36results about How to "Improve defect detection accuracy" patented technology

The invention provides a steel surface defect detection method and device, and belongs to the technical field of steel defect detection.The steel surface defect detection method comprises the steps that a defect detection network based on a YOLO architecture is constructed, and the defect detection network comprises a lightweight feature extraction network, a self-adaptive multi-scale feature fusion network and a head network; the lightweight feature extraction network comprises four layers of architectures, and each layer of architecture comprises a first convolutional layer and a space expansion feature module; the feature space expansion module comprises a second convolutional layer and an element multiplication operator module; the adaptive multi-scale feature fusion network comprises an adaptive fusion module and a feature space expansion module; training the constructed defect detection network based on the historical steel defect image, and performing channel pruning on the trained defect detection network by using LAMP (Loop-Mediated Isothermal Amplification); and acquiring a to-be-identified steel image, and inputting the to-be-identified steel image into the pruned defect detection network for defect detection. According to the method, the defect detection precision of the network can be improved while the network complexity is reduced.

The invention belongs to the technical field of machine vision defect detection, and particularly discloses a self-adaptive workpiece defect detection method based on machine vision, electronic equipment and a storage medium, and the method comprises the following steps: S1, shooting an original picture of a workpiece, and processing the original picture to obtain a cut picture; s2, acquiring an end face template picture in the shot picture, and acquiring an end face area of the workpiece; s3, constructing a defect detection algorithm for detecting surface defects of the workpiece; s4, constructing a self-adaptive algorithm selector, and detecting surface defects of the workpiece by adopting a proper defect detection algorithm; according to the method, the images acquired by the image acquisition equipment are subjected to operations such as preprocessing and adaptive algorithm selection, so that whether the surface of the workpiece has defects can be detected, a proper scratch detection scheme can be selected according to detection results of workpieces of different batches, the method can adapt to workpieces of different types and batches, detection of defects of different types is met, and the detection efficiency is improved. And the defect detection accuracy is improved.

The invention provides a neural network based on a mixed attention mechanism and category feature optimization and a defect detection method, and relates to the technical field of defect detection, the neural network comprises a feature extraction network, a Transform network, a cross attention network, a feature fusion network, a category feature optimization network and a full connection layer; the feature extraction network is used for feature map construction, and the Transform network is used for feature map dependency relationship construction; the cross attention network is used for feature map global pixel point association; the feature fusion network is used for feature fusion of the feature map; the category feature optimization network is used for feature information smoothing processing of the feature map, and the full connection layer is used for defect category prediction of the feature map. According to the invention, the neural network with an optimized structure is used for panel defect detection, so that the problem that missing detection and false detection are easy to occur when the existing neural network is used for panel defect detection can be solved.

The invention provides a battery positive and negative direction detection method and system, and relates to the technical field of new energy. An image acquisition module is utilized to obtain an image sample of a battery module, the battery module comprises a plurality of single batteries, and the image sample comprises mark point information of each single battery; the mark point information is used for representing positive electrode point position information and / or negative electrode point position information of the single battery. Determining a pixel difference value between adjacent single batteries according to the coordinates of the mark point information; and then determining positive and negative pole directions between adjacent single batteries according to the pixel difference values, and traversing each single battery to obtain positive and negative pole detection results. And finally, judging whether the positive and negative electrode detection result is consistent with the standard positive and negative electrode sequence of the battery module so as to obtain a positive and negative electrode deviation detection result. On the basis, the invention provides a lithium battery positive and negative electrode detection scheme, the lithium battery defect detection precision can be improved, and the labor cost can be reduced.

The invention relates to the technical field of image processing, in particular to a method and system for detecting surface defects of an insulating layer of a polyethylene insulated cable, and the method comprises the steps: obtaining a surface image of the insulating layer; the defect response index of each pixel in the surface image is calculated, and the defect response index is in positive correlation with the product of the gradient amplitude of each pixel in the corresponding local window and is in positive correlation with the absolute value of the difference value of the gray average values of all the pixels in the local window. According to the method, a defect response index is constructed by introducing a gradient direction angle variance, the defect response index and the defect response index are distinguished by utilizing the physical characteristics that the gradient direction of a highlight region is consistent and a defect region is disordered, and a defect significance enhancement factor is constructed according to the physical characteristics to dynamically adjust the Gaussian kernel scale. According to the method, large-kernel smooth interference is automatically adopted in a highlight area, small-kernel reserved details are adopted in a defect area, the limitation of a traditional fixed parameter algorithm is effectively overcome, and the defect detection precision under the complex reflective background is remarkably improved.

