73 results about "Mask set" patented technology

The invention relates to a stacked cargo positioning method and device. The method comprises the steps of identifying acquired image data, constructing a dynamic grid based on a spatial distribution rule of an initial mask, and performing local fine segmentation on missing grids in the dynamic grid to obtain a total mask set; performing mask quality optimization and anomaly elimination on the total mask set based on the multi-dimensional matching degree of the dynamic grid to obtain a correct mask set; performing coordinate system reverse transformation on the correct mask set based on the original coordinate system of the image data to obtain a correct binary mask, and positioning the stacked goods; according to the method, the acquired image data is identified, a dynamic grid is constructed, and a mask quality optimization and anomaly elimination mechanism is combined, so that the problem of segmentation noise caused by factors such as non-uniform illumination and cargo shielding in a warehouse environment is effectively solved, high-precision positioning on low-computing-power equipment is realized, and the method is suitable for large-scale popularization and application. The problem that the positioning precision of stacked goods on low-computing-power equipment such as an embedded platform is insufficient is solved.

The invention relates to an impregnated paper production quality detection method and system based on deep learning, and the method comprises the following steps: S1, obtaining an industrial camera image flow, sensor and process parameters, and event and work order information, and constructing a synchronous data packet; s2, preprocessing the synchronous data packet to obtain preprocessed image data, process data and an ROI mask; s3, obtaining a detection frame set and a segmentation mask set based on multi-model AI detection and segmentation according to the preprocessed image data, the process data and the ROI mask; s4, segmenting the mask set according to the detection frame set, and performing track clustering along the paper feeding direction to form a defect event flow; s5, on the basis of the defect event stream, performing online quality prediction and root cause analysis, and obtaining future interval quality prediction and key factor sorting; and S6, according to future interval quality prediction and key factor sorting, adaptive process optimization is carried out, and an optimal control instruction is obtained. According to the invention, the detection accuracy and fineness are effectively improved, and intelligent identification and cross-frame tracking of defects are realized.

A pixel arrangement structure, a display panel, a display apparatus and a mask group are provided. The pixel arrangement structure includes basic pixel units in first and / or second directions. Each basic pixel unit includes five sub-pixels, first to third sub-pixels are of different colors, and third to fifth sub-pixels are of a same color; the first sub-pixel includes opposite first and second sides in the first direction, and opposite third and fourth sides in the second direction; and the second sub-pixel is on and separated from the third side of the first sub-pixel, the third sub-pixel is on and separated from the first side of the first sub-pixel, fourth and fifth sub-pixels are both on the fourth side of the first sub-pixel and are separated from the fourth side of the first sub-pixel, and are separated from each other in the first direction.

The utility model discloses a parallel correction device of an exposure machine. The parallel correction device comprises a mask assembly, a correction assembly arranged on the mask assembly and a moving assembly, the correction assembly comprises an air cylinder, a correction plate arranged on the air cylinder and a plurality of correction balls arranged on the correction plate; the air cylinder controls the correction plate to enter and exit between the moving assembly and the mask assembly, one end of the correction ball abuts against the side, close to the correction plate, of the mask assembly, and the moving assembly drives a film source to move in the direction close to the mask assembly through torsion control. Therefore, the film source abuts against the plurality of correction balls. According to the utility model, the moving assembly drives the film source to move towards the correction balls, and the torsion-controlled moving assembly ensures that the uniformly distributed correction balls respectively abut against the photomask and the film source, so that the photomask and the film source are arranged in parallel, the alignment time is shortened, the productivity is improved, the exposure effect of the film source is improved, and the rework rate of products is reduced.

The invention relates to a perception identification method for verification and evaluation of a space autonomous capture full task chain, and the method comprises the steps: shooting a space region containing a target through a fixed binocular camera, and reconstructing a three-dimensional point cloud model of the space region where the target is located; a mask set of a target to be grabbed is screened out through a deep learning image segmentation algorithm and target feature comparison, a target three-dimensional point cloud is obtained through mapping, geometric centroid calculation and coordinate system conversion are carried out on the point cloud, and a three-dimensional center coordinate of the target under a base coordinate system of the space robot is obtained; a monocular camera carried at the tail end of the space robot is used for shooting multi-view images of a target, and a high-precision target three-dimensional point cloud model with a continuous surface is generated; carrying out fusion registration on the high-precision target three-dimensional point cloud model and the three-dimensional point cloud model of the space region where the target is located to obtain a target complete geometric model with accurate scale and pose; and the optimal grabbing pose and path are calculated. And the problem of autonomous perception and recognition of the robot in the autonomous grabbing process in the space environment is solved.

