27 results about "Image differencing" patented technology

The invention relates to the technical field of defect detection, and particularly discloses a high-precision defect detection system based on image difference and threshold processing, which comprises a registration image acquisition module, a fixed mask conversion module, an image difference detection module, a correction difference graph generation module and a defect set output module, the method comprises the following steps: firstly, completing affine registration by shape features, changing a fixed mask into a dynamic mask, and performing edge robustness in the mask to obtain a preprocessed image; local movement difference is carried out on the preprocessed image and the multiple reference images, fusion of a reference domain and a time domain is carried out to generate a difference response image, and candidate areas are extracted in combination with a dynamic mask; estimating and correcting a displacement field in the candidate range, synchronously mapping to obtain a correction difference graph and a correction mask graph, and determining a peripheral rejection area; according to the method, false alarm and missing detection are effectively reduced, and the method is suitable for online high-precision detection.

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 application discloses a method for intelligent identification of changes in river and lake water areas by a UAV and early warning of abnormal problems in rivers and lakes, comprising the following steps: constructing a digital twin bottom plate data of rivers and lakes; manually editing a basic flight route of the rivers and lakes, intelligently generating a shooting flight route based on the basic flight route and the digital twin bottom plate data of the rivers and lakes, splicing the basic flight route and the shooting flight route, and obtaining a dynamic flight route of the UAV; performing dynamic flight route flight according to the dynamic flight route, collecting data information during flight, and returning the data information to a UAV base station through a network and transmitting the data information to an edge computing device; generating river and lake orthographic images and river and lake spatial terrain data by combining the data information collected by the UAV with water area management lines; and identifying and comparing the orthographic images before and after the two times by using a water area surface identification model and an image difference method, so as to obtain a water area surface change area and abnormal problems in the rivers and lakes. The method solves the problems of low identification accuracy, low image spatial resolution and unintelligent flight route scheduling in the existing UAV patrol of the rivers and lakes.

The invention relates to the technical field of industrial robots, and discloses a robot flexible plug-in teaching method and system based on double-vision collaboration.The method comprises the steps that S1, a double-vision system and a robot coordinate system are calibrated, and a feeder area is defined; s2, in a teaching mode, a human hand track is tracked through a global positioning camera, and a'material taking 'action at a feeder is automatically identified by using a sliding window clustering algorithm; s3, triggering a high-precision Mark point camera to shoot a local image of the PCB after the human hand leaves the plug-in, and accurately calculating a plug-in position coordinate of the component through an image difference technology; and S4, automatically synthesizing a robot executable program according to the identified action sequence and the calculated accurate coordinates. According to the method, traditional manual programming is replaced with visual teaching, the operation technical threshold is remarkably reduced, the industrial-grade operation precision is guaranteed through a double-layer cooperation mechanism of hand guiding and visual fine calibration, the multi-variety production line changing time is greatly shortened, and flexible automatic plug-in is achieved.

The present application relates to the technical field of visual detection device, especially to a mirror shift type double-sided visual detection device. Its technical scheme comprises a rack, a conveying component and a visual detection component. The conveying component adopts double-sided conveying belt support to make the middle part of the workpiece suspended, and the visual detection component realizes synchronous imaging of the top surface, bottom surface and side surface of the workpiece through upper and lower industrial cameras and mirror reflection. In view of the problem that the mirror surface is easy to be contaminated, leading to misjudgment, the device is provided with a movable protective film covering the mirror surface, and when the initial detection is unqualified, the protective film is driven to move and secondary shooting is performed. Through image difference intelligent discrimination of defects, real defects and stains on the film are effectively distinguished. The present application is also integrated with a spacing adjustment and automatic sorting mechanism, which can complete multi-angle and high-precision detection and sorting in a single process, and has the advantages of high detection efficiency, strong anti-interference ability, good adaptability and the like.

The invention relates to the technical field of image processing and defect detection, in particular to an image enhancement method for surface defects of a mining sputtering sensor, which comprises the following steps: an image mapping step: acquiring a single-exposure two-dimensional digital image; mapping a pixel gray value into a node temperature, and constructing a virtual enthalpy field matrix; a matrix evolution step: calculating a local structure tensor, extracting a texture main direction, and generating a heat conduction coefficient matrix; virtual time iterative evolution is started, and a local second derivative is calculated; a barrier construction step: constructing a heat insulation wall if a preset sudden change condition is met; otherwise, keeping unchanged; a decoding difference step: generating a steady-state thermal field and reversely decoding the steady-state thermal field into a substrate background image; performing differential operation to extract a heat dissipation residual image; a fusion output step: superposing the residual image to a non-highlight area to output an enhanced image; extracting or filtering a thermal gradient output defect topological coordinate system; according to the method, self-adaptive smoothing of highlight and forced sharpening of defect edges are realized.