The invention relates to the technical field of image data processing, in particular to a hub surface defect detection method and system based on image processing, and the method comprises the steps: shooting the surface of a hub, obtaining an enhanced grayscale image, and carrying out the superpixel segmentation of the enhanced grayscale image, so as to obtain a connected domain; constructing a connected domain set of a target connected domain of an enhanced grayscale image shot over against the surface of the hub; respectively inputting the connected domains in the connected domain set into the trained SVM model, and outputting the defect probability that each connected domain belongs to each defect type; and performing weighted fusion on the defect probability of each connected domain belonging to the target defect type to obtain a comprehensive probability of the target connected domain belonging to the target defect type, and when the comprehensive probability is greater than a defect threshold, judging that the target connected domain has the defect of the target defect type. According to the method, the adaptive measurement distance is constructed, so that the superpixel segmentation process is more fit with the hub surface physical structure and the defect real boundary, and the defect detection accuracy is improved.

This application relates to the field of pipeline network detection technology, and discloses a visual detection method and system for pipeline network node defects based on a detection robot. The method includes: acquiring node images of a sewer network using a detection robot, and performing circle detection and sector segmentation on the node images to obtain multiple sector region blocks; extracting the block feature vector of each sector region block; calculating angular attenuation weights and radial attenuation weights, and constructing a node connection relationship matrix based on the angular attenuation weights and radial attenuation weights; combining the block feature vectors and the node connection relationship matrix to perform feature aggregation and illumination compensation to obtain a global feature vector; calculating angular deviation index, radial mutation rate index, and leakage index, and generating defect visual detection results, thereby realizing comprehensive diagnosis and spatial positioning of pipeline network node connection defects, and improving the defect detection accuracy of sewer detection robots in complex node environments.

The present invention relates to the technical field of image analysis, and discloses an automatic detection system and method for surface defects of an OLED display screen based on machine vision. The system comprises a display screen surface image data processing module, a display screen surface defect detection module, and a display screen surface defect information feedback module. An intelligent search algorithm is used to compare image number values ​​according to OLED display screen surface partition defect type parameters and standard OLED display screen surface feature partition image coordinate parameters, and the OLED display screen surface partition defect coordinate parameters are accurately searched out to achieve accurate positioning of the OLED display screen surface defect position. The OLED display screen surface partition defect type parameters and the OLED display screen surface partition defect coordinate parameters are matched according to image numbers and coordinate values, accurately mapped to the standard OLED display screen surface feature image coordinate combination parameters, and displayed through a display device for feedback, so as to achieve visual and intuitive feedback of the OLED display screen surface defect type and defect position.

The invention discloses a multi-mode high-voltage cable insulation sleeve defect detection device and a remote control method, and belongs to the field of high-altitude cable insulation sleeve defect detection.The multi-mode high-voltage cable insulation sleeve defect detection device comprises a shell, a plurality of crawling assemblies are evenly installed on the inner wall of the shell, and a detection mode switching assembly is installed in the shell; the crawling assembly comprises a first connecting rod, a second connecting rod rotationally connected with the two ends of the first connecting rod, a moving assembly and an imaging assembly, the moving assembly is fixedly connected with the end, away from the first connecting rod, of the second connecting rod, and the imaging assembly is installed on the first connecting rod; the output end of the detection mode switching assembly is electrically connected to the moving assembly. The problem of low cable defect detection accuracy and flexibility caused by limited detection range and single detection mode is solved, and the accuracy and flexibility of high-voltage cable defect detection are remarkably improved.

A method and device for defect detection. The method includes: (210): obtaining a defect eigenvector of an image to be detected; (220): calculating a similarity score of the image to be detected for each known defect type according to the defect eigenvector; and (230): performing defect classification on the image to be detected according to the similarity score. The similarity score between the defect eigenvector of the image to be detected and each known defect type is calculated, and then it is possible to distinguish known defects from unknown defects and accurately classify the known defects according to the similarity scores, so as to effectively detect the defects.