A method for manufacturing a display device is provided. [Solution] The method includes placing a substrate and a first mask assembly inside a chamber, passing a vapor-deposited material through the first mask assembly to form first counter electrodes in the first and second display areas of the substrate, varying the position of at least one of the substrate and the first mask assembly, passing a vapor-deposited material supplied from a vapor deposition source through the first mask assembly to form a second counter electrode superimposed on the first and second display areas, respectively, the first counter electrode and a second counter electrode, at least a portion of which is superimposed, after replacing the first mask assembly with the second mask assembly, supplying vapor-deposited material from the vapor deposition source to the substrate to form a third counter electrode and a fourth counter electrode in the second display area, and forming a main counter electrode in the third display area of ​​the substrate, wherein the third counter electrode connects the fourth counter electrode to one of the first or second counter electrodes, and the third and fourth counter electrodes have different areas on a plane.

There is provided a mask assembly, a method of manufacturing the mask assembly, and an electronic device manufactured using the mask assembly, the mask assembly including: a mask frame including a first opening portion and including a first portion doped with an N dopant; and a mask disposed on the mask frame and including a plurality of second opening portions overlapping the first opening portions.

A method includes: providing color images for a geological rock core sample, creating initial masks for a subset of the color images, dividing each color image into sets of image tiles, splitting the sets of image tiles into a training set and a validation set, augmenting the training and validation sets, including orienting each image tile in a same direction by sample depth, training a model with the augmented training validation sets, generating image masks from the trained model, corresponding to the color images, combining the sets of image tiles to regenerate each of the color images from their image tile sets, applying the generated image masks to the color images to generate greyscale masked images, stacking the greyscale masked images by sample depth, and applying colors to the stacked greyscale masked images to generate and display a stacked color image representing the entire sample length.

The present application provides an organic device, a mask set, a mask, and a method for manufacturing an organic device. The organic device can include a substrate, a first electrode on the substrate, an organic layer on the first electrode, and a second electrode on the organic layer. In a case where the substrate is observed in a direction of a normal line of the substrate, the organic device can include a first display region including the second electrode having a first occupancy ratio, and a second display region including the second electrode having a second occupancy ratio smaller than the first occupancy ratio. In the second display region, the organic layer can be arranged in a first direction and arranged in a second direction intersecting the first direction. In the second display region, the second electrode can include electrode lines arranged in the first direction. The electrode lines can include electrode segments arranged in the second direction and overlapping the organic layer. Two electrode segments adjacent in the second direction can be connected to each other. The electrode segments can include a first electrode segment having a first shape, and a second electrode segment having a second shape different from the first shape.

A mask assembly includes a mask frame having an opening area, and a mask sheet disposed on the mask frame to overlap the opening area, the mask sheet including a first area, and a second area surrounding the first area. The first area includes a first opening pattern that is a half-etched pattern, the second area includes a second opening pattern that is a penetrating pattern, and in a plan view, the first opening pattern and the second opening pattern are different from each other.

The invention provides a mask group plate for an ion implantation process and a use method. The mask group plate comprises a zero-layer mask plate and at least one current mask plate, at least one first overlay mark is arranged on the zero-layer mask plate, and the first overlay mark is of a first rotational symmetry structure with a first symmetry center; at least one second overlay mark is arranged at the position, corresponding to the at least one first overlay mark, of the current mask plate, and the second overlay mark is of a second rotational symmetry structure with a second symmetry center; the second symmetric center coincides with the first symmetric center, the rotational symmetry of the first rotational symmetric structure is the same as that of the second rotational symmetric structure, and the angular displacement of the second overlay mark and the first overlay mark is zero.

A screen printing device includes a stage on which a display panel is disposed, a mask assembly disposed on the display panel, a coating member for applying a polymer paste onto the mask assembly, a pressing member for bringing the mask assembly into contact with the display panel, and a blocking member disposed at an edge of the mask assembly.

The present disclosure provides a pixel arrangement structure, a fine metal mask set and a display apparatus. The pixel arrangement structure includes a plurality of sub-pixel repetition units along a first direction or a second direction. The plurality of sub-pixel repetition units each form a plurality of pixel units. The sub-pixel repetition units each include one or more first color sub-pixels, one or more second color sub-pixels and one or more third color sub-pixels. Each of the first color sub-pixels and each of the second color sub-pixels independently belong to one pixel unit respectively, and each of the third color sub-pixels is shared by two pixel units. The first direction intersects with the second direction.

