3484 results about "Image extraction" patented technology

The invention provides an industrial part defect detection method, which comprises the following steps: acquiring an input industrial part burr defect image, extracting the shape, size and distribution position characteristics of burrs in the image to obtain a burr characteristic pattern, segmenting a burr defect region according to the edge roughness and color difference in the burr characteristic pattern, and generating a binary burr defect mask; performing morphological operation on the binarized burr defect mask, eliminating isolated noisy points through expansion and corrosion, connecting adjacent burr areas, segmenting the processed burr mask, and extracting independent burr defect areas according to the three-dimensional contour and surface texture features of burrs; performing image enhancement processing on the preliminary verification code character matrix, adjusting the color contrast of characters to highlight the thickness of character strokes, and generating a verification code image; and carrying out compression and format conversion on the generated verification code image to obtain a final industrial part burr defect verification code which is used for defect detection of workpiece parts.

Disclosed in the embodiments of the present application are a defect detection method and apparatus, an electronic device, a storage medium and a program product. The method comprises: acquiring an image under test of a target workpiece and a template image of the target workpiece, and comparing the image under test with the template image so as to obtain a differential image; inputting the image under test and the differential image into a defect detection model, and executing the following processing: on the basis of the image under test and the differential image, extracting a target image feature and, on the basis of the target image feature, performing defect detection on the image under test to obtain defect detection box information of the image under test; positioning a defect area in the differential image and, according to the defect area, determining a first detection result of the target workpiece; and, according to the defect detection box information and the first detection result, determining a second detection result of the target workpiece.

The invention relates to the technical field of agricultural planting management, and discloses an intelligent agricultural planting method and system. The method comprises the following steps: analyzing nutritional requirements based on environment sensing and plant image data, and generating nutrition allocation data; carrying out growth prediction through seedling image features and formulating a cultivation standard; spectral parameters are extracted according to environment condition analysis and canopy images, and an environment regulation and control scheme is formed; combining growth state evaluation and pest and disease damage characteristics to calculate health indexes; a management strategy is optimized through growth parameter time sequence analysis; and determining the harvesting opportunity and grade evaluation according to the plant maturity and quality characteristics. According to the application, environment monitoring, growth diagnosis, quality evaluation and market analysis are organically combined, so that more accurate and intelligent agricultural planting decision support is provided.

The invention provides an industrial production part detection method based on machine vision, and the method comprises the steps: collecting multi-dimensional image data through a multispectral industrial camera when a part passes through a detection region, and carrying out the preprocessing of the multi-dimensional image data; constructing a three-dimensional feature space according to the structured light projection, and mapping the preprocessed multispectral image data into the three-dimensional feature space to carry out space registration operation to obtain a to-be-detected image; extracting composite parameters in the to-be-detected image; performing coarse screening identification on the parts through the geometric parameters and the texture parameters, and removing the parts with appearance defects; and carrying out microcosmic fine judgment identification on the roughly screened parts through material characteristic parameters, and rejecting the parts with quality defects. According to the method, the three-dimensional feature space is constructed through fusion of multispectral imaging and structured light projection, and composite analysis of geometry, texture and material characteristic parameters is combined, so that the problem of single detection dimension of a traditional method is solved, and the recognition accuracy and efficiency of complex defects are improved.

The invention relates to the technical field of industrial component detection, in particular to a transformer iron core detection method based on computer vision, which comprises the following steps of: acquiring an iron core image, extracting key pixel characteristics, screening a directional scattering abnormal region to generate an interference map, extracting a consistent gradient region correction image to generate a reconstruction map, and positioning a symmetric disturbance generation structure map by integral gray difference. And analyzing an overlapping relation by a superposition structure graph to generate an abnormal component graph, and evaluating a risk level by matching a reference index to generate an early warning graph layer. Interference reflection and structural features can be distinguished through linkage analysis of the pixel direction vector and the brightness change frequency, correction of a distorted area in an image is realized based on a gray statistical stable value, and the distortion of the image is corrected by constructing a symmetric point map and analyzing the change trend of a gradient difference value sequence. And the structural overlapping relation is quantitatively judged by combining a component mapping profile diagram, so that the relevance between an abnormal region and a key component is clearly expressed, and the grading evaluation capability of various fault risks in the iron core is improved.

