CN114199892B - Plate measuring method and system based on machine vision - Google Patents
Plate measuring method and system based on machine vision Download PDFInfo
- Publication number
- CN114199892B CN114199892B CN202111504912.9A CN202111504912A CN114199892B CN 114199892 B CN114199892 B CN 114199892B CN 202111504912 A CN202111504912 A CN 202111504912A CN 114199892 B CN114199892 B CN 114199892B
- Authority
- CN
- China
- Prior art keywords
- plate
- result
- characteristic
- defect
- convolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
Abstract
The invention discloses a plate measuring method and system based on machine vision, wherein the method comprises the following steps: carrying out size identification on the first image information set to obtain first basic size information; performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information; performing defect analysis on the first image information set to obtain a first plate defect result, and positioning the first plate defect result; inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result; and screening the first plate according to the first plate quality result and the preset plate quality grade requirement. The technical problems that in the prior art, manual measurement is poor in precision, measurement accuracy and measurement efficiency are low, and accordingly the quality of the plate cannot be guaranteed are solved.
Description
Technical Field
The invention relates to the field of data measurement, in particular to a plate measuring method and system based on machine vision.
Background
The plate (sheet material) is a flat rectangular building material plate with standard size, is applied to the building industry, is used as a component of a wall, a ceiling or a floor, has flat appearance, large width-to-thickness ratio and large surface area of unit volume, and can be divided into a thin plate, a middle plate, a thick plate and an extra-thick plate which are usually made into the flat rectangular building material plate with standard size.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problems that in the prior art, manual measurement is poor in precision, low in measurement accuracy and measurement efficiency and incapable of guaranteeing the quality of the plate exist.
Disclosure of Invention
The embodiment of the application provides a plate measuring method and system based on machine vision, solves the technical problems that in the prior art, manual measurement is poor in precision, measurement accuracy and measurement efficiency are low, and plate quality cannot be guaranteed, achieves the purpose of automatically measuring and judging plates by acquiring images through machine vision, is high in measurement precision, improves detection efficiency and detection success rate, and accordingly guarantees the technical effect of quick screening of plate quality.
In view of the above, the present invention has been made to provide a method that overcomes or at least partially solves the above mentioned problems.
In a first aspect, an embodiment of the present application provides a sheet material measurement method based on machine vision, where the method includes: obtaining a first image information set through the image acquisition device, wherein the first image information set comprises a multi-angle image set of a first plate; obtaining a first identification instruction, and carrying out size identification on the first image information set according to the first identification instruction to obtain first basic size information; performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information; obtaining a first analysis instruction, performing defect analysis on the first image information set according to the first analysis instruction to obtain a first plate defect result, and performing position positioning on the first plate defect result; inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result; obtaining the quality grade requirement of a preset plate; and screening the first plate according to the first plate quality result and the preset plate quality grade requirement.
In another aspect, the present application further provides a sheet material measuring system based on machine vision, the system comprising: a first obtaining unit for obtaining a first image information set by an image acquisition device, wherein the first image information set comprises a multi-angle image set of a first plate; a second obtaining unit, configured to obtain a first identification instruction, perform size identification on the first image information set according to the first identification instruction, and obtain first basic size information; a third obtaining unit, configured to perform plane modeling on the first plate according to the first basic size information, obtain a first mechanical profile, and label the first mechanical profile according to the first basic size information; a fourth obtaining unit, configured to obtain a first analysis instruction, perform defect analysis on the first image information set according to the first analysis instruction, obtain a first plate defect result, and perform position location on the first plate defect result; a fifth obtaining unit, configured to input the first basic size information and the first plate defect result into a plate quality analysis model, and obtain a first plate quality result; a sixth obtaining unit, configured to obtain a predetermined plate quality grade requirement; the first screening unit is used for screening the first plate according to the first plate quality result and the preset plate quality grade requirement.
