168 results about "Defect region" patented technology

The invention relates to a defect detection method and device for an optical element, computer equipment and a storage medium. The method comprises the following steps: acquiring a target image of an optical element; based on the trained defect detection model, performing defect detection on the target image to obtain a defect identification frame corresponding to at least one detection target and a corresponding defect type label; the defect detection model is obtained based on deep learning model training; and carrying out fusion processing on the defect identification frames of the labels with the same defect type to obtain a defect area in the optical element. By adopting the method, adjacent or overlapped same-class defect areas can be effectively merged, so that a complete defect contour and a complete distribution range can be accurately restored.

The invention relates to a wafer defect detection method and system based on image neighborhood analysis, and the method comprises the steps: carrying out the image collection of a to-be-detected wafer, and obtaining a digital image containing a complete wafer back surface; performing traversal detection on each wafer back pixel point in the digital image; in the traversal detection process, through a dynamically adjusted single-size neighborhood window and / or a fixed multi-size neighborhood window, carrying out abnormity determination on the currently traversed wafer back pixel points until determination of all pixel points in the digital image is completed, and obtaining all abnormal pixel points; and carrying out clustering processing on the abnormal pixel points to obtain candidate defect areas in the digital image. Through the wafer defect detection method and device, a dynamic detection strategy and a fusion detection strategy are realized, the misjudgment risk of a global threshold is effectively overcome, the consistency of real defect detection is ensured, the defect detection precision of the wafer is improved, and the problem of how to improve the defect detection precision of the wafer is solved.

The invention relates to the technical field of optical waveguide master mask manufacturing processes, and discloses a monitoring and correcting method and system for an optical waveguide master mask etching process, and the method comprises the steps: setting a plurality of monitoring regions and corresponding monitoring point positions, and collecting the real-time monitoring data of each monitoring point position; inputting real-time monitoring data into the etching analysis model to obtain a real-time etching coefficient of each monitoring point; judging whether correction is needed or not according to the real-time corrosion coefficient, and if yes, determining a plurality of local defect areas and generating a correction instruction; a correction instruction is issued, a feedback time node is set, a correction data packet of each local defect area is collected according to the feedback time node, a correction evaluation value is generated, whether the local defect area is corrected again or not is judged according to the correction evaluation value, and real-time monitoring and accurate correction of the etching process are effectively achieved. The problems that in a traditional etching process, defects are known after being perceived due to lack of real-time monitoring, and resources are wasted due to global reworking are solved.

The invention relates to the technical field of semiconductor detection, and discloses a method and a system for detecting chips on the surface of a semiconductor wafer. The method comprises the following steps: acquiring a high-resolution image of the surface of a wafer, and separating a defect candidate region set from a reference background region through noise filtering and contrast equalization processing; extracting defect areas to be identified one by one, and accessing the defect knowledge graph to obtain potential defect types; performing multi-feature fusion on the potential defect type and the reference background region, generating a defect semantic feature vector through a context sensing encoder, and analyzing the vector to judge the actual defect type; and processing all the candidate areas and then outputting a defect detection report. According to the method, the distinction degree of defects and backgrounds is enhanced, the defect judgment range is narrowed, similar defects are accurately recognized, missing detection and false detection are reduced, the detection efficiency and accuracy are improved, and reliable technical support is provided for wafer production quality control.

The invention relates to the technical field of integrated circuit defect detection, and discloses an integrated circuit defect detection method and system using an optical means, and the method comprises the following steps: controlling the emission of incident light, and controlling the polarization state of the incident light, enabling the incident light to irradiate a detection area of the wafer with the integrated circuit in a preset polarization direction; returning light rays reflected or scattered from the detection area are collected, polarization state parameters of the returning light rays are calculated, and the polarization state parameters comprise the polarization degree and the polarization angle; and comparing the polarization state parameter with a reference polarization state parameter of a preset defect-free area so as to judge whether a defect exists on the wafer with the integrated circuit or not. According to the method, high-sensitivity and high-precision defect detection and classification are realized through polarization state analysis, and the depth of defect analysis is enhanced while the detection sensitivity and reliability are remarkably improved.