The invention relates to an underwater environment three-dimensional reconstruction method. The method comprises the following steps: projecting a multi-band structured light pattern in an underwater environment, and capturing an image by using a multispectral camera; fusing images of different wavebands through a spectrum matching algorithm, and extracting depth information to generate three-dimensional reconstruction basic data; a depth error caused by underwater scattering and absorption is corrected by using a depth compensation technology; generating an environment characteristic model by using real-time monitoring environment parameters including illumination, turbidity and temperature of an underwater sensor; adaptively adjusting image acquisition and processing parameters including exposure, contrast and color balance according to the environment characteristic model; detecting a distorted area caused by environment change in the image through an intelligent correction algorithm, and executing local correction and overall optimization; generating a multi-scale image pyramid, and decomposing the structure information of the three-dimensional image layer by layer from coarse to fine; and through an adaptive detail enhancement technology, carrying out refinement processing on the key area to generate an underwater three-dimensional image.

A method for shoreline segmentation in complex environments based on the perspective of an unmanned surface vessel is provided. A visible light image, a thermal infrared image and a raw radar echo image of a shoreline are obtained. The visible light image and the thermal infrared image are subjected to fusion and feasible region segmentation to obtain an all-weather two-dimensional image information of the shoreline, and an echo image including tiny features is obtained based on the raw radar echo image. An extraction region is constrained and shoreline features are enhanced based on the all-weather two-dimensional image information and the echo image to obtain a multi-feature point cloud dataset for shoreline segmentation.

The invention discloses a grabbing control system for robot visual guidance, and belongs to the technical field of grabbing control systems.The grabbing control system comprises a visual perception module used for collecting workpiece images, extracting workpiece feature information and calculating accurate coordinates of workpieces in space; the robot main body module is used for receiving a system instruction to drive a carrier to move to a target position; the grabbing execution module is used for being in contact with the workpiece, grabbing the workpiece stably and transferring the workpiece to a designated position to be placed without damage; the system integration module is used for guaranteeing the safety, operability and stability of the feeding and discharging process; according to the system, workpiece information can be accurately collected, the posture of the grabbing execution end is analyzed based on the workpiece position, the grabbing posture is corrected in real time according to the grabbing dynamic state, and the workpiece grabbing precision and stability are improved.

The invention relates to the technical field of defect detection, in particular to a suturing scalpel packaging quality detection method based on optic nerves, which comprises the following steps: collecting suturing scalpel packaging images to perform angular point detection and gradient screening, obtaining alignment parameters under a unified coordinate system, calculating an optical flow displacement initial value and a residual error, and calculating an optical flow displacement initial value; an ROI sub-image is cut to extract a cutting edge contour; an orthogonal projection length is calculated to generate a cutter form mark; texture and shape features are extracted and input into a support vector machine for defect identification; a random forest regression model is called to calculate compensation parameters; according to the method, coordinate mapping is established through angular point detection and gradient screening, displacement is corrected through combination of optical flow residual and depth tracking, a cutting edge contour is extracted through ROI cutting, shape deviation is quantized through orthogonal projection, a classification basis is constructed through texture fusion, defects are identified through a support vector machine, parameters are compensated through random forest regression, and performance is optimized through closed-loop feedback.

The invention relates to the technical field of intelligent driving, and discloses an obstacle avoidance analysis system for intelligent driving. The system comprises a data acquisition module, a road feature extraction module, a lane type judgment module, a virtual marking generation module, an obstacle detection and trajectory prediction module, a dynamic obstacle avoidance decision module and a system verification and optimization module. The method comprises the following steps: acquiring data through a laser radar, a camera and the like; fusing point cloud and an image to extract the width and curvature of a road; judging the type of a lane according to the width; generating a virtual marking line on a marking-free road, fitting by using a B-spline curve when the curvature is large, fusing the point cloud and the image to detect an obstacle, and predicting a track by using Kalman filtering or a social force model. In combination with virtual marking and risk assessment, a safe trajectory is generated through an OccupanyGrid map, an A * algorithm and MPC, and a simulation and real road test optimization system is adopted, so that the problem of marking-free road trajectory planning deviation is solved, and the obstacle avoidance precision and the road condition adaptability are improved.