In a third aspect, an embodiment of the present invention provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the method for controlling output data includes any one of the steps described above.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the method for controlling output data described in any one of the above.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
due to the adoption of the method, a first image information set is obtained through the image acquisition device, and the first image information set comprises a multi-angle image set of the first plate; performing size recognition on the first image information set according to the first recognition instruction to obtain first basic size information; performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information; performing defect analysis on the first image information set according to the first analysis instruction to obtain a first plate defect result, and performing position positioning on the first plate defect result; inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result; and screening the first plate according to the first plate quality result and the preset plate quality grade requirement. And then reach and acquire the image through machine vision and carry out automatic measurement judgement to panel, measurement accuracy is high, has improved detection efficiency and detection success rate to guarantee the technical effect of panel quality quick screening.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flowchart of a sheet material measuring method based on machine vision according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating a method for obtaining a defect result of a sheet material in a sheet material measurement method based on machine vision according to an embodiment of the present disclosure;
FIG. 3 is a schematic view illustrating a process of positioning a defect result of a sheet material in a sheet material measuring method based on machine vision according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram illustrating a process of obtaining a plate feature result in a plate measurement method based on machine vision according to an embodiment of the present disclosure;
fig. 5 is a schematic flowchart illustrating a convolution operation performed on a sheet feature in a sheet measurement method based on machine vision according to an embodiment of the present disclosure;
FIG. 6 is a schematic flow chart illustrating a process of correcting a plate material quality result in a plate measuring method based on machine vision according to an embodiment of the present disclosure;
FIG. 7 is a schematic flow chart illustrating a sheet quality result obtained by a sheet measuring method based on machine vision according to an embodiment of the present disclosure;
FIG. 8 is a schematic structural diagram of a sheet measuring system based on machine vision according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device for executing a method for controlling output data according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a sixth obtaining unit 16, a first screening unit 17, a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, an operating system 1151, an application 1152 and a user interface 1160.
Detailed Description
In the description of the embodiments of the present invention, it should be apparent to those skilled in the art that the embodiments of the present invention can be embodied as methods, apparatuses, electronic devices, and computer-readable storage media. Thus, embodiments of the invention may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, embodiments of the invention may also be embodied in the form of a computer program product in one or more computer-readable storage media having computer program code embodied in the medium.
The computer-readable storage media described above may take any combination of one or more computer-readable storage media. The computer-readable storage medium includes: an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium include: a portable computer diskette, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, a flash memory, an optical fiber, a compact disc read-only memory, an optical storage device, a magnetic storage device, or any combination thereof. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device.
Summary of the application
The embodiments of the present invention describe the provided method, apparatus, and electronic device through flowchart and/or block diagram.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner. Thus, the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The embodiments of the present invention will be described below with reference to the drawings.
Example one
As shown in fig. 1, the present application provides a method for measuring a sheet material based on machine vision, wherein the method is applied to a sheet material measuring system, the system includes an image capturing device, and the method includes:
step S100: obtaining a first image information set through the image acquisition device, wherein the first image information set comprises a multi-angle image set of a first plate;
particularly, through image acquisition device is right the image information of first panel gathers, image acquisition device is the array camera of accurate interval, can be right panel carries out the image acquisition of multi-angle not equidirectional for it is more accurate various to panel image acquisition, with the accuracy that is used for follow-up size to acquire. The plate is a flat rectangular building material plate with standard size, and is widely applied to the aspects of chemical industry, containers, buildings, metal products, metal structures and the like, and comprises steel, wood, glass, ceramic plates and the like.
Step S200: obtaining a first identification instruction, and carrying out size identification on the first image information set according to the first identification instruction to obtain first basic size information;
step S300: performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information;
specifically, size recognition is carried out on the first image information set acquired from multiple angles according to the first recognition instruction, and basic size information of the plate is acquired, wherein the basic size information comprises the length, the width, the thickness and the like of the plate structure. And performing plane modeling on the first plate according to the first basic size information, such as CAD plane modeling, constructing a structural outline of the plate, and completely describing all geometrical information of the plate, including information of a size structure, a face, an edge and a vertex. And marking the size of the modeling mechanical contour drawing of the plate according to the first basic size information, so as to ensure the accurate measurement of the size of the plate, and be used for the subsequent quality analysis of the plate.
