5173 results about "Visual inspection" patented technology

The invention discloses a visual detection system and method for tiny flaws of industrial products, and belongs to the technical field of product detection, multi-source image data of a target industrial product under multiple detection angles and illumination conditions are acquired, and an image information matrix is established; performing region segmentation and texture enhancement on the image, and extracting local texture direction inconsistency parameters; carrying out normalization analysis on the pixel ratio under different spectrum channels, and calculating a multispectral reflectance ratio abnormal index; constructing a deep convolution recognition model; reasoning the image by using the model, and outputting a defect judgment result and a confidence score; judging whether the area is a flaw area based on a dynamic threshold mechanism, and outputting a detection report containing flaw position information and a visual heat map; according to the method, multi-dimensional fusion identification of texture structure disturbance and spectral response abnormity is realized, the micro defect identification precision is effectively improved, and the method has high robustness, automation and engineering practicability and is suitable for high-precision quality control requirements of various industrial scenes.

The invention provides an external wall visual detection method and system based on deep learning, and the method comprises the steps: firstly obtaining an initial visual image set of a plurality of external wall image units which are collected at different shooting angles and under different illumination conditions and are provided with pixel coordinate marks, and then carrying out the feature preprocessing of the initial visual image set, and generating a standardized feature image set; then, a pre-trained outer wall defect detection model is called to carry out defect feature recognition on the standardized feature image set, a preliminary detection result is obtained, and a final detection result is determined according to confidence distribution of a defect type candidate set in the preliminary detection result and spatial position relevance of candidate areas. And finally, generating an outer wall defect detection report containing defect type statistical information and a position distribution diagram based on a final detection result, and sending the outer wall defect detection report to the target terminal equipment to trigger subsequent maintenance operation. Therefore, the accuracy and efficiency of outer wall detection are improved.

The invention discloses an automobile leather defect detection method and system based on visual inspection, and relates to the technical field of industrial visual inspection, and the method comprises the steps: reconstructing the three-dimensional shape of a leather surface and generating a three-dimensional point cloud picture by analyzing the parallax relation and illumination direction reflection characteristics among multi-view automobile leather images; automobile leather surface curvature change characteristics of the three-dimensional point cloud picture are extracted, multi-scale texture analysis is carried out, and potential defect areas are identified and marked; through a three-dimensional shape measurement method, defect three-dimensional shape characteristics of the potential defect area are extracted, and defect three-dimensional geometric parameters are calculated; by analyzing defect geometrical characteristics and spatial distribution rules of the defect three-dimensional geometrical parameters and utilizing a preset grading judgment rule to divide defect grades, an automobile leather quality evaluation report containing defect three-dimensional coordinates is generated; according to the method, through combination of curvature-texture multi-scale fusion detection, the recognition capability of complex surface defects is remarkably enhanced.

The invention discloses an aluminum alloy surface defect detection method and system using deep learning, and relates to the related field of detection performed in combination with deep learning, and the method comprises the following steps: carrying out image acquisition on an aluminum alloy finished product, constructing a surface image data set to extract multi-scale surface features, and constructing a feature enhanced image set to carry out defect detection, and a defect detection result is obtained to dynamically optimize aluminum alloy production process parameters, and a process adjustment instruction is generated and fed back to a production system. The technical problems that traditional detection mostly depends on manual visual inspection or a machine vision system based on rules, imaging distortion, small defect missing detection and process adjustment are caused are solved, and the technical effects that deep learning is conducted through the double-branch network, the defect detection efficiency and the production yield are improved, and control over the aluminum alloy manufacturing quality is met are achieved.

The invention discloses an intelligent welding forming method and system for a green building steel heating radiator, and the method comprises the following steps: carrying out the surface defect recognition of a steel heating radiator base material based on an AI visual inspection system, recognizing a qualified base material, and automatically matching the type of a welding material from a material database according to the material and thickness parameters of the qualified base material. Welding parameters are intelligently matched through AI visual inspection and a neural network model, a laser and friction stir hybrid welding process is combined, traditional manual operation is replaced, the welding efficiency and precision are improved, and the problems of uneven welding seams and the like are solved; welding data are analyzed in real time through a multi-mode AI model, parameters are dynamically adjusted, intelligent defect recognition and repair welding are achieved in cooperation with 3D visual inspection, and the quality stability is improved through whole-process monitoring; smoke dust is treated through an environment-friendly process, acid pickling is replaced with mechanical rust removal, efficient recycling of materials is achieved through waste recycling, a green manufacturing system is constructed, and the sustainable development requirement of green buildings is met.