The invention relates to the technical field of medical image processing, in particular to a multimodal-based digestive tract tumor lesion image segmentation method and segmentation system. The method comprises the following steps: acquiring an alimentary canal tumor lesion image, and extracting an alimentary canal tumor ultrasonic image; evaluating the tumor invasion depth based on the digestive tract tumor ultrasonic image; performing focus three-dimensional visual modeling according to the tumor invasion depth to obtain a digestive tract tumor focus model; extracting a tumor tissue pathological image according to the digestive tract tumor lesion image; performing tumor region segmentation based on the tumor tissue pathological image to obtain digestive tract tumor region data; performing tissue arrangement anomaly detection based on the digestive tract tumor region data to obtain tissue arrangement anomaly data; and calculating a tissue arrangement disorder index according to the tissue arrangement abnormal data and the digestive tract tumor area data. According to the invention, the tumor identification accuracy and the malignant region segmentation precision are improved based on the medical image processing technology.

The invention discloses an icing detection method based on multi-source data feature interaction, and belongs to the technical field of image processing, and the method comprises the steps: inputting an original icing image into a dynamic routing image enhancement auto-encoder, and generating a high-quality enhanced image; extracting multi-level features of the image, wherein the multi-level features comprise local icing features, icing global features and meteorological time sequence features; after uniform scale mapping and feature precoding are carried out on the icing local features, the icing global features and the meteorological time sequence features, interactive fusion is carried out through a bidirectional cross-modal attention mechanism and feature splicing operation to output icing fusion features; the icing fusion features are input into a multi-task prediction module, deep features are extracted through a residual fusion encoder, task mapping is completed, and corresponding icing types and icing thickness levels are output; according to the invention, through meteorological time sequence information and feature fusion, efficient icing detection is realized, different climate and topographic conditions can be adapted, and the operation safety and stability of the power transmission line are improved.

The invention discloses a foam concrete image processing method based on sub-pixel edge reconstruction, and particularly relates to the field of foam concrete image processing.The method comprises the steps that an image of foam concrete is obtained, and a boundary response feature set containing edge direction information, edge gradient change information and local intensity comparison information is extracted; performing edge structure classification on the image region based on boundary response feature set combined threshold judgment; and aiming at the image region which is judged to be the local direction convergence mutation region, identifying a cross mutation point set by fitting a direction tensor convergence trend, and executing directionally-guided corrosion and expansion image processing. By constructing a structure judgment variable based on image boundary response characteristics and guiding a corrosion expansion path and a vein backtracking path to execute sub-pixel-level aperture boundary separation, image structure processing and contour reconstruction of a porous adhesion area are realized.

The invention discloses a TIG (Tungsten Inert Gas) welding penetration depth self-adaptive control system for a coiled pipe, belongs to the technical field of welding automatic control, and aims to solve the problems of inconsistent penetration depth control and real-time early warning of abnormal processing in TIG welding of the coiled pipe. The method comprises the steps that welding parameters are initialized based on parameters such as the material and the pipe diameter of the coiled pipe, and the target fusion depth is determined; identifying a straight line segment and a curve segment through the panoramic image, marking a target welding point and generating a welding path; determining a local processing space according to welding point position division types and differentiation, and verifying and updating; positioning precursor, current and subsequent points during updating, collecting images to extract multi-modal features, and adaptively updating the target fusion depth based on the geometric change of the subsequent points and the quality features of the precursor points; and during welding, processing quality and intervention abnormity early warning is carried out according to the real-time multi-mode characteristics, the processing parameters and the environment parameters.

The invention relates to an aerial photography target detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an aerial image acquired by an image sensor; inputting the aerial image into a pre-trained target detection model to obtain a target detection result; the target detection model comprises a backbone network, a neck network and a head network; wherein the backbone network is used for performing feature extraction on an aerial image to obtain image extraction features; the neck network is used for performing multi-scale fusion on the image extraction features to obtain a plurality of fusion features of different scales; the neck network comprises a bidirectional information transfer network, the bidirectional information transfer network comprises a separation and attention enhancement module, and the separation and attention enhancement module is used for generating fusion features corresponding to tiny targets; and the head network comprises a detection head corresponding to the tiny target and is used for obtaining a target detection result corresponding to the fusion feature based on the fusion feature. By adopting the method, the detection accuracy under the complex aerial image can be improved.