Step S400: obtaining a first analysis instruction, performing defect analysis on the first image information set according to the first analysis instruction to obtain a first plate defect result, and performing position positioning on the first plate defect result;
as shown in fig. 2, further to the above, the performing defect analysis on the first image information set according to the first analysis instruction to obtain a defect result of the first plate material, step S400 in this embodiment of the present application further includes: :
step S410: constructing a plate defect characteristic database through big data;
step S420: performing image segmentation on the plate image in the first image information set to obtain pixel information of N sub-images;
step S430: classifying according to the pixel size of each point image in the N sub-image pixel information to obtain each category of image pixel information;
step S440: performing characteristic analysis on the pixel information of each type of image to obtain first plate characteristic information;
step S450: and comparing the first plate characteristic information with the plate defect characteristic database to obtain a first plate defect result.
Specifically, defect analysis is performed on the multi-angle image information set of the plate according to the first analysis instruction, namely various defect information on the influence quality and the use value of the plate is analyzed, and the defect position of the first plate is accurately positioned on the defect result. And constructing a board defect characteristic database through the big data, wherein the board defect characteristic database comprises various defect characteristics of the board, such as natural defects, color defects, drying defects, and defects of blunt edges, sharp edges, corrugated saw marks, wavy lines, burrs, saw cut deflection and the like generated in the machining process. The image segmentation is a technology and a process for dividing an image into a plurality of specific areas with unique properties and providing an interested target, and is a key step from image processing to image analysis, the image segmentation is carried out on a plate image in the first image information set to obtain N pieces of sub-image pixel information, and classification is carried out according to the pixel size of each point image in the N pieces of sub-image pixel information to obtain each type of image pixel information, such as a plate color type image, a plate surface structure type image, a plate smoothness type image and the like. And performing characteristic analysis on the pixel information of each category of image to obtain each characteristic information of the plate, and comparing the first plate characteristic information with the plate defect characteristic database to obtain the defect result condition of the plate. The technical effects that the image segmentation analysis processing technology is adopted, the flaw defect judgment of the plate is more accurate, the defect position is accurately positioned, and the subsequent plate quality analysis result is more reasonable and accurate are achieved.
Step S500: inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result;
as shown in fig. 7, further, wherein the inputting the first basic size information and the first sheet defect result into a sheet quality analysis model to obtain a first sheet quality result, step S500 of this embodiment further includes:
step S510: inputting the first basic size information and the first plate defect result into the plate quality analysis model as input information;
step S520: the plate quality analysis model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises: the first base size information, the first sheet defect result, and identification information for identifying a first sheet quality result;
step S530: and obtaining a first output result in the plate quality analysis model, wherein the first output result comprises the first plate quality result.
Specifically, the plate quality analysis model is a Neural network model, i.e., a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network device formed by widely connecting a large number of simple processing units (called neurons), reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning device. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (ANN), is a description of the first-order properties of human brain devices. Briefly, it is a mathematical model. And through training of a large amount of training data, inputting the first basic size information and the first plate defect result into a neural network model, and outputting the first plate quality result.
More specifically, the training process is a supervised learning process, each set of supervised data includes the first basic size information, the first sheet defect result, and identification information for identifying a first sheet quality result, the first basic size information and the first sheet defect result are input into a neural network model, the neural network model performs continuous self-correction and adjustment according to the identification information for identifying the first sheet quality result, and the set of supervised learning is ended until the obtained first output result is consistent with the identification information, and the next set of data supervised learning is performed; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervision and learning of the neural network model, the neural network model can process the input information more accurately, the output first plate quality result information is more reasonable and accurate, the plate quality is evaluated by combining the plate size and defect analysis, the plate quality analysis accuracy and objectivity are improved, and the technical effect of more reasonable and accurate plate quality screening is achieved.
Step S600: obtaining the quality grade requirement of a preset plate;
step S700: and screening the first plate according to the first plate quality result and the preset plate quality grade requirement.