The present application discloses a defect detection method, system and device for a micro display device, which is used to improve the defect detection accuracy of the micro display. The present application method includes: obtaining a first initial image and a second initial image of the micro display; obtaining first initial coordinate parameters corresponding to a plurality of lamp beads according to the first initial image, and obtaining second initial coordinate parameters corresponding to a plurality of lamp beads according to the second initial image; obtaining first valid coordinate parameters and abnormal coordinate parameters in the first initial coordinate parameters according to the standard coordinate parameters; obtaining second valid coordinate parameters corresponding to the abnormal coordinate parameters according to the first valid coordinate parameters; obtaining first physical coordinate parameters of any lamp bead according to the first valid coordinate parameters and the second valid coordinate parameters; obtaining second physical coordinate parameters of any lamp bead according to the second initial coordinate parameters and the standard coordinate parameters; and calculating the coordinate offset of any lamp bead according to the first physical coordinate parameters and the second physical coordinate parameters.

The invention provides a casting defect detection method and device, a program product and electronic equipment, and relates to the technical field of casting detection. The method comprises the following steps: determining a three-dimensional model of a casting to be detected; performing voxelization processing on the three-dimensional model to obtain voxel information of the casting to be detected; and performing fusion detection processing on the voxel information and the image information of the to-be-detected casting through a defect detection model to obtain defect information of the to-be-detected casting. The voxel information in the space direction and the image information in the plane direction are subjected to fusion detection processing through the defect detection model, defect detection of the to-be-detected casting can be efficiently and automatically completed, and therefore the detection efficiency and the detection accuracy are improved.

The invention discloses a visual detection method for the welding quality of a lithium battery pole, and the method comprises the steps: S1, obtaining a lithium battery pole welding image and a pixel-level marking image corresponding to each welding image, and forming a sample set; step S2, carrying out preprocessing on the training sample set train; s3, building a visual detection model; s4, training the visual detection model, storing a training weight file of the visual detection model, and generating the visual detection model; s5, inputting a to-be-tested lithium battery pole welding image into the trained visual detection model to obtain a segmentation result image, and processing the segmentation result image to obtain a semantic segmentation region result image; and S6, performing post-processing on the semantic segmentation region result map, processing and segmenting internal mixing and undersize pixel filtering, and obtaining a final semantic segmentation type region result map. According to the method, the defects of low detection precision, insufficient generalization adaptive capacity, low detection speed and multiple required samples in the prior art are overcome.

The present invention provides a divertor target plate defect detection method, device, equipment, computer product and storage medium, which obtains target plate surface defect data by acquiring a target plate surface image to be tested and inputting the target plate surface image to be tested into a pre-trained target plate defect detection model. The present application is based on the YOLOv5 algorithm and improves its model framework structure to obtain a target plate defect detection model, introduces a ResNet residual network in the defect feature extraction stage, and realizes multi-scale feature fusion of defects through bidirectional feature pyramid network learning weights. The present invention can be run in a real-time detection environment, realizes the lightweight of the detection model, and solves the problems of large size and slow computing speed of the existing detection model; at the same time, it improves the defect detection accuracy, solves the problem of low accuracy of small target defect detection of the existing model and the problem of errors or misjudgments in complex environments.

The invention provides boxing and stacking equipment and a working method thereof.The boxing and stacking equipment comprises a rack and a box body defect detection mechanism, a box body stacking mechanism, an opening expanding and boxing mechanism and a mechanical arm which are arranged on the rack, the box body defect detection mechanism comprises a detection camera assembly, a sensor assembly, a conveying belt and a defect removing assembly, and the conveying belt is arranged on the rack; the conveying belt can drive boxes placed on the conveying belt to move in the conveying direction, the sensor assembly is arranged at the inlet end of the conveying belt, the sensor assembly, the detection camera assembly and the defect removing assembly are sequentially arranged in the conveying direction, the box stacking mechanism comprises a stacking plate and an adsorption head, and the opening and boxing mechanism comprises a push plate assembly and a supporting plate assembly. The pushing plate assembly and the supporting plate assembly are arranged on the two sides of the stacking plate respectively, the box sealing mechanism comprises a cover plate folding assembly, a linear sealing machine core, a corner edge sealing machine core and an adhesive tape supporting and pasting assembly, the cover plate folding assembly is arranged at one end of the linear sealing machine core, and the adhesive tape supporting and pasting assembly is arranged at one end of the corner edge sealing machine core.