The invention relates to an AOI defect detection method and system based on image processing, in particular to the field of AOI defect detection, and can effectively overcome interference of complex texture backgrounds and accurately recognize tiny defects on a circuit board. A defect-free reference image is generated as a comparison reference, a defect area signal is enhanced in combination with a space attention mechanism, defect features of different sizes are captured by utilizing multi-scale feature fusion, and model adaptability and generalization ability are improved by means of transfer learning and meta-learning. And finally, the false alarm rate and the omission ratio are remarkably reduced while the detection precision is ensured.

The invention discloses a cooperative detection method and system for an intelligent industrial visual detection robot, and relates to the technical field of industrial visual detection. According to the method, detection items are divided into basic items, recheck items and recheck items, so that a multi-level item architecture of'basic guarantee + suspected verification + pressure balance 'is formed; judging suspected defect generation according to a preorder link basic result in a reinspection item, preferentially transmitting a whole item and secondarily preferentially transmitting a defect area, and triggering manual reinspection if the defect cannot be transmitted; reinspection items depend on a detection item library, are sequenced according to a preset detection link, quantify the detection pressure in combination with the number of items in a to-be-inspected link, and are dynamically allocated to a target link; in the multi-level project system, the basic project ensures that the core item is not missing, the re-inspection project focuses on the suspected risk point, and the re-inspection project supplements the cross-link detection blind area, so that the full-life-cycle detection requirement of the workpiece can be covered by cooperation of the basic project, the re-inspection project and the cross-link detection blind area

The invention belongs to the technical field of measuring equipment, and discloses a system and a method for detecting geometric dimensions and surface defects of tubes and bars, and the system comprises a laser diameter measuring instrument, a CCD (Charge Coupled Device) linear array camera and other core components. During detection, the laser diameter measuring instrument collects the circle center coordinate and the orthogonal diameter of the pipe bar, and the mean value of the double diameters is taken as the section diameter; introducing a correction parameter M based on the elliptical cross section model to calculate the real ovality; and the straightness of different positions of the pipe bar is calculated by combining an optimized three-point method. Meanwhile, a CCD camera is used for collecting circumferential images, defect areas are positioned through multi-step processing, features are extracted, and defects are classified through a cascade model. The system realizes synchronous online detection of geometric dimensions and surface defects of the pipes and the bars, breaks through the problems of single function, poor interference resistance, low efficiency and the like, and meets the strict standard of high-end manufacturing industry on the quality of the pipes and the bars.

The invention provides an electrostatic chuck internal defect detection method and device, a terminal and a medium, the electrostatic chuck comprises a ceramic layer and a metal layer, the method comprises the following steps: carrying out point-by-point contact scanning on the surface of the ceramic layer through an eddy current probe, and collecting an impedance change value corresponding to each scanning point to obtain impedance change data; inputting impedance change data into the impedance thickness model, and calculating the ceramic layer thickness of each scanning point to obtain ceramic layer thickness data; and processing the thickness data of the ceramic layer, and determining an internal defect area of the electrostatic chuck. According to the method, eddy current is induced in the conductive material by utilizing the alternating magnetic field, efficient and contact type defect detection is realized by analyzing impedance change, online nondestructive detection of the internal defect and the film thickness of the electrostatic chuck is realized, and the bump defect is accurately identified.

The invention relates to the technical field of mold detection, and discloses a special working state inner wall detection device for a neutral borosilicate molded bottle mold, which comprises a workbench, an opening and closing mechanism is arranged on the middle side of the top of the workbench, a clamping mechanism is arranged on the top of the workbench, and a six-degree-of-freedom mechanical arm is mounted on the rear side of the top of the workbench. A ceramic probe is arranged on the outer side of the six-degree-of-freedom mechanical arm, and a base fixing seat is fixedly connected to the outer side of the ceramic probe. A real-time image differential analysis module is arranged, a blowing and powder spraying mechanism is used for carrying out pneumatic excitation on a suspected defect area, and a multispectral endoscope module is controlled to respectively collect optical images before and after excitation; by calculating the normalized difference measure of the two images and comparing the normalized difference measure with the preset physical displacement threshold value, the non-solid-phase attachments displaced due to pneumatic excitation and the solid-phase defects with fixed positions can be distinguished, and the technical problem that two abnormal areas with different properties are difficult to effectively classify in the prior art is solved.