Specifically, the preset plate quality grade requirement is a qualified standard of plate quality, the required plate quality grade is different according to different applications of the plate, if the surface of the plate is required not to be allowed to have cracks, peeling, bubbles and local mechanical damage, the maximum depth of the defect cannot exceed 0.5mm, and the total area of the defect does not exceed 5% of the total area of the plate. And screening the first plate according to the first plate quality result and the preset plate quality grade requirement so as to ensure that the plate meeting the preset quality standard is accurately and efficiently selected.
As shown in fig. 3, further, step S450 in the embodiment of the present application further includes:
step S451: constructing a first plate defect area model;
step S452: taking the horizontal direction of the first plate defect result as the horizontal coordinate of the model, and taking the vertical direction as the vertical coordinate of the model;
step S453: performing integral calculation on the first plate defect area model to obtain a first plate defect area;
step S454: and if the defect area of the first plate exceeds the preset defect area of the plate, positioning the defect result of the first plate.
Specifically, the defect area model of the first plate is constructed, the defect area of the plate is calculated, the horizontal direction of the defect result of the first plate is taken as the abscissa of the model, the vertical direction is taken as the ordinate of the model, the integral area calculation is carried out on the model, and the defect area of the plate is calculated through an integral infinitesimal calculation. The preset plate defect area is a preset defect area which does not affect the plate quality, if the first plate defect area exceeds the preset plate defect area, the defect area affects the plate quality result, and the position of the plate defect result needs to be positioned. The technical effects that the calculation of the defect area of the plate is more accurate through integral operation, the quality of the plate is accurately controlled and positioned, and the quality screening accuracy of the plate is ensured are achieved.
As shown in fig. 4, further, the embodiment of the present application further includes:
step S810: determining plate category characteristics, plate density characteristics and plate appearance characteristics according to the first image information set;
step S820: obtaining a first plate convolution feature of the plate type features, a second plate convolution feature of the plate density features and a third plate convolution feature of the plate appearance features;
step S830: obtaining a first plate characteristic result according to the first plate convolution characteristic, the second plate convolution characteristic and the third plate characteristic;
step 840: and supplementing the first plate quality result according to the first plate characteristic result.
Particularly, according to the multi-angle image information set of panel, confirm panel classification characteristic, panel density characteristic and panel appearance characteristic, panel classification characteristic is the kind of panel, including solid wood board, big core board, bamboo makeup, density board, decorative board, thin core board, finger joint board, melamine board, waterproof board, gypsum board, cement board, baking finish board, shaving board etc.. The density characteristic of the plate is the density characteristic of the plate, different application ways and different density requirements on the plate are met, and the density of the plate can be obtained through calculation of the mass and the measured volume of the plate. The sheet appearance characteristics are sheet appearance surface characteristics including surface structure, surface smoothness, surface patterns and the like. The convolutional neural network is a deep feedforward neural network with the characteristics of local connection, weight sharing and the like, has a remarkable effect in the field of image and video analysis, such as various visual tasks of image classification, target detection, image segmentation and the like, and is one of the most widely applied models at present. A convolutional neural network, literally comprising two parts: convolution + neural network. The convolution is a feature extractor, and the neural network can be regarded as a classifier. A convolutional neural network is trained, namely a feature extractor (convolution) and a subsequent classifier (neural network) are trained simultaneously. And extracting and classifying the product characteristics through a convolutional neural network to obtain the convolutional characteristics of the corresponding plate type characteristics, the plate density characteristics and the plate appearance characteristics. And obtaining a first plate characteristic result through convolution calculation results of the first plate convolution characteristic, the second plate convolution characteristic and the third plate convolution characteristic, and supplementing the first plate quality result according to the first plate characteristic result. Reach through drawing the panel characteristic to supply the correction to panel quality result, make acquisition of panel characteristic information more accurate reasonable, thereby guarantee the technological effect of the accurate screening of panel quality.
As shown in fig. 5, further, wherein the obtaining a first sheet material characteristic result according to the first sheet material convolution characteristic, the second sheet material convolution characteristic, and the third sheet material characteristic, step S830 in this embodiment of the present application further includes:
step S831: using the plate category characteristic as a first plate characteristic, the plate density characteristic as a second plate characteristic and the plate appearance characteristic as a third plate characteristic;
step S832: performing traversal convolution operation on the first plate convolution feature, the second plate convolution feature, the third plate convolution feature and the third plate feature respectively to obtain a corresponding first convolution result, a corresponding second convolution result and a corresponding third convolution result;
step S833: and carrying out result fusion analysis on the first convolution result, the second convolution result and the third convolution result to obtain a first plate characteristic result.