The invention discloses a high-speed rail station building railway passing area structure health monitoring system and method and a medium, and the system comprises a concrete structure self-sensing monitoring subsystem which is used for collecting sensing data; the image acquisition and recognition subsystem is used for acquiring surface images of the concrete structure and the steel structure, inputting a surface defect recognition model and outputting a structured surface defect recognition result; the data acquisition and preprocessing unit subsystem is used for receiving the sensing data and the structured surface defect recognition result, and respectively performing preprocessing and feature extraction to obtain a sensing data feature vector and an image feature matrix; and the data fusion and analysis subsystem is used for receiving the sensing data feature vector and the image feature matrix, inputting the sensing data feature vector and the image feature matrix into a structure defect recognition model and outputting a structure defect recognition result. According to the invention, all-around, accurate and real-time monitoring of the concrete structure and the steel structure of the railway passing area of the high-speed rail station building from inside to outside is realized.

The invention relates to the technical field of light source devices, and discloses a composite light source device which comprises a supporting and fixing assembly and a light source assembly. The light source assembly is arranged in the containing cavity, the light source assembly is supported and fixed to the supporting and fixing assembly, the light source assembly comprises a direct light source assembly and a low light source assembly, the low light source assembly is obliquely arranged on one side of the direct light source assembly, and the direct light source assembly and the low light source assembly both face the same side of the supporting and fixing assembly. And the light of the direct light transmission source assembly and the light of the low light transmission source assembly are emitted from the same side of the supporting and fixing assembly. The light source assembly of the composite light source device comprises the direct light transmission source assembly and the low light transmission source assembly, and the low light transmission source assembly is obliquely arranged on one side of the direct light transmission source assembly, so that the direct light transmission source assembly and the low light transmission source assembly are arranged in the same device, the overall occupied space is reduced, the defect detection error is reduced, and the defect detection precision is improved.

The present application relates to the technical field of power transmission line detection, in particular to a power transmission line fastener defect detection method based on image processing, comprising: 1, collecting multiple power transmission line fastener images, and using the multiple power transmission line fastener images to construct a power transmission line fastener dataset; 2, labeling the power transmission line fastener dataset, and dividing the labeled power transmission line fastener dataset into a training set, a validation set and a test set according to a specified proportion; 3, building an improved target detection model; 4, training the improved target detection model using the training set, and verifying using the validation set; 5, testing the trained target detection model using the test set. The present application overcomes the problems of small target size of power transmission line fasteners, complex environment background, large contrast of aerial light, and diversified angles, and can improve the precision of power transmission line fastener defect detection, providing technical reference for maintenance personnel to carry out power transmission line fastener defect detection work.

The invention belongs to the technical field of electromagnetic nondestructive testing, and particularly discloses an eddy current modulation detection system and method for magnetic Barkhausen noise. Comprising a magnet exciting coil wound on the U-shaped magnet yoke; the ferromagnetic material is arranged towards the pole shoe direction of the U-shaped magnet yoke; the eddy current excitation coil and the eddy current detection coil are arranged between the U-shaped magnet yoke and the ferromagnetic material; the eddy current excitation coil and the eddy current detection coil are positioned between two pole shoes of the U-shaped magnet yoke and are arranged side by side; the distance between the eddy current excitation coil and the ferromagnetic material and the distance between the eddy current detection coil and the ferromagnetic material are fixed; the bipolar current source is electrically connected with the excitation coil; the signal generator is electrically connected with the eddy current excitation coil; and the integral and filter circuit module is electrically connected with the eddy current detection coil. According to the method, the eddy current signal which is high in precision and reflects magnetic Barkhausen noise information can be obtained, so that the detection precision is improved, and the method has the advantages of being higher in detection precision and easier to analyze.