The invention relates to a metal weld defect nondestructive identification method, device and equipment and a medium. The method comprises the following steps: acquiring original detection data of a to-be-detected metal welding seam; a welding seam area is extracted based on the original detection data, and welding seam area data are obtained; the original detection data comprises at least one of ultrasonic waveform data, ray image data and optical image data; inputting the weld joint area data into a pre-trained target detection model to obtain a candidate defect area; classifying defects in the candidate defect area to obtain defect instance information; the defects comprise at least one of cracks, air holes, slag inclusion, incomplete fusion and incomplete penetration; and calculating the physical size of the defect area based on the defect instance information to obtain defect detailed information. By adopting the method, the defect characteristics can be accurately quantified, and each defect area and various defects can be accurately divided.

The invention discloses a defect detection method and system for a silicon wafer based on visual inspection, and relates to the technical field of visual inspection, the surface image of the silicon wafer is deeply excavated based on a multi-scale attention mechanism, and the primary defect content of the silicon wafer is subjected to multi-level fusion to output a plurality of primary defect areas; and each primary defect region and the corresponding associated region determine a final defect region in semantic dimension analysis, so that the accuracy of the final defect region is further improved. Performing multi-stage analysis on the plurality of silicon wafer defect characteristics along the gray gradient and the morphological parameters to determine the defect grade of each silicon wafer defect characteristic; according to the technical scheme, the plurality of defect combinations are determined according to the feature form of each silicon wafer defect feature and the corresponding defect level, the corresponding visual report is determined based on the identification of each defect combination, and the defect regulation and control instruction of the silicon wafer is determined along the multi-level iteration of the plurality of visual reports, so that the accuracy of the defect regulation and control instruction of the silicon wafer is improved.

The invention discloses a defect detection method, device and equipment based on a multi-field light source and a binocular camera and a storage medium, and relates to the technical field of image recognition, and the defect detection method based on the multi-field light source and the binocular camera comprises the following steps: collecting initial image data of multiple groups of binocular cameras for the same defect area under light sources of a bright field, a dark field and a side field, three-dimensional images under three light sources are generated through stereo correction and matching, and then defect detection is carried out to obtain a bright field defect detection result, a dark field defect detection result and a side field defect detection result; and when at least two of the detection results are inconsistent, fusing the three three-dimensional images, and performing defect detection on the fused image to obtain a target defect detection result. Through the closed-loop process of multi-light three-dimensional parallelism and conflict fusion re-detection, the detection accuracy and the recognition rate of the surface defects of the plates and the roller products are improved.

The invention discloses a micro-nano visual lithography defect self-adaptive repairing method based on multi-modal image fusion, which comprises the following steps: acquiring a multi-modal image of a wafer surface, inputting the multi-modal image into a cascade-feedback type double-branch defect analysis network, fusing feature maps of two extraction networks by adopting a decision-making layer self-adaptive fusion mechanism based on confidence coefficient weighting, and obtaining a micro-nano visual lithography defect self-adaptive repairing result. Generating a fusion defect probability graph; performing defect detection and classification based on the fused defect probability graph, and identifying the type, position and size parameters of the photoetching defect so as to adaptively determine repair parameters; repairing the defect area according to the repairing parameters; and after repairing is completed, the multi-modal image of the defect area is collected again, the similarity of the images before and after repairing is calculated, when the similarity is smaller than a preset threshold value, repairing parameters are determined again till the similarity is larger than or equal to the preset threshold value, and a final repairing image is output. The defect detection precision can be improved, and the repair effect is improved while the repair efficiency is improved.

The invention provides a method for reducing OSF of large-size Czochralski monocrystalline silicon, and relates to the technical field of large-size Czochralski monocrystalline silicon. In the crystal pulling process, the rotating speed of a crucible and the reduction amplitude of heating power are reduced in the later stage of shouldering, so that a set vacancy type point defect area is formed in advance, and the OSF of the large-size Czochralski monocrystalline silicon is reduced; increasing the rotating speed of the crucible and increasing the reduction amplitude of heating power in the equal-diameter earlier stage; in the later stage of shouldering, dynamic switching from'low crucible rotation + vacancy type 'to'high crucible rotation + low power' in the earlier stage of equal diameter is carried out, so that vacancy type point defects are driven to move towards a V / I boundary (namely the area where an OSF ring is located) or even from the gap type side, and a clean area without an OSF nucleus is formed in a crystal.