The invention relates to the technical field of microlens detection, in particular to an automatic microlens detection method and system, and the method comprises the steps: obtaining a stripe image of a microlens under the illumination of a stripe structure; preprocessing the stripe image to obtain a preprocessed image with a block area as a foreground; determining a rotation angle according to the boundary of the reference block region, and rotating the corrected stripe image to align the stripe with the row direction; segmenting the rotating image, identifying a connected block, solving an external frame to generate a block mask and a complementary set interval mask thereof, and obtaining a block image and an interval image; performing segmentation on the block image, taking a median value according to rows to replace and generate a block reference image, performing differential binarization to obtain a block defect candidate, and performing independent binarization and merging on an abnormal region; overlapping the interval image and the block mask, performing closed operation to suppress line noise, and then performing binarization inversion to obtain an interval defect candidate; and superposing the two candidate output defect mark images. According to the invention, the defect can be automatically identified and marked and output by the microlens under the stripe background.

The invention discloses a faint target multi-frame enhancement method based on differential comparison. The method is suitable for a multi-faint target image sequence obtained by an infrared detector, and comprises the following steps: step S101, obtaining an infrared faint target image sequence; step S102, background suppression of the infrared image sequence; step S103, carrying out segmentation and multi-frame accumulation on the front and back sequence image groups; step S104, performing contrast enhancement processing on the local features of the front and rear images; step S105, front and back sequence accumulation enhanced image difference contrast factor extraction; and S106, calculating a target difference comparison multi-frame enhancement result. For a dark target image sequence obtained by an infrared detection system, target energy is remarkably enhanced by adopting multi-frame accumulation and local contrast enhancement, the signal-to-noise ratio of the target is improved by combining the local space contrast difference of a difference result after the movement target is enhanced, dark targets with different movement states in a field of view can be accurately enhanced, and the detection accuracy is improved. And an efficient and reliable technical scheme for enhancing and detecting the faint target is provided for the field of infrared detection.

This application discloses a method for collaborative evaluation of the physical modal segmentation of seedling stems and leaves and their physiological quality, belonging to the field of agricultural robot perception and precision detection. The method includes the following steps: outputting a horizontal sinusoidal excitation signal and acquiring at least two images of the seedling under two morphological conditions within the leaf resonant frequency range; performing image difference on any two images to obtain a grayscale difference map; extracting a dynamic mask of the leaves from the grayscale difference map; segmenting the leaves and stems in one of the two images based on the dynamic mask; determining the measured amplitude of the leaves based on the dynamic mask; determining the physiological stiffness of the leaves based on the measured amplitude; determining the stiffness difference between the physiological stiffness and a stiffness threshold, and determining the ratio of the stiffness difference to the stiffness threshold; and determining the seedling quality based on the ratio. This application improves the accuracy and robustness of stem and leaf recognition and segmentation, and meets the requirements for early non-destructive recognition under low computational power and water stress.

This invention discloses a machine vision-based method for measuring the trajectory of an electromagnetic needle selector. The method includes: acquiring a continuous image sequence of the needle selector during operation using a high-speed industrial camera; adaptively cropping the Region of Interest (ROI) using sparse optical flow fusion and image differencing; performing Otsu thresholding, connected component extraction, minimum bounding rectangle fitting, and gray-level centroid calculation on each needle selector region within the ROI to extract feature points of multiple needle selectors; constructing an inter-frame feature matching and trajectory reconstruction algorithm to continuously identify and sort the temporal trajectory of each needle selector; and finally outputting a complete and smooth multi-target motion trajectory. Compared to traditional single-point measurement methods, this method has advantages such as non-contact operation, high concurrency, and high precision, and is suitable for applications such as electromagnetic needle selector status assessment, fault detection, and performance analysis.

The invention relates to the technical field of intelligent storage recognition, and particularly discloses an intelligent storage adaptive recognition system based on deep learning. According to the method, multi-source goods storage identification data are fused, a defect area is positioned and a goods defect value is identified through processing such as image difference, the goods sealing performance is judged by using a DTW algorithm, factors such as a storage environment are integrated to predict an actual residual period of efficacy of goods, and a goods storage state discrimination vector is constructed according to the goods defect value, the sealing performance and the actual residual period of efficacy. The cumulative probability of the goods storage state grade is calculated through a multivariate ordered Logistic regression model, the category with the maximum probability is selected as the storage state grade, and intelligent judgment of the goods storage state is achieved; meanwhile, corresponding strategies are executed based on different goods identification results, intelligence and automation of goods warehouse management are achieved, and the overall efficiency and reliability of warehouse operation are improved.