The application discloses a kind of multi-channel optical imaging system and device of wafer defect detection, it is related to semiconductor detection field.The system includes the objective lens, DIC prism and independent bright field, dark field, fluorescence PL imaging channel arranged in sequence.Wherein, after dark field and PL light are collected by objective lens, single pass through DIC prism is split into vertical o light and e light, and is transmitted along the same light path.The core is that polaroid is arranged between the DIC prism of dark field or PL channel and camera, so that its optical axis is collinear with DIC prism, and the light entrance surface is perpendicular to the light path.Rotating polaroid can only allow o light or e light single beam to be transmitted to camera, effectively eliminates ghosting, solves the problem of over-checking of particle defects, and improves the imaging clarity and detection accuracy of subsurface defects.

The invention provides a target defect identification method and system based on an underwater inspection system. Collecting image information and position; the collected data are transmitted through the base station; the data processing center uses an image intelligent identification algorithm to pre-process the image, combines data of the historical image database and the target information database to identify defects, and outputs the severity of the defects and the positions of the target defects. According to the method, defects of bridge pier columns, pile foundations, ship bottoms, propellers and other underwater key parts are efficiently and accurately detected and recognized by integrating various sensors and intelligent algorithms.

The invention provides a tool defect detection model construction method and a tool defect detection method, and relates to the technical field of image processing, and the tool defect detection model construction method comprises the steps: obtaining a training data set; for each first cutter image, performing feature extraction on each first cutter image by using a pre-constructed first unsupervised network to obtain a first feature map corresponding to the first cutter image; adjusting the channel dimension of the first cutter image according to a first feature map corresponding to the first cutter image to obtain a second cutter image corresponding to the first cutter image; and training the first supervised network according to the second cutter images corresponding to the plurality of first cutter images to obtain a second supervised network, and taking the second supervised network as a cutter defect detection model. Compared with the prior art, the accuracy of tool defect detection can be enhanced.

This application relates to a method, apparatus, computer equipment, and medium for detecting defects in compressed hardware fittings. The method includes: performing image enhancement processing on an acquired original hardware fitting image to obtain an enhanced image; extracting the hardware fitting contour from the enhanced image to obtain a contour image; extracting features from the contour image using a region localization model; obtaining candidate region images based on the extracted features; performing deduplication processing on the candidate region images to obtain a target region image; performing size correction on the target region image to obtain a crimped area image; performing a first defect detection on the crimped area image using a defect detection network model to obtain a first candidate defect image; performing a second defect detection on the crimped area image to obtain a second candidate defect image; and fusing the first and second candidate defect images to obtain a defect detection result. This method can improve the accuracy of defect detection.

The control device includes an acquisition unit and a determination unit. The acquisition unit is capable of acquiring a first estimated pixel value corresponding to a post-processing pixel group of a first region and a second estimated pixel value corresponding to a post-processing pixel group of a second region on the basis of a first image estimation model, a second image estimation model, and a pre-processing captured image of a substrate to be inspected. The first image estimation model corresponds to a pixel group of a first region in the pre-processing captured image and the post-processing captured image. The second image estimation model corresponds to a pixel group of a second region in the pre-processing captured image and the post-processing captured image. The determination unit is capable of performing an abnormality determination on the substrate to be inspected on the basis of a result of comparison between the first captured image of the substrate to be inspected and the first estimated pixel value and a result of comparison between the second captured image and the second estimated pixel value.

The present invention relates to a non-planar lens defect detection method and system, and belongs to the field of lens detection technology. The method comprises: performing contour detection on a first image, and determining a contour-matched complement lens set from a lens library based on the contour detection result of the non-planar lens to be detected; performing refractive index simulation calculation based on the complement lens set and the non-planar lens to be detected, and determining a first target lens and a second target lens for complementing the non-planar lens to be detected; obtaining an equivalent lens image collected by using the complemented target lens as a lens lens; inputting the second image into a defect detection model to obtain the defect detection result of the complemented target lens; the defect detection result of the complemented target lens represents the defect detection result of the non-planar lens to be detected. The present application provides a defect detection method for non-planar lenses, which can be applied to non-planar lenses of various curvatures and has a high defect detection accuracy.