The invention relates to a circuit board defect detection method and device, computer equipment and a storage medium. The method comprises the following steps: respectively carrying out positioning and defect identification on a target circuit board to obtain a structure type to which each positioning area belongs and a defect type to which each defect area belongs; for each structure type, constructing a hierarchical spatial index corresponding to the structure type according to the spatial coordinates of all the positioning areas under the structure type; according to association rules of defect types and structure types, determining at least one target structure type associated with each defect region; searching in a hierarchical spatial index corresponding to the at least one target structure type according to the position information of the defect area to obtain an adjacent positioning area meeting a preset distance condition with the defect area; and according to the distance between the defect area and the adjacent positioning area, determining quantitative information of the distance between the defect area and the adjacent normal element. By adopting the method, the defect distance detection efficiency in multiple positioning scenes can be improved.

The invention discloses a basin-type insulator superficial air gap defect detection method, system and device and a medium, and belongs to the technical field of defect detection.The method comprises the steps that a basin-type insulator sample is processed, the processed basin-type insulator sample is detected and judged, and feature data are obtained; judging the characteristic data according to the surface temperature difference, and obtaining a defect area and a non-defect area of the basin-type insulator sample; evaluating a detection signal emitted during detection of the thermal radiation threshold pair of the defect area and the non-defect area to obtain an evaluation result; and summarizing an evaluation result, and constructing a detection standard. The problems that in the prior art, sensitivity is low, environmental influence is likely to happen, and destructiveness exists are solved.

The invention relates to the technical field of industrial quality inspection, provides a wafer defect analysis method and electronic equipment, and is used for improving the wafer defect detection efficiency and precision. For a wafer whose appearance defect detection yield is lower than a preset yield threshold, mapping graphs corresponding to detection results of each core particle on the wafer are used as input of a defect segmentation model, independent defect areas of different defect types are identified, blob analysis is carried out on each defect area by using a computer vision technology, defect geometric information is obtained, and the defect geometric information is used as a defect segmentation model. According to the method, the defect geometric information of the wafer is obtained, whether the wafer has process abnormity or not is judged according to the comparison result of the defect geometric information and the defect card control parameters corresponding to the defect types, AI reasoning based on deep learning and traditional CV card control are combined, generalization of AI and accuracy of CV are fully utilized, and the defect detection precision and efficiency are improved.

The invention relates to the technical field of epitaxial wafer defect detection, in particular to a VCSEL epitaxial wafer surface defect detection method based on optical analysis, and the method comprises the steps: obtaining a substrate image, and obtaining all epitaxial images and temperature data in real time; suspected defect areas in all the images are extracted; obtaining a growth influence sequence of each suspected defect area in the last epitaxial image according to the overlapping degree and density characteristics of each epitaxial image and the suspected defect area in the substrate image, and calculating the temperature of each suspected defect area in the last epitaxial image according to the change trend of the obtained growth influence sequence and the similarity degree of the change trend of the growth influence sequence and the temperature data. And according to the average gray values of the suspected defect areas and the average gray values corresponding to the suspected defect areas, obtaining a pit particle significant value of each suspected defect area in the last epitaxial image, and further judging whether each suspected defect area is a pit particle defect area or not. According to the method, the accuracy of surface defect detection of the epitaxial wafer is improved by analyzing the characteristics of the pit defects during equipment interference and temperature change.

The application provides a composite material defect detection system and method. It relates to the field of nondestructive testing technology. It is used to solve the problem of inaccurate detection of small defects under low power excitation. It comprises: a multi-excitation signal generation module that provides different excitation modes, each excitation mode selectively enhances the response of a specific type of defect in the composite material under test; output excitation signals matching target instructions; an ultrasonic excitation module that receives excitation signals and converts them into mechanical vibrations; the mechanical vibrations are transmitted to the composite material under test in the form of symmetrical surface contact to excite the internal defect area of the composite material under test to form a temperature difference relative to the non-defect area; an infrared thermal image acquisition module that acquires thermal image data of the composite material under test through a thermal imaging technology matching the excitation signal; a synchronous control and signal processing module that receives thermal image data and obtains defect positions based on the thermal image data.