Specifically, the plate type feature is used as a first plate feature, the plate density feature is used as a second plate feature, and the plate appearance feature is used as a third plate feature, traversal convolution operation is respectively performed on the first plate convolution feature, the first plate feature, the second plate convolution feature, the third plate convolution feature, and the third plate feature, corresponding first convolution result, second convolution result, and third convolution result can be obtained, fusion analysis is performed on the first convolution result, the second convolution result, and the third convolution result, and a first plate feature result is generated, wherein the first plate feature result is a result obtained after feature training is performed through a convolution neural network. The method achieves the technical effect of analyzing the plate characteristics in a convolutional neural network mode, so that the plate characteristic analysis result is more accurate and reasonable, and the accurate screening of the plate quality is ensured.
As shown in fig. 6, further, the embodiment of the present application further includes:
step S910: obtaining the warping height and the curved edge length of the first plate according to the first mechanical contour diagram;
step S920: inputting the warping height and the length of the curved edge of the first plate into a warping degree calculation formula to obtain the warping degree of the first plate;
step S930: and correcting the quality result of the first plate according to the warping degree of the first plate.
Specifically, the buckling deformation of the plate is the result of internal stress release, and if no effective measures are taken in the production process, the basis that the plate cannot eliminate the internal stress is caused, so that the buckling deformation is caused in the environments of pressure bearing, high humidity and the like. And performing surface size smooth analysis on the mechanical contour diagram of the plate to obtain the warping height and the curved edge length of the surface size of the plate, wherein the warping deformation of the plate mainly comprises bow warping, edge bending and warping deformation. Constructing the warp calculation formula: and the warping degree = warping height/length of the curved edge, inputting the warping height and the length of the curved edge of the first plate into a warping degree calculation formula, and obtaining a calculation result of the formula, namely the warping degree of the first plate. And correcting the first plate quality result according to the first plate warping degree, so that the plate quality is analyzed by combining plate warping deformation factors, the plate quality analysis result is more accurate and comprehensive, and the technical effect of efficiently and accurately screening the plate quality is ensured.
To sum up, the plate measuring method and system based on machine vision provided by the embodiment of the application have the following technical effects:
due to the adoption of the method, a first image information set is obtained through the image acquisition device, and the first image information set comprises a multi-angle image set of the first plate; performing size recognition on the first image information set according to the first recognition instruction to obtain first basic size information; performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information; performing defect analysis on the first image information set according to the first analysis instruction to obtain a first plate defect result, and performing position positioning on the first plate defect result; inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result; and screening the first plate according to the first plate quality result and the preset plate quality grade requirement. And then reach and acquire the image through machine vision and carry out automatic measurement judgement to panel, measurement accuracy is high, has improved detection efficiency and detection success rate to guarantee the technical effect of panel quality quick screening.
Example two
Based on the same inventive concept as the sheet material measuring method based on machine vision in the previous embodiment, the present invention further provides a sheet material measuring system based on machine vision, as shown in fig. 8, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain a first image information set through an image acquisition device, where the first image information set includes a multi-angle image set of a first plate;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain a first identification instruction, perform size identification on the first image information set according to the first identification instruction, and obtain first basic size information;
a third obtaining unit 13, where the third obtaining unit 13 is configured to perform plane modeling on the first plate according to the first basic size information, obtain a first mechanical contour diagram, and label the first mechanical contour diagram according to the first basic size information;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to obtain a first analysis instruction, perform defect analysis on the first image information set according to the first analysis instruction, obtain a first plate defect result, and perform position location on the first plate defect result;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to input the first basic size information and the first plate defect result into a plate quality analysis model, and obtain a first plate quality result;
a sixth obtaining unit 16, where the sixth obtaining unit 16 is configured to obtain a predetermined plate quality grade requirement;
a first screening unit 17, wherein the first screening unit 17 is configured to screen the first plate according to the first plate quality result and the predetermined plate quality grade requirement.