A highly reliable and high-precision navigation and positioning method and system for UAV under GPS-DENIED conditions includes: obtaining measurements of inertial sensor and image of binocular camera, extracting and tracking point features of the image, and obtaining altitude value; calculating position and attitude of camera and depth of landmark point based on the parallax and baseline of the binocular camera; fusing the measurement data of the inertial sensor and the binocular camera, and optimizing the data to obtain high-precision position and attitude data; obtaining the altitude value of the ranging radar and performing four-degree-of-freedom position and attitude graph optimization after adding the detected keyframes when repeated occurrence of the UAV at the same location is detected; encapsulating optimized position and attitude data to form a pseudo-GPS signal, inputting the pseudo-GPS signal to the UAV for positioning.

The disclosed embodiments disclose a video generation method, device, electronic device and storage medium, which obtain a starting frame image and an ending frame image of a target video to be generated, extract a first potential feature of the starting frame image and a second potential feature of the ending frame image, extract a first optical flow between the starting frame image and an intermediate frame image to be generated in the target video, and a second optical flow between the ending frame image and the intermediate frame image, distort the first potential feature based on the first optical flow, distort the second potential feature based on the second optical flow, fuse the distorted first potential feature and the distorted second potential feature to obtain a first distorted feature of the intermediate frame image, splice the first potential feature, the first distorted feature and the second potential feature with random noise respectively, and input them into a diffusion model for denoising to obtain a target video, thereby improving the quality of video generation.

The invention relates to the technical field of image processing, in particular to an image acquisition and analysis method and system, and provides the following scheme: obtaining a visible light and near-infrared multispectral image, generating a spectral difference image, and performing weighted fusion to obtain a first image; segmenting a target region based on the fused saliency map, and calculating a pixel reflectance ratio; solving a color mapping matrix according to the reflectance ratio, and carrying out color correction on the target region to obtain a standardized feature image; and extracting characteristic parameters such as spectrums, colors and textures, inputting the characteristic parameters to a multi-branch convolutional neural network, fusing the characteristic parameters through an attention mechanism, and outputting a state classification result and a quantitative index. The cross-spectral imaging difference can be adaptively compensated, and the fusion precision and the analysis stability are improved.

The invention discloses a medical ultrasonic image intelligent processing method and system, and relates to the technical field of medical image.According to the main scheme, normal feature coordinates of different organs and tissues are calculated by obtaining normal ultrasonic image data, to-be-processed image data and historical medical record information of a patient; extracting coordinates of a to-be-detected image and comparing the coordinates with normal coordinates for preliminary judgment; performing secondary judgment by combining ovality and circularity; setting a lesion gray threshold to judge whether a lesion exists or not; calculating the size of a lesion area when the lesion exists; according to the method and the system, the comprehensive blood flow evaluation index is calculated in combination with color Doppler blood flow imaging data, the disease evaluation value is calculated according to known medical record data and the like, the disease level is judged, the diagnosis report is automatically generated, the accuracy and the efficiency of medical ultrasonic diagnosis are improved, and powerful support is provided for clinical diagnosis.

The invention provides an AR-based bridge crack detection analysis method and system, and relates to the technical field of bridge detection analysis, and the technical scheme is characterized in that the method comprises the steps: monitoring the ambient light parameters of a bridge detection region; adjusting illumination output to stabilize imaging illumination conditions of the crack region; acquiring a crack image, and acquiring polarization information of the crack; stokes parameters are calculated, and a polarization degree image and a polarization angle image are generated; extracting a crack two-dimensional contour based on the polarization degree image and the polarization angle image; fusing the two-dimensional contour of the crack with the depth data to generate a three-dimensional model of the crack; and based on the crack three-dimensional model, crack geometric parameter quantitative analysis and multi-stage evolution state evaluation are carried out. The AR-based bridge crack detection and analysis method and system provided by the invention have the advantages of overcoming the influence of outdoor complex illumination conditions on image acquisition quality, improving the accuracy of crack recognition and three-dimensional modeling, and supporting reliable multi-stage evolution state evaluation.

The invention discloses a PDF (Portable Document Format) document content processing method and device, equipment, a storage medium and a program product, and relates to the technical field of document structured processing. Preprocessing the PDF document to obtain a to-be-processed data set corresponding to each page of the PDF document; determining the page type of each page of the PDF document based on all the to-be-processed data sets and the image of each page of the PDF document; and based on the to-be-processed data set corresponding to each directory page and the image of the directory page, extracting a hierarchical structure relationship of each title data in the directory page, and constructing a directory tree. And matching the title data of the directory page and the title data of the non-directory page based on the semantic similarity and the text similarity between the title data of the directory page and the title data of the non-directory page, and correspondingly filling the content data under each title node of the directory tree according to a matching result to obtain a structured representation result of the PDF document. According to the method and the device, the semantic reduction degree and the structural quality of the PDF document are improved.