The invention relates to the technical field of visual inspection, in particular to a multi-mode industrial product dynamic defect detection system based on edge calculation. According to the method, by introducing a multi-modal image construction and enhancement mode, three-dimensional acquisition and enhanced expression of detail information of the surface of the wind power blade are realized, and by means of inter-modal image synchronization and a space registration mechanism, the consistency extraction capability of defect information under different sensor view angles is improved; through combination of density change trend analysis and direction mutation identification means, surface micro cracks, edge damages and other structural changes can be accurately identified in continuous frames, and further through multi-source discrimination and mutual elimination comparison of abnormal indexes, environmental interference and misjudgment risks are effectively eliminated, and the accuracy of the detection result is improved. Therefore, a stable defect track area with direction consistency and distribution continuity is screened out, accurate detection and partition identification of the surface defects of the wind power blade under the dynamic condition are achieved, and the reliability and precision of defect positioning are remarkably improved.

The invention discloses a package defect elimination method based on visual inspection, and relates to the technical field of image processing and computer vision, and the method comprises the following steps: setting a polarized light source with a fixed angle on a package production line, and uniformly illuminating a target package area to enable the incident light polarization direction and the package surface reflection direction to form a deviation angle; an industrial camera provided with a polarization filter is used for carrying out image collection on a packaging target area, and the polarization direction of the filter is perpendicular to the polarization direction of a light source so as to restrain reflection interference to the maximum extent. Reflection interference is eliminated through polarized light, and the image quality is improved; by combining a neural network and feature fusion scoring, the defect recognition accuracy and adaptability are improved; a closed-loop elimination control and data tracing mechanism is introduced, the elimination precision is guaranteed, quality responsibility investigation is supported, and the intelligence and reliability of the packaging defect detection and elimination system are integrally improved.

The invention discloses a photovoltaic glass defect detection method and system based on image recognition, particularly relates to the technical field of visual inspection, and is used for solving the problem that defect recognition is interfered by optical artifacts caused by a film layer interference effect on the surface of coated glass. The method comprises the following steps: extracting interference characteristics through a reflection image to generate an optical artifact distribution diagram, positioning an interference region in a transmission image frequency domain space, constructing a process response template in combination with a sedimentary pulse frequency, and executing polarization coherence screening and time-varying deconvolution collaborative filtering to eliminate artifacts; based on energy ratio dynamic decision reinspection or defect classification process implementation, inherent optical noise and real physical defects of a material are effectively separated, and the accuracy and reliability of coated glass defect detection are remarkably improved.

The invention provides a supporting cable production monitoring method and system for 3D visual detection, and relates to the technical field of image processing and intelligent detection, and the method carries out multi-source fusion processing based on collected cable three-dimensional space image data, and comprises coordinate alignment, point cloud reconstruction and multi-scale feature extraction, and construction of a unified space geometric model. On the basis, the center line of the cable is extracted, coordinates of starting and ending points are calculated, and then geometric evaluation parameters such as the axial deviation rate and the straightness are obtained. The method has the advantages of high precision, high robustness and high universality, and is suitable for real-time detection and quality control of slender components such as cables and hoses in the industrial production process. According to the invention, the technical problems of inaccurate three-dimensional structure extraction, insufficient defect identification, difficult defect cause tracing and untimely early warning response in the prior art can be solved.

The invention relates to the field of image processing, and particularly discloses a welded pipe surface defect detection method based on robot visual inspection. The method comprises the steps that a robot carries a binocular camera and an annular LED light source and moves at a constant speed in the axial direction of a welded pipe to collect orthographic and inclined views, and a three-dimensional point cloud is constructed; and establishing a parameterized mapping function based on the point cloud, and converting the 3D coordinate into a 2D expansion surface coordinate. In the convolutional neural network, a first layer is inserted into a spatial transformation network to correct distortion of the expanded image, deformable convolution is adopted to extract edge, local deformation and specific defect response features, and standard convolution is combined to extract global features; and fusing multi-scale features and adding an attention mechanism to improve the weight of a defect region, and outputting a defect category and a bounding box offset after generating a candidate box. The method effectively solves the problems of stretching, deformation and defect distortion of welded pipe curved surface imaging, reduces the imaging difference of the same defect, and remarkably improves the defect positioning precision and recognition accuracy.