Further, the system further comprises:
the first construction unit is used for constructing a plate defect characteristic database through big data;
a seventh obtaining unit, configured to perform image segmentation on the plate image in the first image information set to obtain N pieces of sub-image pixel information;
an eighth obtaining unit, configured to classify the image pixels of each point in the N sub-image pixel information according to the size of the image pixel of each point, so as to obtain image pixel information of each category;
a ninth obtaining unit, configured to perform feature analysis on the pixel information of each type of image, so as to obtain first plate feature information;
a tenth obtaining unit, configured to obtain a first plate defect result by comparing the first plate feature information with the plate defect feature database.
Further, the system further comprises:
the second construction unit is used for constructing a first plate defect area model;
the first coordinate unit is used for taking the horizontal direction of the first plate defect result as the abscissa of the model and taking the vertical direction as the ordinate of the model;
an eleventh obtaining unit, configured to perform integral calculation on the first plate defect area model to obtain a first plate defect area;
the first positioning unit is used for positioning the first plate defect result if the first plate defect area exceeds a preset plate defect area.
Further, the system further comprises:
a first determination unit configured to determine a sheet type feature, a sheet density feature, and a sheet appearance feature according to the first image information set;
a twelfth obtaining unit, configured to obtain a first sheet convolution feature of the sheet category feature, a second sheet convolution feature of the sheet density feature, and a third sheet convolution feature of the sheet appearance feature;
a thirteenth obtaining unit, configured to obtain a first plate feature result according to the first plate convolution feature, the second plate convolution feature, and the third plate feature;
a first supplementing unit for supplementing the first sheet quality result according to the first sheet characteristic result.
Further, the system further comprises:
a first characteristic unit configured to use the plate category characteristic as a first plate characteristic, the plate density characteristic as a second plate characteristic, and the plate appearance characteristic as a third plate characteristic;
a fourteenth obtaining unit, configured to perform traversal convolution operations on the first plate convolution feature and the first plate feature, the second plate convolution feature and the second plate feature, and the third plate convolution feature, and obtain a corresponding first convolution result, a corresponding second convolution result, and a corresponding third convolution result;
a fifteenth obtaining unit, configured to perform result fusion analysis on the first convolution result, the second convolution result, and the third convolution result, so as to obtain a first plate characteristic result.
Further, the system further comprises:
a sixteenth obtaining unit, configured to obtain, according to the first mechanical profile, a warping height and a curved edge length of the first plate material;
a seventeenth obtaining unit, configured to input the warping height and the length of the curved edge of the first plate into a warping degree calculation formula, so as to obtain a warping degree of the first plate;
and the first correcting unit is used for correcting the first plate quality result according to the warping degree of the first plate.
Further, the system further comprises:
a first input unit for inputting the first basic size information and the first sheet defect result as input information to the sheet quality analysis model;
an eighteenth obtaining unit, configured to train the plate quality analysis model to obtain through multiple sets of training data, where each set of training data in the multiple sets of training data includes: the first base size information, the first sheet defect result, and identification information for identifying a first sheet quality result;
a nineteenth obtaining unit, configured to obtain a first output result in the plate quality analysis model, where the first output result includes the first plate quality result.
Various modifications and embodiments of a machine vision-based sheet material measuring method in the first embodiment of fig. 1 are also applicable to a machine vision-based sheet material measuring system in the present embodiment, and a method for implementing a machine vision-based sheet material measuring system in the present embodiment is clear to those skilled in the art from the foregoing detailed description of the machine vision-based sheet material measuring method, so for the brevity of the description, detailed description is omitted here.
In addition, an embodiment of the present invention further provides an electronic device, which includes a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the processes of the method for controlling output data are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition.
Exemplary electronic device
Specifically, referring to fig. 9, an embodiment of the present invention further provides an electronic device, which includes a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, and a user interface 1160.
In an embodiment of the present invention, the electronic device further includes: a computer program stored on the memory 1150 and executable on the processor 1120, the computer program, when executed by the processor 1120, implementing the various processes of the method embodiments of controlling output data described above.