The application relates to the technical field of image processing, and particularly discloses a glass bottle defect recognition method and system, which is characterized in that the mouth, bottom and body of a glass bottle are photographed and imaged to obtain corresponding three views for preprocessing, so as to weaken and inhibit the noise of the collected three views and obtain a preprocessed image; the preprocessed image of a single channel is further fused, the pictures in three directions are subjected to feature extraction, and the pictures are fused into a three-channel feature map for defect detection according to different weights, so that the defect detection precision can be improved, and the detection task can be completed at a relatively fast speed; then, the calculation capacity of a convolutional neural network is utilized to collect and process image features of different degrees, and the features are subjected to convolution, pooling and feature fusion of different degrees, and then convolution up-sampling and the like, so that a target feature image is obtained, the image features can be fully extracted, and the defect recognition precision can be improved.

The present application relates to the field of industrial detection, and specifically discloses a general defect detection method for industrial manufacturing, comprising the following steps: S1, reference image construction and to-be-detected region calibration; S2, positive and negative sample storage and to-be-detected region extraction; S3, to-be-detected image acquisition; S4, similarity calculation and result output. The present application also discloses a general defect detection system for industrial manufacturing, comprising a reference image calibration module, a sample processing and storage module, an image registration alignment module, a similarity calculation and result output module. In actual use, the present application requires few samples, only 20-30 positive samples and 10-20 negative samples are needed for deployment, greatly reducing the cost of sample collection and labeling and solving the problem of scarce defect samples. In addition, the detection accuracy is high, the core registration algorithm has small error, the similarity calculation model improves the accuracy, and the adaptability is strong. When the product model is updated, the reference image and sample library can be replaced, meeting the flexible production demand.

The present application relates to the technical field of Mini-LED chip detection, and a Mini-LED repair method and device based on automatic optical detection, comprising: performing Gaussian filtering on an optical chip image to obtain a filtered chip image, training a neural network based on an original chip image set to obtain a defect area detection model, detecting the filtered chip image according to the defect area detection model to obtain a defect image area group, if the defect image area group is not an empty set, recording the product to be repaired as a repairable product, performing local contrast enhancement on the filtered chip image to obtain a target chip image, performing single chip recognition on the target chip image to obtain a single chip area set, identifying a chip area group to be repaired according to the single chip area set, and generating a repair opinion report based on the chip area group to be repaired. The present application can improve the accuracy of Mini-LED product defect detection and reduce the labor consumption of Mini-LED products.

This invention discloses a lightweight asphalt road defect detection method and system with partial multi-scale attention, belonging to the field of computer vision and intelligent transportation technology. This invention is applicable to the real-time detection and precise localization of defects such as cracks and potholes. It employs PMA modules, SCConv modules, and the inner-AIoU loss function to construct the required asphalt road detection model, achieving accurate detection of the road image to be detected. The model constructed in this invention, while maintaining its lightweight advantage, achieves significant improvements in speed, substantial increases in defect detection accuracy, and diversification of detected defect categories, fully meeting the needs of real-time detection. Furthermore, the detection model constructed in this invention also possesses good portability and scalability, making its integration with hardware devices more convenient.

The invention relates to the technical field of light source devices, and discloses a composite light source device which comprises a supporting and fixing assembly, a cover plate assembly and a light source assembly, the cover plate assembly is arranged on the outer side of the supporting and fixing assembly, and a containing cavity is defined by the supporting and fixing assembly and the cover plate assembly; the light source assembly is arranged in the containing cavity, the light source assembly is supported and fixed to the supporting and fixing assembly, the light source assembly comprises a direct light-transmitting source assembly and two low light-transmitting source assemblies, the two low light-transmitting source assemblies are obliquely arranged on the two sides of the direct light-transmitting source assembly respectively, and the direct light-transmitting source assembly and the low light-transmitting source assemblies are arranged towards the same side of the cover plate assembly. And the light of the direct light transmission source assembly and the light of the low light transmission source assembly are emitted from the same side of the cover plate assembly. According to the composite light source device, the direct light transmission source assembly and the low light transmission source assembly are arranged in the same device, so that the overall occupied space is reduced, the defect detection error is reduced, and the defect detection precision is improved.