The invention relates to the technical field of industrial machine vision detection and image processing, in particular to an automobile part production mold surface smoothness detection system based on image enhancement, which comprises a data acquisition module used for acquiring an original grayscale image of the surface of an automobile part mold; performing low-pass filtering processing on the original grayscale image to eliminate imaging thermal noise; the manifold reconstruction module is used for constructing a structure tensor field; reversely deducing a pseudo-curvature field of the mold surface; the adaptive enhancement module is used for generating a corrected image; constructing a texture orthotropic diffusion model; generating a texture reconstruction reference image; the surface metering module is used for calculating the difference between the corrected image and the texture reconstruction reference image and generating a defect saliency image; calculating the surface roughness value of the mold surface; according to the method, the problem that design textures and abnormal scratches are difficult to distinguish in the prior art is effectively solved, and the technical bottleneck that micro defects are easily missed in a complex geometric structure in traditional visual detection is overcome.

The invention discloses a chip surface defect visual detection method and system, and the method comprises the steps: carrying out the high-sensitivity imaging through the dynamic adaptation of a quantum imaging enhancement module to the surface reflectivity, and achieving the sparse efficient processing of a defect signal through the combination of event-driven vision and a pulse neural network; based on a risk thermodynamic diagram generated in real time, intelligently scheduling detection precision and speed resources, and utilizing multi-modal feature decoupling and a federal knowledge graph to accurately associate defects and process roots; the digital twinning module synchronously predicts a defect evolution path and drives online adjustment and optimization of process parameters, and meanwhile the dynamic compensation module corrects optical defocus in real time. According to the invention, full-detection coverage of nanoscale defects is realized, a defect transfer chain is actively blocked while the detection efficiency is improved, and the chip manufacturing yield and reliability are remarkably improved.

The invention discloses a ship plane segmented welding multi-robot path planning system based on visual inspection, and relates to the technical field of ship manufacturing, the ship plane segmented welding multi-robot path planning system comprises a multispectral visual inspection module which is mounted on a portal frame and comprises a laser scanning sensor and an infrared thermal imager, the system is used for collecting three-dimensional point cloud and temperature distribution data of ship plane segments in real time. According to the ship plane segmented welding multi-robot path planning system based on visual inspection, the problem of path planning misalignment caused by assembly errors, thermal deformation and complex working conditions in large ship plane segmented welding is fundamentally solved through a multispectral visual real-time perception and material self-adaption dynamic correction mechanism. A composite correction vector and space-time grid collaborative pre-judgment technology is adopted, the welding seam track precision is effectively improved, it is ensured that the weld leg size strictly reaches the standard in the high-difficulty processes such as wrap angle welding and vertical position welding of the maximum-size workpiece, the defects such as air holes and cracks are eliminated, and the rework rate and the quality risk are greatly reduced.

The invention discloses an automobile production line gluing system based on visual inspection, and relates to the technical field of industrial automation and intelligent control, and the automobile production line gluing system comprises a gluing data acquisition module, a gluing feature extraction module, a compensation correction module, a gluing decision module and a closed-loop management and control module; the gluing data acquisition module preprocesses assembly line gluing track images and glue gun nozzle three-dimensional coordinate data, the gluing feature extraction module constructs a gluing feature sequence table, the compensation correction module outputs glue outlet opening degree compensation amount and nozzle track correction amount, and the gluing decision-making module outputs glue gun pressure adjusting amount and nozzle movement speed. And the closed-loop management and control module detects pressure abnormity and speed stability in real time, optimizes control parameters and generates a process quality map. Through real-time visual detection and dynamic closed-loop control, the glue line width precision is improved, the track compensation response is shortened, the glue gun speed fluctuation coefficient and glue waste are reduced, the gluing qualification rate is improved, the production cost is reduced, and the automobile manufacturing and production requirements are met.

A visual defect detection method, device, medium and product relate to the field of visual detection, and the method comprises the following steps: firstly, recording brightness changes of pixel points in different illumination directions by constructing an illumination response matrix, and establishing a complete mapping of surface reflection characteristics; secondly, performing joint calculation by using the light source direction matrix and the illumination response matrix to obtain normal vector data and reflectivity data, and representing spatial geometric features and material optical features of the surface respectively; thirdly, calculating a gradient feature map, a curvature feature map and a deformation feature map based on the normal vector data, generating a reflectivity map by using the reflectivity data, and forming a multi-dimensional feature representation system; and finally, in a defect detection stage, a strategy of combining gradient feature pre-screening with multi-feature verification is adopted, and final judgment is carried out by calculating a comprehensive defect feature value, so that the technical problem of insufficient micro defect detection precision of a visual detection method in the prior art is solved.