A transceiver 1130 for receiving and transmitting data under the control of the processor 1120.
In embodiments of the invention in which a bus architecture (represented by bus 1110) is used, bus 1110 may include any number of interconnected buses and bridges, with bus 1110 connecting various circuits including one or more processors, represented by processor 1120, and memory, represented by memory 1150.
The bus 1110 may also connect various other circuits such as peripherals, voltage regulators, or power management circuits to provide an interface between the bus 1110 and the transceiver 1130, as is well known in the art. Therefore, the embodiments of the present invention will not be further described.
The transceiver 1130 may be one element or may be multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 1130 receives external data from other devices, and the transceiver 1130 transmits data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as: touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, stylus.
It is to be appreciated that in embodiments of the invention, the memory 1150 may further include memory located remotely with respect to the processor 1120, which may be coupled to a server via a network. One or more portions of the above-described network may be an ad hoc network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless fidelity network, and a combination of two or more of the above. For example, the cellular telephone network and the wireless network may be global mobile communications devices, code division multiple access devices, global microwave interconnect access devices, general packet radio service devices, wideband code division multiple access devices, long term evolution devices, LTE frequency division duplex devices, LTE time division duplex devices, long term evolution advanced devices, universal mobile communications devices, enhanced mobile broadband devices, mass machine type communications devices, ultra-reliable low-latency communications devices, and the like.
It will be appreciated that the memory 1150 in embodiments of the present invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. Wherein the nonvolatile memory includes: read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, or flash memory.
The volatile memory includes: a random access memory that functions as an external cache. By way of example, and not limitation, many forms of RAM are available, such as: static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronous link dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in connection with the embodiments of the invention includes, but is not limited to, the above-described and any other suitable types of memory.
In an embodiment of the present invention, memory 1150 stores the following elements of operating system 1151 and application programs 1152: an executable module, a data structure, or a subset thereof, or an expanded set thereof.
Specifically, the operating system 1151 includes various device programs, such as: a framework layer, a core library layer, a driver layer, etc. for implementing various basic services and processing hardware-based tasks. Applications 1152 include various applications such as: the media player and the browser are used for realizing various application services. Programs that implement methods in accordance with embodiments of the present invention can be included in application programs 1152. The application programs 1152 include: applets, objects, components, logic, data structures, and other computer device-executable instructions that perform particular tasks or implement particular abstract data types.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements each process of the above method for controlling output data, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The above description is only a specific implementation of the embodiments of the present invention, but the scope of the embodiments of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the embodiments of the present invention, and should be covered by the scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method for measuring a sheet material based on machine vision, wherein the method is applied to a sheet material measuring system comprising an image acquisition device, the method comprising:
obtaining a first image information set through the image acquisition device, wherein the first image information set comprises a multi-angle image set of a first plate;
obtaining a first identification instruction, and carrying out size identification on the first image information set according to the first identification instruction to obtain first basic size information;
performing plane modeling on the first plate according to the first basic size information to obtain a first mechanical contour drawing, and labeling the first mechanical contour drawing according to the first basic size information;
obtaining a first analysis instruction, performing defect analysis on the first image information set according to the first analysis instruction to obtain a first plate defect result, and performing position positioning on the first plate defect result;
inputting the first basic size information and the first plate defect result into a plate quality analysis model to obtain a first plate quality result;
obtaining the quality grade requirement of a preset plate;
screening the first plate according to the first plate quality result and the preset plate quality grade requirement;
determining a plate type characteristic, a plate density characteristic and a plate appearance characteristic according to the first image information set;
obtaining a first plate convolution characteristic of the plate type characteristic, a second plate convolution characteristic of the plate density characteristic and a third plate convolution characteristic of the plate appearance characteristic;
obtaining a first plate characteristic result according to the first plate convolution characteristic, the second plate convolution characteristic and the third plate convolution characteristic;
supplementing the first plate quality result according to the first plate characteristic result;
obtaining the warping height and the curved edge length of the first plate according to the first mechanical contour diagram;
inputting the warping height and the length of the curved edge of the first plate into a warping degree calculation formula to obtain the warping degree of the first plate;
and correcting the quality result of the first plate according to the warping degree of the first plate.
