognized, and the screen abnormity type comprises at least one of color cast, dead pixels, full-screen abnormity and overheat points; analyzing the identified screen abnormity by adopting a two-dimensional coupling algorithm, and generating an early warning signal of a corresponding grade based on a result of the two-dimensional coupling algorithm; and when the early warning signal level is serious abnormity, an abnormal signal is converted into a CAN frame through the weekly standing power module, an instruction is sent to the execution module through the control bus, the relay module is controlled to execute power-off operation, and the vehicle machine is triggered to be restarted. The method is obviously superior to the prior art in five dimensions of detection precision, real-time performance, reliability, easy deployment and later cost.

The present disclosure relates to an electronic device and an imaging element configured so as to be able to avoid further degradation in performance. The imaging element is provided with, for each of a plurality of pixels, a single-photon avalanche diode (SPAD) that generates avalanche multiplication as a result of the supply of a reverse bias voltage, the imaging element further comprising: a storage unit into which address information indicating an address of a defective pixel has been written; a digital processing circuit that outputs a pixel selection signal, for selecting the defective pixel, in accordance with the address information read from the storage unit; and a retention unit that is provided for each pixel and retains defect information indicating whether the pixel is a defective pixel. For each pixel, the retention unit provided in a pixel selected by the pixel selection signal output from the digital processing circuit retains defect information indicating that the pixel is defective, and outputs a control signal for blocking supply of the reverse bias voltage to the SPAD. The present technology can be applied to, for example, an imaging element in which a SPAD is used.

This disclosure provides a method, apparatus, electronic device, and storage medium for correcting image defects. The method includes: for any pixel in the image data to be processed, determining a target data window with a preset scale centered on that pixel; determining whether the center pixel meets preset conditions based on the target data window, the preset conditions including a first condition for the pixel value of the center pixel to be satisfied and / or a second condition for the pixel values ​​of the same channel type in at least one direction corresponding to the center pixel to be satisfied; if the center pixel meets the preset conditions, determining the center pixel as a defective pixel; determining a corrected target pixel value for the center pixel based on the pixel values ​​of other pixels in the target data window; and determining corrected target image data corresponding to the image data to be processed based on the target pixel value. This method effectively balances defective pixel recall and high-contrast edge preservation, thereby improving the accuracy of defective pixel correction.

To provide an inspection device capable of determining whether each pixel of an inspection image is a defective pixel or a non-defective pixel without setting a model image.SOLUTION: The inspection apparatus specifies a search range away from the target pixel by an integer multiple of the pitch of the periodic pattern. When the target pixel is a non-edge pixel, the inspection device determines whether the target pixel is a defective pixel or a non-defective pixel according to a comparison result between a minimum value of a density difference between the target pixel and a pixel included in the search range and a first threshold. When the target pixel is an edge pixel, the inspection device determines whether the target pixel is a defective pixel or a non-defective pixel according to a comparison result between a minimum value of a difference in the change direction of the density gradient between the target pixel and the pixel included in the search range and a second threshold value.SELECTED DRAWING: Figure 1

The invention provides an image sensor dead pixel detection method and electronic equipment, and the method comprises the steps: carrying out the mean filtering of each pixel point, and obtaining the mean pixel of each pixel point; according to whether the deviation degree of the original pixel value of each pixel point relative to the mean value pixel exceeds a preset threshold range or not, judging whether the pixel point is a defective pixel or a good pixel, and obtaining pixel point state image data of each pixel; traversing the pixel point state image data to obtain connected dead pixels, and storing pixel values and pixel coordinates in a dead pixel connected region where the connected dead pixels are located in a linked list; acquiring a pixel gradient value of each pixel point in the defective pixel communication region, and acquiring a dark point circle and a bright point circle; and according to the circle centers, the radiuses and the number of pixel points of the dark spot circle and the bright spot circle, judging that the defective pixel communication region is a dirty or defective pixel cluster. Through the image sensor dead pixel detection method provided by the invention, the accuracy of pixel detection can be improved.

The application discloses an electrophoretic coating liquid, an electrophoretic display panel and a display device. Compared with the prior art, the application adds an enal compound into the electrophoretic coating liquid, the aldehyde group and the double bond of the enal compound react with gelatin and resin monomers or unsaturated resin in the microcapsule wall respectively to form an aldehyde amine condensation and addition reaction, so that a firm molecular structure is formed, the microcapsules are uniformly dispersed in the electrophoretic coating layer, the dispersibility of the microcapsules in the electrophoretic coating layer is improved, appearance defects such as empty points, scratches, convex points and bad points of the electrophoretic coating layer are avoided, and the yield of the electrophoretic display panel is improved. In addition, the enal compound is bonded with the microcapsule wall and the bonding strength between the microcapsules and the glue material is enhanced, so that the cracking of the coating layer caused by bending, folding and the like can be avoided.