A method (100) for acquiring and analyzing a scene (4) by image difference is described, the method (100) comprising the steps of acquiring (101) a first image of the scene (4), the first image being formed by ambient light reflected or scattered by the scene; excitation (102) of the scene by an excitation source (1), the excitation (102) triggering a light emission from at least a part of the scene, for a period of emission time; acquisition (103) of a second image of the scene, the acquisition (103) of the second image being synchronized with the excitation (102) so that the acquisition of the second image is carried out during the emission time, the second image being formed by the light emission from the scene added to the reflected or scattered ambient light;calculating a second image (104) adjusted with respect to the first image to compensate for a relative movement of the scene with respect to the sensor (2), calculating (105) a differential image, the differential image being a difference between the first image and the second adjusted image.;

A remote sensing change detection method based on differential enhancement and deep supervision networks belongs to the field of remote sensing image processing technology. First, a pair of high-resolution remote sensing images and their corresponding actual labels are treated as samples. Multiple collected samples are segmented and preprocessed to obtain bi-temporal remote sensing images. Second, a differential enhancement and deep supervision network model is constructed. Third, the differential enhancement and deep supervision network model is trained and validated. Finally, the network training and validation process is repeated; after epochs of network training, the optimal validation result is selected as the final differential enhancement and deep supervision network model. This invention, by introducing an image differential enhancement module, can accurately capture and emphasize subtle changes between bi-temporal remote sensing images; the use of a deep supervision module ensures that the model can fully utilize its output information at all levels, improving detection accuracy; and it exhibits better change detection capabilities when processing complex and variable remote sensing images.

The application discloses a kind of sequence image difference part surface defect detection methods, specific method as follows:First, selecting sequence image in same production batch, the registration of adjacent parts before and after is carried out;Second, in the process of image registration, sequence difference needs to be carried out to part image;Finally, it is judged whether the part to be measured is qualified or not.It is gradually accumulated due to the error in the process of silk screen printing, so when the production sequence difference between template parts and detection parts is too large, accurate difference cannot be achieved, so the above-mentioned sequence image difference part surface defect detection method is used to realize high-precision, high-stability detection of surface feature complex part printing quality defects based on visual detection technology.

The invention provides an inter-image brightness compensation method and a wafer defect detection system, and belongs to the field of image processing and semiconductor detection, and the method comprises the steps: dividing an input image into grid blocks with fixed sizes according to grids, obtaining a local grid block image and a corresponding mask binary image, acquiring a brightness compensation kernel corresponding to the local grid block image; acquiring a local grid block image subjected to brightness compensation; and splicing to acquire a complete adjacent Die reference image subjected to brightness compensation. According to the method, the brightness compensation between the images is carried out in a grid square mode, the local brightness difference between the reference image and the to-be-detected image can be effectively reduced, the robustness of a compensation result of the local brightness of the high-resolution image is improved by introducing a blocking strategy of the grid square mode and a self-adaptive brightness compensation kernel solving mechanism, and the robustness of the local brightness of the high-resolution image is improved. Accuracy and stability of subsequent image differential detection are remarkably improved, and popularization and application in the field of semiconductor optical detection and image processing are facilitated.

The present application relates to a wafer preparation method, system, electronic device and medium of parameter closed-loop optimization. An intelligent feedback mechanism based on defect identification results is constructed. After the defect identification results are obtained through the relatively accurate detection of the image difference defect identification algorithm and the double defect detection path of the defect identification intelligent model, it is further judged whether the detection recipe optimization condition is met based on the defect identification results. If the detection recipe optimization condition is not met, it is directly judged whether the wafer preparation process needs to be optimized based on the defect identification results. If the detection recipe optimization condition is met, the wafer detection recipe parameters are optimized first, that is, only when it is ensured that the detection recipe parameters can accurately detect the defect identification results, the optimization problem of the preparation process parameters is considered, and then the dynamic self-adaptive closed-loop optimization of the wafer detection recipe parameters and the preparation process parameters is reasonably realized, so as to significantly improve the automation level and yield control ability of the wafer manufacturing process.