The invention relates to the technical field of electronic component detection, in particular to an IC (integrated circuit) carrier plate detection method based on surface state image extraction, which comprises the following steps: acquiring a gray image, analyzing structural parameters, extracting gradient features, detecting boundary disturbance, integrating the image, calculating an abnormal score, identifying a defect position area, extracting features and outputting an identification result. According to the invention, by analyzing the structure parameters of the bonding pad in the gray level image, calculating the edge line segment, the center coordinate and the spacing, and constructing the two-dimensional coordinate system, the regional positioning reference is enabled to have geometric consistency, the coordinate mapping is combined with the gradient direction change frequency and the continuous aggregation point, the boundary disturbance identification precision is improved, and the image division is executed based on the disturbance region. According to the method, non-functional region mixing is effectively avoided, a clustering and probability model is introduced after region gray level statistics, a deviation scoring mechanism is constructed, gray level feature abnormity is accurately recognized, the discrimination capability of small-amplitude and low-contrast defects is improved, and the selectivity and target focusing performance of feature detection are enhanced.

The invention relates to the technical field of unmanned aerial vehicle detection and recognition, in particular to an unmanned aerial vehicle detection system and method based on vision, laser radar and sound waves, and the system comprises a sensor unit, a data processing fusion unit and a target recognition tracking unit. The data processing fusion unit performs multi-source data alignment and weighted fusion to extract texture, shape and color features of the image, point cloud generates a depth map, sound wave signals are mapped into a two-dimensional feature map, and weights are dynamically distributed based on sensor reliability to generate a unified feature map; the target identification and tracking unit identifies the type of the unmanned aerial vehicle by using the optimized deep learning model and realizes accurate prediction and updating of position and speed states in combination with Kalman filtering, and the decision response unit triggers sound-light alarm and wireless alarm for the non-cooperative unmanned aerial vehicle in real time and transmits target dynamic information to the ground station. And the target detection accuracy of the unmanned aerial vehicle in a complex environment is improved.

The invention discloses a carbon-coated foil coating uniformity detection method and system based on machine vision, and the method comprises the steps: S1, collecting blue light, green light, red light and near infrared spectrum images of the surface of a carbon-coated foil coating through a multi-angle camera, and generating a fused composite image through a multispectral image fusion algorithm; s2, performing adaptive histogram equalization and reflected light spot suppression processing on the fused composite image, and outputting an enhanced image; s3, coating edge features in the enhanced image are extracted, segmentation of a coating region is realized in combination with a region growing method, and a coating region mask is obtained; s4, extracting multi-scale texture features of the coating region by adopting a pre-trained ResNet-50 deep convolutional network, and constructing a coating surface feature vector; and S5, based on the extracted feature vectors and a standard template library, through a uniformity evaluation model, calculating a uniformity index of the coating, and detecting the uniformity of the coating. According to the invention, accurate detection of the coating uniformity can be realized.

The invention discloses a dynamic self-adaptive calibration method and device for hands and eyes of two arms of a robot. The method comprises the steps that calibration plates are fixed to the tail end of a left mechanical arm and the tail end of a right mechanical arm respectively, the mechanical arms are controlled through an automatic program to execute N times of translation and rotation movement in the view field of a camera, and calibration plate images are collected after each time of movement; based on the collected calibration plate image, the angular point position of the calibration plate is extracted, and the pose of the calibration plate in a camera coordinate system is calculated; and the pose of the calibration plate corresponding to each calibration plate image in the mechanical arm coordinate system is obtained, and the rotation matrix and the translation vector of the camera coordinate system and the mechanical arm coordinate system are solved. According to the technical scheme, the pose is corrected in real time through dynamic environment perception and vibration compensation, closed-loop re-projection error optimization and spiral / grid path planning are combined, high-precision robot double-arm hand-eye calibration is achieved, the environment interference calibration failure rate is reduced, and efficiency is improved.