The application discloses an explainable attribution method and system based on a star atlas semantic segmentation model, a device and a storage medium, and belongs to the technical field of deep space exploration image processing. The star atlas image is subjected to gray processing and gradient calculation, and the image is divided into super-pixel regions based on a gradient minimum strategy; a regional-level topological structure diagram is constructed, and node links are established based on spatial adjacency and brightness gradient similarity; the structural importance of each region is calculated, a center point of a mask is sampled, a directional elliptical Gaussian perturbation mask set is generated according to a gradient main direction angle; the perturbation mask is applied to the original image, and a semantic segmentation model is input to calculate a saliency score; and saliency information is propagated in the topological structure diagram based on a graph attention mechanism, and a structural saliency explanation diagram is constructed. Through regional division and topological propagation of terrain perception, model explanation of spatial continuity and terrain consistency is realized, and the technical problems that a traditional method ignores the physical characteristics of terrain structure and lacks a propagation path description are solved.

Described herein are photonic communication platforms that can overcome the memory bottleneck problem, thereby enabling scaling of memory capacity and bandwidth well beyond what is possible with conventional computing systems. Some embodiments provide photonic communication platforms that involve use of photonic modules. Each photonic module includes programmable photonic circuits for placing the module in optical communication with other modules based on the needs of a particular application. The architecture developed by the inventors relies on the use of common photomask sets (or at least one common photomask) to fabricate multiple photonic modules in a single wafer. Photonic modules in multiple wafers can be linked together into a communication platform using optical or electronic means.

The present invention provides a deposition mask manufactured in combination of an etching method and a plating method, a manufacturing method thereof, and a deposition mask assembly including the same. The deposition mask manufacturing method includes the steps of forming a resist on a first surface and a second surface of a metal plate, leaving a plurality of first resist patterns on the second surface, forming a plating layer on a remaining portion except for the portion where the first resist patterns are left, leaving a plurality of second resist patterns on the first surface, etching a remaining portion except for the portion where the second resist patterns are left, and peeling off the first resist patterns and the second resist patterns.

Provided is a mask assembly manufacturing apparatus including a mask stage for seating thereon a mask frame defining an opening, a clamp unit at one side of the mask stage, and comprising first clamps arranged in a first direction and configured to clamp a first edge of a first mask sheet, and to position a second edge of the first mask sheet, which is opposite to the first edge, over the opening, a sensor configured to sense the second edge of the first mask sheet, and a controller configured to align the first mask sheet by adjusting the first clamps based on information regarding the second edge from the sensor.

An apparatus for manufacturing a display device including a mask assembly including a mask frame and a mask sheet, the mask frame including an opening area and the mask sheet covering the opening area, wherein the mask sheet includes a body fixed to the mask frame, an opening arranged in the body, the opening through which a deposition material passes, and a corrector arranged in the body and configured to correct deformation of the opening, and the corrector includes a correction hole penetrating the body and a correction member crossing at least a portion of the correction hole and being cuttably connected to the body.

The application relates to the technical field of multi-sensor fusion, in particular to a laser radar-camera external parameter automatic calibration method and a calibration device, wherein the method comprises the following steps: based on a vehicle-mounted laser radar and a camera, point cloud data and image data of a road scene are synchronously collected; image data is subjected to semantic segmentation to generate a semantic mask set of each image; based on the point cloud data, the geometric properties of the road scene are extracted from a vectorized map, and the laser radar coordinate system of the vehicle-mounted laser radar and points in the vectorized map are projected into the image in combination with the semantic mask set, a target consistency function is constructed; based on the target consistency function, an external parameter matrix is adjusted until the target consistency function reaches a maximum value, and automatic calibration is completed. Therefore, the problems that related technologies rely on a large amount of labeling data or specific environments, have poor generalization ability, cannot combine high-precision maps and road prior information, and result in insufficient calibration precision and difficulty in meeting the high-precision perception requirements of automatic driving are solved.

The present invention relates to a mask assembly and a method of manufacturing the same. The method includes forming a unit mask including a mask pattern and a mesh frame including a conductive pattern disposed to correspond to the mask pattern, respectively, and disposing the unit mask and the mesh frame on a mask frame. Forming the unit mask and the mesh frame includes forming a polymer layer, a conductive layer, and a hard mask layer, forming a mask pattern layer including an etching pattern, and forming the unit mask and the mesh frame using the mask pattern layer.

A mask assembly and a manufacturing apparatus of a display device are disclosed. The present invention includes a mask frame equipped with a first opening portion, a support member arranged in at least one of a first direction and a second direction and disposed in the mask frame to divide the first opening portion into at least one second opening portion and at least one third opening portion, and a division member disposed to overlap the support member.