The invention discloses a wiring terminal full appearance detection system and method based on an annular track platform, and the system comprises a track which is provided with a transparent material conveying chain plate segment and is used for the uniform motion transmission of a wiring terminal; the multi-station visual detection device comprises a plurality of visual camera groups and an object distance adjusting assembly, the plurality of visual camera groups are respectively arranged at different stations of the track and are used for carrying out image acquisition on six front-view main surfaces and a set surface of the wiring terminal, and the object distance adjusting assembly is connected with the visual camera groups and is used for carrying out image acquisition on the set surface of the wiring terminal. The object distance adjusting assembly is used for adjusting the object distance or / and the position of the linear scanning camera; the AI visual inspection module comprises an image marking unit used for carrying out defect classification and marking on the collected images; the model training unit is used for carrying out iterative training on the marked image based on a small sample learning algorithm to generate a multi-station detection model; and the real-time detection unit is used for deploying a multi-station detection model to execute component statistics, defect detection and defective product rejection.

The invention discloses a part visual inspection method and system for powder metallurgy machining, and belongs to the field of powder metallurgy manufacturing. The method comprises the steps that a gray image of the surface of a part is acquired; obtaining a window scale coefficient of each pixel point according to the gray level change of other pixel points in the neighborhood range of each pixel point in the gray level image; obtaining a global gray center point according to the gray distribution of the gray image; obtaining a central point offset coefficient of the pixel point according to the window scale coefficient, the gray scale difference and the global gray scale central point of the pixel point; according to the center point offset coefficient of the pixel point, obtaining the center importance degree of the pixel point to the grayscale image, including obtaining the overall importance degree and the local correction coefficient; the pixel points are divided into interested areas or non-interested areas according to the center point offset coefficient, scale transformation is carried out in combination with the center importance degree, visual detection is completed, and the detection adaptability to defects of different scales and forms is improved through self-adaptive window analysis and an overall-local double correction mechanism.

The invention discloses a lens production defect detection method and equipment thereof, and relates to the technical field of visual inspection.The equipment comprises an information acquisition module, a central processing unit, a process regulation and control module and an interactive communication module.The information acquisition module acquires multi-source sensing information at regular time, so that both comprehensiveness and accuracy are improved; high accuracy of visual detection is guaranteed; through an information processing model, quantification is accurate and traceable, defect degree visualization and defect accurate classification are realized, then process defects are positioned, the interference degree of the environment on a detection result is determined, and misjudgment of the defects due to environmental factors is avoided; through linkage of defect data, process precision and environmental interference, a process optimization scheme is generated in a targeted manner, closed-loop response from defect generation to process adjustment is realized, and the production line response speed is improved; and finally, the lens production yield is remarkably improved, and the production cost of long-term detection is reduced.

The invention discloses a nondestructive testing device for a steel profile and a testing method of the nondestructive testing device. According to the method disclosed by the invention, the ultrasonic technology is combined with optical imaging, so that synchronous detection of surface and internal defects can be completed at one time. Ultrasonic waves penetrate through the interior of the steel profile, and hidden defects such as cracks and air holes are accurately recognized; the optical camera module captures visible problems such as surface scratches and corrosion in real time. The integrated detection mode avoids the tedious process of step-by-step operation required by a traditional method, for example, magnetic powder detection of surface defects and ultrasonic scanning of an internal structure are not needed, the detection period is greatly shortened, and the method is especially suitable for steel structure buildings, bridge engineering and other scenes with high requirements for detection efficiency and has good application prospects. The full-process automatic design effectively reduces the influence of human intervention, and ensures the scanning continuity of the detection area; the intelligent algorithm automatically analyzes the ultrasonic echo signal and the optical image data, and judges the defect level according to the preset standard, thereby avoiding subjective misjudgment of manual visual inspection.

The invention relates to the technical field of welding platforms, in particular to a multifunctional welding process experiment platform and a process optimization system.The process optimization method comprises the following steps that a welding process setting module is constructed, and a welding mode, a groove type and a heat input scheme are preset; outputting the initial process configuration parameter set to drive a welding execution unit to perform automatic welding operation according to the initial process configuration parameter set; extracting a multi-dimensional process response vector including a stability index, metal fusion depth distribution and a heat affected zone expansion degree; outputting a welding seam grade result according to a preset quality grading standard, and generating a feedback identifier; and after updating, inputting to the step S2 again to form closed-loop optimization control. According to the method, digital modeling and evaluation of key indexes such as the welding stability, the fusion depth and the heat affected zone are achieved, and the problem that a traditional process depends on visual inspection and experience judgment is solved.