The invention discloses a multi-level weighted face image differential privacy protection method. The method comprises the following steps: firstly, acquiring a wavelet coefficient of a face image by applying multistage wavelet transform; secondly, calculating the influence of the noise of the wavelet coefficient of each sub-band of each level on the face features by using partial derivative; then, respectively quantizing privacy budget contributed by noise disturbing each level of weighted wavelet coefficient to face features and a local data utility loss function, decomposing a constraint optimization problem into a plurality of sub-problems level by level, and solving a preliminarily optimized noise scale parameter; then, according to the preliminarily optimized scale parameters, reconstructing a global constraint optimization problem, and further solving to obtain optimized scale parameters; and finally, obtaining a disturbed face image and a face feature vector according to a multi-level weighted differential privacy mechanism, hierarchical sampling of noise, disturbance of wavelet coefficients and inverse wavelet transformation. According to the method, sensitive face features in the public face image can be effectively protected, and meanwhile, the visual effect of the image is reserved.

The invention discloses a seedling stem leaf physical mode segmentation and physiological quality collaborative evaluation method, and belongs to the field of agricultural robot perception and precision detection. The method comprises the following steps: outputting a horizontal sine excitation signal, and obtaining at least two images of a seedling in two forms in a leaf resonance frequency interval; carrying out image difference on any two images to obtain a gray difference image; extracting a dynamic mask of the blade from the gray difference graph; based on the dynamic mask, segmenting leaves and stalks in one of any two images; determining the actually measured amplitude of the blade based on the dynamic mask; determining the physiological stiffness of the leaf based on the actually measured amplitude; determining a rigidity difference value between the physiological rigidity and a rigidity threshold value, and determining a ratio of the rigidity difference value to the rigidity threshold value; and determining the quality of the seedlings based on the ratio. According to the method, the precision and robustness during stem leaf identification and segmentation are improved, and the requirements of low calculation power and early lossless identification of water stress are met.

The application discloses a camera data transmission method, system, device and storage medium, and relates to the technical field of image transmission. The method comprises the following steps: a first encoding is performed on an initial image signal received by a target vehicle in a driving process through a camera module to obtain a target image difference signal, and the target image difference signal is sent to a data decoding module; a first decoding is performed on the target image difference signal through the data decoding module to obtain a candidate protocol signal, and the candidate protocol signal is sent to a data encoding module through a high-speed serial or parallel interface; a second encoding is performed on the candidate protocol signal through the data encoding module to obtain the target image difference signal, and the target image difference signal is sent to a data receiving module. According to the technical scheme, the data decoding module and the data encoding module are introduced in the camera data transmission process, the image difference signal is converted and then transmitted, and the transmission distance of the camera image data can be effectively improved.

The invention provides a PCB defect detection method and system fusing deep learning and machine learning, and relates to the technical field of PCB defect detection, and the method comprises the steps: obtaining a region Mask image based on a line region detection model; acquiring a defect Mask image based on a defect position detection model; performing image difference processing on the area Mask image and the defect Mask image to obtain a defect area difference image including defect and line area intersection information; and carrying out defect severity judgment on the defect area difference image subjected to intersection area statistics on the basis of the circuit principle information and the circuit area position coding information of the PCB support plate so as to obtain a defect severity judgment result of the PCB support plate. According to the invention, PCB defect detection is carried out in a mode of combining deep learning, machine learning, PCB carrier board circuit principle information and circuit area position coding information, and the problem that existing PCB carrier board circuit defects cannot be found and repaired in time is solved.

Provided is an image processing device for obstacle detection and recognition, which can appropriately cluster (group) difference data of a subject moving obstacle even if a relative angle of the subject moving obstacle with respect to a host vehicle remains constant, and which can improve reliability of detection and recognition of the obstacle even if the difference data of the subject obstacle decreases as in a situation of a collision path. There are a difference data calculation section (141) that calculates difference data of a plurality of bird's-eye images different in time, a difference data clustering section (151) that clusters the difference data, a cluster combination section (161) that combines clusters with each other based on features of the bird's-eye images using a result of the difference data clustering section (151), and a cluster combination determination section (171) that determines a combination result of the cluster combination section (161) based on features of a subject object.

The invention relates to the technical field of visual inspection devices, in particular to a mirror moving type double-sided visual inspection device. According to the technical scheme, the device comprises a rack, a conveying component and a visual detection component. The conveying part is supported by double-side conveying belts to suspend the middle of the workpiece, and the visual detection part achieves synchronous imaging of the top face, the bottom face and the side faces of the workpiece through upper and lower industrial cameras and mirror reflection. Aiming at the problem of misjudgment caused by easy pollution of the mirror surface, the device wraps the mirror surface with a movable protective film, the protective film is driven to move and performs secondary shooting when the primary detection is unqualified, the authenticity of defects is intelligently judged through image difference, and the real defects and stains on the film are effectively distinguished. The device is further integrated with a distance adjusting and automatic sorting mechanism, multi-angle and high-precision detection and sorting can be completed in a single process, and the device has the advantages of being high in detection efficiency, high in anti-interference capacity, good in adaptability and the like.