The invention relates to a mask assembly and a method of manufacturing the same. The method comprises the following steps: providing a wafer; forming a first inorganic layer on the wafer; forming a second inorganic layer on the first inorganic layer; etching the wafer to form a cell opening; forming a photosensitive layer on a rear surface of the first inorganic layer exposed through the cell opening; etching the photosensitive layer to form a plurality of photosensitive openings; isotropically etching the first inorganic layer to form a plurality of first openings overlapping the plurality of photosensitive openings; and anisotropically etching the second inorganic layer to form a plurality of second openings overlapping the plurality of first openings.

The utility model provides a mask for deposition and a mask assembly comprising the mask for deposition. The mask for deposition includes: a mask unit region having a plurality of pixel openings; and the edge areas are respectively arranged on two sides of the mask unit area along the first direction. Each of the pixel openings extends in a second direction that intersects the first direction. Each of the pixel opening portions has a first width in the first direction at both side edge portions in the second direction, and each of the pixel opening portions has a second width in the first direction smaller than the first width at a center portion in the second direction.

The invention relates to a method of manufacturing a mask assembly. A method of manufacturing a mask assembly includes: providing a wafer; forming a photoresist layer on the wafer; placing a photomask over the photoresist layer, and irradiating light to the photoresist layer through the photomask to form a photoresist opening penetrating the upper and lower surfaces of the photoresist layer; forming a mask pattern including silicon (Si) in the photoresist opening using a chemical vapor deposition process; and removing the photoresist layer.

Disclosed herein is a mask, a mask assembly, and a method of manufacturing a mask. The mask includes a polymer film defining at least one cell region and at least one peripheral region therein, the at least one peripheral region surrounding the at least one cell region; a conductive layer disposed on the polymer film and including a metal; an inorganic layer disposed between the polymer film and the conductive layer and including a silicon-based inorganic material; and a plurality of holes penetrating the polymer film, the conductive layer, and the inorganic layer and superimposed on the at least one cell region in a plan view.

A mask setting apparatus is provided to reliably and efficiently calculate the three-dimensional plane of a workpiece as the measurement object through automated mask processing. When acquiring three-dimensional information of the workpiece from a three-dimensional sensor, the mask setting apparatus of the present invention sets a mask for three-dimensional points outside the measurement object area so that these three-dimensional points cannot be used in the calculation of the three-dimensional plane. The mask setting apparatus includes: a contour extraction unit that extracts the contour of the workpiece by performing pattern recognition on a two-dimensional image of the workpiece captured by a camera; a height information acquisition unit that acquires height information related to the contour from a distance image in the three-dimensional information acquired by the three-dimensional sensor; and a mask setting unit that sets a mask for areas other than the workpiece based on the height information.

This application relates to a method, apparatus, readable storage medium, and program product for human image instance segmentation. The method includes: acquiring human image mask inference results at different scales of the original image; performing deduplication processing on each human image mask based on the degree of mask overlap between the inference results to obtain a candidate mask set; acquiring the local images corresponding to the candidate masks in the original image from the candidate mask set, and using the local images to perform boundary correction on the candidate masks to obtain corrected masks; generating quality quantization information for each corrected mask using a pre-trained visual language model, and determining the human image instance segmentation result of the original image based on the quality quantization information. This method can improve the accuracy of human image instance segmentation in high-density crowd images.

Provided are a mask, a mask assembly, and a method for manufacturing a mask assembly, the mask including: an effective mask region located in a middle portion of the mask, wherein the effective mask region includes a plurality of first through holes arranged in an array; and a welding region configured to be welded to a mask frame and located on opposite sides of the effective mask region, wherein the welding region includes a plurality of second through holes arranged in an array.

A manufacturing method of a mask assembly includes tensioning a mask sheet, connecting the tensioned mask sheet with a mask frame, and defining opening processing areas in the tensioned mask sheet to form openings respectively corresponding to the opening processing areas. The defining of the opening processing areas includes defining initial opening processing areas in the tensioned mask sheet in a first direction and in a second direction crossing the first direction to determine a processing sequence of the initial opening processing areas, calculating cumulative deformation amounts accumulated in each of the initial opening processing areas based on the processing sequence, and correcting a size and a position of each of the initial opening processing areas based on the cumulative deformation amounts.

This application discloses a method, apparatus, and device for processing image materials, relating to the field of image processing technology. It can finely divide the text and background portions of an image material, avoiding processing errors caused by large-scale image restoration. The method includes: receiving an image material; obtaining text regions from the image material; generating a mask for the text regions; dividing the text regions into bright and dark regions using the average grayscale value of the text regions, with the bright and dark regions corresponding to the text and background portions respectively; identifying the correspondence between the bright and dark regions and the text and background portions respectively; merging the masks of all text regions in the image material using the correspondence to generate a mask set for the image material; and processing the image material using an image restoration algorithm based on the mask set to obtain the restored image material.