The invention discloses a defect detection method and device for a cable accessory based on vector detection, and relates to the technical field of defect detection methods, and the complex reflection coefficient of the cable accessory is determined based on the recognition of each feature data combination. And determining a plurality of defect characteristics of the cable accessory according to the complex reflection coefficient, the performance parameters of the cable accessory and the corresponding time domain signals, thereby improving the accuracy of the plurality of defect characteristics of the cable accessory. Therefore, the corresponding area image is determined according to the tracing of the defect area, and the defect type of the defect area is determined according to the area image, the corresponding defect feature and the previous defect event of the cable accessory; the defect surface morphology is determined according to the area position of the defect area, the corresponding defect type and the surface morphology of the cable accessory, and the defect distribution diagram of the cable accessory is determined according to the defect surface morphology, the defect type of the corresponding defect area and the plurality of defect characteristics, so that the accuracy of the defect distribution diagram of the cable accessory is improved.

The invention relates to the technical field of visual inspection, in particular to a multi-level defect intelligent evaluation method and system for a resistance spot welding electrode cap, and the method comprises the steps: obtaining an electrode cap image collected by an industrial camera, and carrying out the preprocessing of the electrode cap image; inputting the image into a preset target detection model, detecting whether an electrode cap exists in the image, and if not, directly terminating the process; if yes, inputting the electrode cap image to a classification stage; inputting the image into a YOLOv8 model, identifying whether obvious structural defects exist in the image by the model, if so, marking as NG, and if not, entering a defect analysis stage; in the defect analysis stage, segmentation operation is performed on the electrode cap image, and image masks of an end face area and a defect area of the electrode cap are extracted respectively; and executing multi-stage geometric consistency verification and defect area evaluation to judge the end face quality of the electrode cap. According to the invention, intelligent evaluation of the surface defects of the electrode cap can be realized under various working conditions.

The invention provides a defect image clustering method, a defect detection system and a medium, and the method comprises the steps: obtaining a defect image clustering model through two-stage training, and based on the clustering model, according to one or more to-be-detected defect region images of a to-be-detected sample and the surface feature data of each to-be-detected defect region image, obtaining a defect image clustering model; performing clustering analysis operation on each to-be-detected defect area image, and predicting a clustering result of each to-be-detected defect area image; therefore, the defect type of each to-be-detected defect area image can be effectively recognized, the method has a remarkable effect on recognition of complex defects, the clustering precision is high, defect problem qualification and process abnormality root positioning are facilitated, and continuous improvement of a semiconductor or generic semiconductor manufacturing process is guided; and each clustering result can be used for training a subsequent defect image classification model, so that the time consumption of data annotation can be effectively reduced, and the labor cost is saved.

The present disclosure provides a system and method for real-time visualization of a material during ultrasonic non-destructive testing. The system includes a graphical user interface (GUI) capable of showing a three-dimensional (3-D) image of a composite laminate constructed of a series of two-dimensional (2-D) cross sections. The GUI is capable of displaying the 3-D image as each additional 2-D cross section is scanned by an ultrasonic testing apparatus in real time or near real time, including probable defect regions that contain a flaw such as a hole, crack, wrinkle, or foreign object within the composite. Furthermore, in one embodiment, the system includes an artificial intelligence capable of highlighting defect areas within the 3-D image in real time or near real time and providing data regarding each defect area, such as the depth, size, and / or type of each defect.

The invention provides a control method for a fitting gap of an exterior curved surface of a repair welding position of a storage tank, which comprises the following steps: S1, extracting spatial three-dimensional coordinates of n points uniformly distributed around a defect area from three-dimensional scanning point cloud data of the exterior curved surface of the storage tank, and defining the geometric center of the defect area as a defect center; s2, based on the defect center, mapping the space three-dimensional coordinates of the n points extracted in the step S1 to a robot tool coordinate system through a coordinate conversion relation to obtain converted coordinates of n target points; s3, calculating a three-dimensional space error value between the converted coordinates of the target point and the coordinates of the corresponding point on the supporting tool; s4, iteratively optimizing the error value in a robot joint kinematics constraint range, solving an optimal support tool space coordinate, and taking the coordinate as a robot motion target point; and S5, joint coordinates corresponding to the moving target point of the robot are transmitted to a robot controller through the real-time industrial bus communication technology, and the mechanical arm is driven to drive the supporting tool to move to the target point.