The present application relates to the technical fields of image processing and defect detection, in particular to a method for image enhancement of surface defects of a mine sputtering sensor, comprising: an image mapping step: obtaining a single-exposure two-dimensional digital image; mapping pixel gray value to node temperature to construct a virtual enthalpy field matrix; a matrix evolution step: calculating a local structure tensor to extract a main direction of texture to generate a thermal conductivity coefficient matrix; starting virtual time iteration evolution to calculate a local second-order derivative; a barrier construction step: if a preset mutation condition is met, an adiabatic wall is constructed; otherwise, it remains unchanged; a decoding difference step: generating a steady-state thermodynamic field and decoding reversely into a base background image; performing difference operation to extract a thermal dissipation residual image; a fusion output step: superimposing the residual image to a non-high-light area to output an enhanced image; extracting a thermal gradient to output a defect topological coordinate system or to filter out; the present application realizes adaptive smoothing of high light and forced sharpening of defect edges.

The present application relates to the technical field of image processing, and particularly relates to a welding seam performance visual detection method and system based on image processing, the present application obtains a gray image sequence of any welding seam in each sampling period by acquiring the gray image of any welding seam in each sampling period; the gray image sequence is subjected to image difference processing to obtain a difference image sequence, and at least two target images of potential damage evolution regions are screened in the difference image sequence; for any target image, a comprehensive damage coefficient of any target image is acquired according to the roughness and organizational features of each potential damage evolution region in any target image and the confusion degree of pixel points in each potential damage evolution region; the functional relationship between the sampling period and the remaining service life of any welding seam is constructed by using the data variation trend of the comprehensive damage coefficient of each target image, the remaining service life of any welding seam is predicted, and the fatigue damage state of the welding seam is predicted in advance.

The invention discloses a chip abnormal defect identification method based on multi-template fusion and a storage medium. The method comprises the following steps: step 1, constructing a chip defect detection model based on deep learning; step 2, collecting each type of chip image; 3, based on median fusion, obtaining an ideal chip image of each type of chips; step 4, carrying out image difference; step 5, performing sliding cutting on the difference image to obtain chip difference images with the same size and overlapped set sizes; step 6, training a chip defect detection model; step 7, performing differential operation and sliding cutting on the to-be-detected chip image; step 8, predicting a chip defect type and a defect position in a corresponding set chip difference image by using the trained chip defect detection model; and finally, determining the position of the defect in the original to-be-detected chip according to the difference image number of the chip with the set size. According to the invention, the appearance difference between chips of different models can be reduced, the universality of the model is improved, and the defect identification precision is high.

The invention discloses a moving target detection method based on sonar image difference time-space correlation. The method comprises the following steps: carrying out image difference preprocessing; image difference sequence space position correlation; carrying out image difference sequence time position association; the frame of the invention adopts a two-stage method: firstly, on the basis of difference calculation of a detection image and a multi-reference image, an image difference threshold value is calculated by using a Newton-Raphson iteration method, steady-state background noise is removed, and an image space position intersection association principle is designed to effectively reduce random noise interference; and finally, constructing an image difference sequence time position continuous association principle, suppressing a high-intensity reverberation noise false alarm probability, and realizing accurate detection of a moving target. According to the method, not only is simple inter-frame difference carried out, but also correlation analysis is carried out on a series of difference images, the moving target can be detected more accurately by mining the space-time continuity rule of target movement in the difference sequence, the interference of underwater environment noise is effectively overcome, and the accuracy and reliability of detection are improved.

The invention discloses a video melting point acquisition method, a melting point instrument, a program product and a storage medium, and relates to the field of analyzing materials by measuring physical properties of the materials. The method comprises the following steps: identifying sublimation pixel points generated in sample temperature rise through image difference; when the number exceeds a threshold value, starting linear heating, and continuously analyzing the image to generate a hyperbolic curve of the main light transmittance and the main texture complexity; if the light transmittance curve has a negative slope and the texture complexity curve does not decline, excluding the section of abnormal data; determining the temperature at the moment when the slope of the light transmittance curve exceeds a forward threshold for the first time and the texture complexity curve synchronously starts to drop as the initial melting point of the sample; and determining the temperature when the slope of the light transmittance curve tends to be gentle and the texture complexity curve is stabilized at the minimum value as the final melting point of the sample. By implementing the technical scheme provided by the invention, the accuracy of an automatic melting point measurement result is improved.