Methods, systems, and computer-readable storage media for a defect detection system that generates synthetic defect data that is representative of real-world defects in products. The synthetic defect data is included in training data for training a defect detection model. The defect detection model is deployed to a production environment to detect defects in products.

The invention provides an industrial defect image generation system and method based on deep learning, and relates to the technical field of artificial intelligence. A defect form adaptive module, a physical attribute modulation module and a multi-mechanism fusion module are integrated in a defect image generation module; dynamically selecting a feature extraction unit according to the defect type label based on a pre-constructed generative network model, and generating a defect feature map; generating an affine transformation parameter based on the physical attribute vector, and performing channel-by-channel linear modulation on a defect feature map of a middle layer of the generative network model, so that a multi-scale defect feature map finally generated by the generative network model contains specified defect type features and physical attribute features; and fusing the multi-scale defect feature image and the defect-free background image to obtain a fused defect image. The problems that in the prior art, industrial defect image generation is insufficient in sense of reality, poor in controllability and poor in fusion effect are solved, the method can be used for data enhancement of industrial visual inspection, and downstream model performance is improved.

The invention discloses a photoelectronic device surface defect visual detection method and system based on image recognition, and the method comprises the steps: carrying out the processing and fusion of three-waveband image data, and obtaining a three-waveband composite image; constructing a DFD-Net double-branch deep network model, inputting a three-band synthetic image into the model, capturing multi-scale defect geometric features through an ASPP module with increasing voidage, extracting reflective insensitive texture features through a phase-consistent convolutional layer, and performing feature fusion by using a gated cross attention mechanism to obtain a multi-scale defect feature fusion model; performing coarse positioning on the fused feature image based on an improved YOLOv5 target detection algorithm to obtain a defect area image, and calculating a pixel-level mask of the defect area image to obtain a segmented image; and positioning a defect boundary of the segmented image through an NMS non-maximum suppression algorithm, and outputting defect coordinates and size information. And the surface defect detection efficiency of the optoelectronic device is improved.

The invention provides a high-resolution machine vision detection method and system for precise chromatic aberration detection and a medium, and the method comprises the steps: carrying out the calibration of a camera based on a camera calibration tool, and synchronously calibrating a light source parameter and a color parameter; setting shooting parameters based on the calibrated camera, obtaining a workpiece image in real time, preprocessing the workpiece image, mapping the preprocessed image to a standard color space from an original RGB space, and extracting color features of the preprocessed image; comparing the color feature with the color feature of the standard sample, calculating a color difference index, and comparing with the color difference index based on a set color difference threshold to obtain a detection result; by calibrating various parameters of the camera, the visual detection precision is ensured, and by performing color space mapping on the workpiece image and analyzing the difference between the color difference index of the color feature and the color difference threshold value, the color abnormal area is accurately analyzed, and the detection precision of the abnormal color is improved.

The invention discloses an automatic production line control system and method for stamping and welding vehicle body parts, and relates to the technical field of vehicle body part production. The system comprises a welding robot module, an integrated visual detection module, an image processing server, a control PLC, a welding parameter regulator, a defective workpiece processing module, a data tracing cloud platform, a multispectral illumination module, a deep learning acceleration card and a welding spot temperature infrared sensor. On-line full inspection of the welding spot quality is achieved, the omission ratio is extremely low, and the integrated vision module maintains the imaging definition in a splashing environment through a nanometer coated lens and a piezoelectric self-cleaning technology; the multi-spectral lighting module solves the problem of reflective interference of an aluminum vehicle body, the defect recognition accuracy is high, the real-time closed-loop response is fast, the pseudo soldering recurrence rate is low through dynamic current compensation, the pneumatic marking positioning precision is high, accurate coordinates are provided for repair, the system supports high-speed detection of welding spots, and the high-beat requirement of a vehicle body part punching and welding automatic production line is met.