The invention relates to a phased array welding defect detection method and system based on long dependency feature decoupling in the technical field of industrial defect detection. The detection method comprises the following steps: extracting a plurality of multi-scale features Fi from an ultrasonic phased array image; separating a high-order feature FH, a middle-order feature FM and a low-order feature FL from Fi; polymerizing the FH, the FM and the FL to obtain a polymerization characteristic FA; de-noising the FA to obtain a de-noised feature FD; performing two-step refinement on the FD to generate a fine candidate region P; and finally, carrying out ROI pooling on the FD and the P, and then obtaining the welding defects through classification and a regression head. According to the method, high-order, middle-order and low-order features of different scales are captured through a feature decoupling model, then the receptive field of multi-scale defects is expanded, the internal relation between a sudden change area and a defect area is fully captured to ensure that high-precision detection is still kept under the complex background, and finally, through coarse-fine two-step bounding box refinement, the detection precision is improved. And finally, the precision and accuracy of defect detection are relatively high.

The application is suitable for the sheet metal technical field, and particularly relates to a progressive multi-point forming process correction method for a special-shaped sheet metal part, which comprises the following steps: determining a plurality of low-risk forming combinations based on blank basic data, process parameter data and equipment state data, determining a suspicious defect area, determining a suspiciously associated influence area based on a multi-dimensional matching result, and obtaining a target defect area set, wherein the target defect area set is determined in the low-risk forming combination, the suspicious defect area is not only screened out, and the suspiciously associated influence area associated according to a cause is screened out, a specific target defect area set and the associated multi-dimensional matching result are obtained, a targeted forming process correction scheme can be generated, and the above method can solve the problems that the traditional process secondary correction is mostly "one-size-fits-all" adjustment, a differentiated scheme is not formulated in combination with the specific cause of the defect area, the correction efficiency is low, and new defects are easily caused.

The present application provides a kind of defect detection method, device, electronic equipment and computer readable storage medium, it is related to nondestructive testing technical field.Defect detection method includes: the original image is input into preset computer vision model, detects out defect area, first defect category and its corresponding first confidence degree;From the original image, the target image corresponding to the defect area is cut out;With first defect category, target image is input into preset multi-modal big model, detects out defect grade, defect text description, second defect category and its corresponding second confidence degree.At least to solve the problem that computer vision model precision is insufficient in related art, multi-modal big model inference speed is slow and the problem that the consumption of large amount of computing resources is big.Adapt to defect detection scene.

The present application relates to the technical field of casting defect detection, and particularly relates to a die casting defect detection method, system and device for aluminum alloy die castings. According to the change degree of thickness data of pixel points in a suspected defect area in an X-ray image, the stable degree of gray scale change and the regular degree of edges, a registration compliance degree is obtained, and a non-registration artifact area in the suspected defect area is selected. According to the non-uniformity degree of gray scale and the irregularity degree of shape of the non-registration artifact area, a defect gray scale shape compliance degree is obtained. According to the thickness data of pixel points in the non-registration artifact area and the change degree thereof, an overlapping thickness compliance degree is obtained. According to the defect gray scale shape compliance degree and the overlapping thickness compliance degree, a final defect area in the non-registration artifact area is selected. The present application comprehensively considers morphological characteristics and thickness characteristics, removes interference caused by projection superposition of three-dimensional structures and registration error of CAD models, and improves the accuracy of die casting defect recognition.

The embodiment of the application provides a defect detection method, device and electronic equipment. In the embodiment, an AI algorithm is used for preliminary positioning of defects in a glove image, initial classification is performed on a suspected defect area, a suspected defect category is obtained, fine classification is performed on the suspected defect area, a target defect category is obtained, automatic detection of the production quality of the glove is realized through machine vision, manual naked-eye detection is replaced, detection efficiency is improved, and the situation of missed detection is avoided. Further, the AI algorithm and the traditional 2D algorithm (i.e., the fine classification process described above) are combined to realize defect detection of the glove, the advantages of the AI algorithm and the traditional 2D algorithm are fully utilized, and the defect detection efficiency and accuracy of the glove are improved.