The invention provides an image static dead pixel correction device and method, an image sensor and imaging equipment. The image static dead pixel correction device comprises a first-stage decoding module, a second-stage decoding module and a third-stage decoding module, wherein the first-stage decoding module reads a two-dimensional static dead pixel cluster corresponding to at least one line of image data including a current image data line from a nonvolatile memory; decoding each two-dimensional static dead pixel cluster and recoding in the X direction to obtain a plurality of one-dimensional static dead pixel clusters in the X direction, and storing the plurality of one-dimensional static dead pixel clusters in a cache region; the secondary decoding module reads the one-dimensional static dead pixel cluster corresponding to the current image data row and decodes the one-dimensional static dead pixel cluster to obtain a plurality of static dead pixels; the dead pixel marking unit determines static dead pixels to be corrected in the current image data row according to a plurality of static dead pixels corresponding to the current image data row; and the dead pixel correction unit corrects the static dead pixel to be corrected. According to the method, the nonvolatile storage space and the internal cache space can be saved, the static dead pixel correction efficiency is improved, and the method is suitable for static dead pixel clusters in any shape.

The present invention discloses a method and related device for optimizing the imaging quality of a multispectral sensor, relating to the field of image processing technology. The method comprises: analyzing the focus parameters of the multispectral sensor on a target object to obtain the target focus parameters; analyzing the imaging impact of ambient light intensity on the multispectral sensor to match the target exposure parameters; correcting the original image data based on a non-uniformity correction matrix; performing white balance processing on the corrected original image data based on the target gain of each color channel obtained by scene light source confidence analysis; and performing bad pixel correction, linear conversion, and fusion processing on first and second decomposed image data obtained by decomposing the white-balanced original image data to obtain the target image. The present invention improves the color expression of the imaged image and more effectively optimizes the imaging quality of the multispectral sensor.

The application discloses a kind of low-illumination scene-oriented adaptive image noise reduction processing method, it is related to digital image processing technical field.The steps include: step S100: low-illumination image is collected and preprocessed, preprocessing includes dark current correction, bad point repair and lens distortion correction;By using back-illuminated CMOS sensor to collect image and execute dark current correction, bad point repair, the preprocessing operation of lens distortion correction, in combination with average brightness and gray standard deviation division low-illumination grade, according to noise intensity and distribution characteristics identify noise type, again based on preset parameter mapping table adaptive matching filter window size, noise reduction intensity weight and detail retention threshold technical means, it is difficult to eliminate in the process of low-illumination image acquisition fixed noise and system error, traditional noise reduction algorithm parameter fixed cannot adapt to different low-illumination grade and noise type, the problem of over-reduction or noise reduction deficiency, image edge detail loss is serious in noise reduction process.

The invention provides a display panel and a display device. The control end of at least one transistor in a pixel circuit in the display panel is electrically connected with a gate line; the shading structure is located on the side, close to the substrate, of the gate line and the pixel circuit, and the shading structure comprises a first shading structure extending in the first direction; the gate lines and the first shading structures are at least partially overlapped in the direction perpendicular to the plane where the substrate is located; the first shading structure has an opening; the gate line comprises a first side and a second side which are opposite in a second direction, and the second direction is crossed with the first direction; the opening is overlapped with the first edge and the second edge of the at least one gate line in the direction perpendicular to the plane where the substrate is located. According to the invention, the short-circuit defect of the gate line can be repaired, only local dead pixels appear during display after repair, and transverse bright and dark lines can be prevented from being displayed.

The invention provides an automatic detection method and system for dead pixels of a liquid crystal display screen, and relates to the technical field of liquid crystal display, and the method comprises the steps: scanning the liquid crystal display screen, and obtaining a drive response feature space; carrying out dead pixel detection according to the driving response feature space; performing driving signal distortion correction according to the dead pixel detection first map; performing detection scene interference compensation on the defective pixel detection second map; performing display scene mining on the liquid crystal display screen, and performing scene adaptive defective pixel detection according to a display scene space; and fusing the third dead pixel detection atlas and the fourth dead pixel detection atlas to generate a fifth dead pixel detection atlas. The technical problem that in the prior art, due to the fact that dead pixel detection depends on fixed threshold judgment or simple signal response distinguishing, intermittent dead pixels and weak defects are difficult to capture and prone to being interfered by signals, dead pixel detection precision is insufficient is solved, multi-driving-signal analysis is carried out, multiple compensation is carried out on the detection result, and the detection accuracy is improved. And the dead pixel detection precision is improved.