The invention discloses a remote sensing image haze removal processing method and system, and relates to the technical field of image processing. The method comprises the steps of obtaining a to-be-processed remote sensing image; extracting wave band data of a plurality of wave bands in the remote sensing image to be processed, and determining a reference wave band and a plurality of target wave bands based on the wave band data; based on the reference wave band, determining an atmosphere illumination parameter, and calculating a transmittance distribution diagram of each target wave band; for each target wave band, carrying out haze removal processing on the target wave band according to the atmosphere illumination parameters and the transmittance distribution diagram to obtain an initial haze removal image of the target wave band; and performing fusion processing on the initial haze-removed images of the target wavebands to obtain a haze-removed image corresponding to the to-be-processed remote sensing image. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of haze removal processing of the remote sensing image is achieved.

The invention relates to the technical field of automatic control, in particular to a multi-parameter cooperative control method and device for a clamping system of a precision boring and milling machine. According to the method, an industrial camera is used for collecting and processing a workpiece image and extracting visual features, and the visual features are fused with process parameters of a workpiece and geometric distribution parameters of a workpiece key area obtained from a process database; generating a comprehensive state vector; based on the vector, outputting a target clamping force adjustment coefficient by a pre-trained MLP decision model, and calculating a final target clamping force in combination with a safe clamping force range; in the main clamping stage, vibration, temperature and pressure signals are synchronously collected, multi-modal disturbance characteristics are extracted, observation vectors are constructed, the observation vectors are input into a preset fuzzy rule base for reasoning, and compensation activation factors are obtained; and finally, a current correction instruction is dynamically generated according to the clamping force deviation and the compensation factor, and an electro-hydraulic proportional valve is driven to achieve accurate compensation. According to the invention, the stability and the machining reliability of the clamping system are obviously improved.

The invention relates to the technical field of hot galvanizing, and discloses an automobile hot galvanizing process parameter optimization method and system based on artificial intelligence, and the method comprises the steps: carrying out window division processing on initial cooling parameters, constructing a cooling rate matrix, and finely depicting heat exchange states of different cooling sections; the problem of insufficient cooling control precision under different cooling speed alternating conditions is solved, a microscopic image is combined to extract the grain main axis direction, calculate the mean value and range of included angles, generate a consistency index set and quantitatively describe the dispersion problem in the grain growth direction, the cooling speed and the consistency index are jointly matched, and a cooling speed structure offset matrix is constructed. The method comprises the following steps: identifying a space mutation region, accurately positioning abnormal coarse or abnormal arrangement positions of crystal grains, and finally screening target cooling parameters according to a cooling index value corresponding to an abnormal region to realize local adjustment of a cooling process, thereby reducing the abnormal growth rate of the crystal grains and improving the direction consistency of the crystal grains.

The invention discloses an intelligent inspection method for a special operation physical examination room, and relates to the field of path planning, and the method comprises the steps: obtaining examination room data and environment parameters in real time, and building a live-action navigation map based on the examination room data, the live-action navigation map being used for real-time linkage with the examination room data; acquiring an examination room image in real time through inspection equipment; image features of the examination room image are extracted, the inspection path is divided into n areas based on the image features, and n is a positive integer; executing a dynamic path planning strategy based on the live-action navigation map and the image features to generate an inspection path of the inspection equipment; performing fusion analysis on the environmental parameters and the image features to determine a congestion index on the inspection path; and determining a dangerous area in the n areas based on the congestion index, and visualizing the dangerous area. The inspection accuracy of the special operation physical examination room can be effectively improved, so that the risk hidden danger of the examination room is effectively reduced.

The invention provides a door and window glass defect feedback control method and device, electronic equipment and a storage medium, and relates to the technical field of door and window glass defect detection. The method comprises the steps of collecting a first image after a polarized light imaging detection device is adjusted to suppress reflected light on the surface of glass and enhance scattered light of bubbles in the glass; after the polarized light imaging detection device is adjusted to enhance reflected light on the glass surface, a second image is collected; calculating an adaptive weight group by analyzing local characteristics of the second image; weighting the first image according to the self-adaptive weight group, and subtracting the weighted first image from the second image to obtain a difference image; and extracting bubble defect information in the glass by analyzing the differential image. According to the method, interference caused by non-uniformity of glass surface reflection is overcome, the adaptability of image differential processing to surface reflection background suppression is improved, and therefore image features of internal bubble defects are extracted more effectively and more accurately.