The invention relates to the technical field of arch bridge monitoring, and particularly discloses a deformed steel arch bridge health monitoring and early warning system based on multi-source data fusion, which comprises a data acquisition module, a data preprocessing module, a multi-source data fusion module, an anomaly detection and mode recognition module and a health assessment and early warning module, a visual detection and image analysis module and a risk prediction and decision support module; by adopting the adaptive sampling method, the sampling frequency can be dynamically adjusted according to the dynamic change of the bridge, the load state and the importance of the sensor, so that the sampling frequency is reduced when the bridge is in a stable state, and the collection of redundant data is reduced; the redundant data generated when the data acquisition frequency is too high is reduced through self-adaptive sampling, so that the requirement for the storage space and the bandwidth requirement for data transmission are reduced, and the calculation efficiency is improved.

The invention provides a visual detection system and method for positioning a welding spot of an injection molded part, and the method comprises the steps: obtaining the original image data of a workpiece, determining the actual position of the workpiece, and generating position deviation data based on the actual position of the workpiece and a preset reference coordinate; according to the position deviation data, calculating a workpiece position deviation and judging whether the workpiece position deviation exceeds a preset threshold range or not, if yes, dynamically adjusting a preset reference coordinate to obtain corrected coordinate reference information, and according to the corrected coordinate reference information, performing region division on the original image data to obtain a region division result; a target area where the welding spot possibly exists is locked in combination with the deviation influence area range to serve as a welding spot candidate area; and a welding spot feature pixel set is extracted from the welding spot candidate area according to the welding spot shape constraint condition and the screening rule, a preliminary recognition result of the welding spot is obtained, secondary filtering is carried out, and final welding spot position coordinate data is determined. According to the invention, through multi-stage accurate positioning and correction, the accuracy and reliability of welding spot detection are effectively improved.

The invention is suitable for the technical field of visual inspection, and provides a circuit board detection method and system based on machine vision, and the method comprises the steps: obtaining an initial image pair of the surface of a circuit board, and calculating a parallax error based on the initial image pair to generate a depth map; based on the depth map, utilizing a preset path planning algorithm to generate an optimized image acquisition path; acquiring an image of the surface of the circuit board according to the optimized image acquisition path to obtain a target image set; extracting defect features corresponding to the target image set according to a preset feature extraction rule to obtain a defect feature set; constructing visual semantic distribution based on the defect feature set, and generating a defect node feature set; according to the defect node feature set, constructing a defect graph topological structure by utilizing each defect node and an edge connection relationship between the defect nodes; according to the method, the topological structure of the defect graph is analyzed by using the graph convolutional network, the connection relationship between the defect features is determined, and the target defect feature is generated, so that the circuit board defect detection precision is improved.

The invention discloses an RGB-D-based van carton stacking 3D point cloud recognition and positioning method, and belongs to the field of machine vision and automatic logistics. An existing visual detection algorithm is poor in recognition and positioning accuracy, complex in calculation and low in detection efficiency. The method comprises the following steps: acquiring RGB images of a target object under two visual angles and depth images of the target object under the two visual angles, performing denoising processing on the acquired images, combining the denoised images of the same visual angle to obtain a three-dimensional point cloud image under the corresponding visual angle, and fusing the three-dimensional point cloud images under the two visual angles to generate a complete three-dimensional point cloud image; the method comprises the steps of optimizing point cloud data in a point cloud image, inputting an optimized two-dimensional RGB point cloud image into a pre-trained YOLO target detection model, outputting a detection image, correcting center coordinates of sub-objects in the detection image, obtaining corrected two-dimensional center point coordinates of all the sub-objects, further obtaining three-dimensional coordinates, and finally obtaining a three-dimensional point cloud image. The method is used for identifying coordinate points of each sub-object.

The invention relates to the technical field of printed matter quality detection and computer vision and the technical field of artificial intelligence systems in the production field, in particular to a color box printed matter printed pattern visual detection algorithm. The invention discloses a visual detection algorithm for a printing pattern of a color box printed matter. The visual detection algorithm comprises the following steps of image acquisition, preprocessing, feature extraction, reference comparison, defect evaluation and defect classification. According to the scheme, the accuracy and the real-time performance of complex printing pattern defect detection are improved. A light-weight multi-scale attention convolutional neural network and a self-learning mechanism are combined, defects in various printing patterns such as block colors, fine characters and graph gradient are effectively detected, and human intervention and misjudgment are reduced. A defect saliency map is generated through color normalization, geometric correction preprocessing and reference map comparison, an online misjudgment cache and incremental learning strategy is introduced, self-adaptive optimization of a model along with time is kept, and real-time high-precision quality monitoring of an offset printing color box production line is achieved.