2. The machine vision-based sheet material measuring method of claim 1, wherein said performing a defect analysis on said first image information set according to said first analysis instruction to obtain a first sheet material defect result comprises:
constructing a plate defect characteristic database through big data;
performing image segmentation on the plate images in the first image information set to obtain pixel information of N sub-images;
classifying according to the size of each point image pixel in the N sub-image pixel information to obtain each category of image pixel information;
performing characteristic analysis on the pixel information of each type of image to obtain first plate characteristic information;
and comparing the first plate characteristic information with the plate defect characteristic database to obtain a first plate defect result.
3. A machine vision based sheet material measurement method as claimed in claim 2, wherein the method comprises:
constructing a first plate defect area model;
taking the horizontal direction of the first plate defect result as the abscissa of the first plate defect area model, and taking the vertical direction as the ordinate of the first plate defect area model;
performing integral calculation on the first plate defect area model to obtain a first plate defect area;
and if the defect area of the first plate exceeds the preset defect area of the plate, positioning the defect result of the first plate.
4. The machine vision based sheet measurement method of claim 1 wherein said obtaining a first sheet material characteristic result from said first sheet material convolution signature, said second sheet material convolution signature, and said third sheet material convolution signature comprises:
taking the sheet type characteristic as a first sheet characteristic, the sheet density characteristic as a second sheet characteristic and the sheet appearance characteristic as a third sheet characteristic;
performing traversal convolution operation on the first plate convolution feature, the second plate convolution feature, the third plate convolution feature and the third plate feature respectively to obtain a corresponding first convolution result, a corresponding second convolution result and a corresponding third convolution result;
and carrying out result fusion analysis on the first convolution result, the second convolution result and the third convolution result to obtain a first plate characteristic result.
5. The machine vision-based sheet material measurement method of claim 1 wherein said inputting said first base dimensional information and said first sheet material defect result into a sheet material quality analysis model to obtain a first sheet material quality result comprises:
inputting the first basic size information and the first plate defect result into the plate quality analysis model as input information;
the plate quality analysis model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises: the first base size information, the first sheet defect result, and identification information for identifying a first sheet quality result;
and obtaining a first output result in the plate quality analysis model, wherein the first output result comprises the first plate quality result.
6. A machine vision based sheet material measurement system, wherein the system comprises:
a first obtaining unit for obtaining a first image information set through an image acquisition device, the first image information set comprising a multi-angle image set of a first sheet material;
a second obtaining unit, configured to obtain a first identification instruction, perform size identification on the first image information set according to the first identification instruction, and obtain first basic size information;
a third obtaining unit, configured to perform plane modeling on the first plate according to the first basic size information, obtain a first mechanical profile, and label the first mechanical profile according to the first basic size information;
a fourth obtaining unit, configured to obtain a first analysis instruction, perform defect analysis on the first image information set according to the first analysis instruction, obtain a first plate defect result, and perform position location on the first plate defect result;
a fifth obtaining unit, configured to input the first basic size information and the first plate defect result into a plate quality analysis model, and obtain a first plate quality result;
a sixth obtaining unit, configured to obtain a predetermined plate quality grade requirement;
the first screening unit is used for screening the first plate according to the first plate quality result and the preset plate quality grade requirement;
a first determination unit configured to determine a sheet type feature, a sheet density feature, and a sheet appearance feature according to the first image information set;
a twelfth obtaining unit, configured to obtain a first sheet convolution feature of the sheet category features, a second sheet convolution feature of the sheet density features, and a third sheet convolution feature of the sheet appearance features;
a thirteenth obtaining unit, configured to obtain a first plate feature result according to the first plate convolution feature, the second plate convolution feature, and the third plate convolution feature;
the first supplementing unit is used for supplementing the first plate quality result according to the first plate characteristic result;
a sixteenth obtaining unit, configured to obtain, according to the first mechanical profile, a warping height and a curved edge length of the first plate material;
a seventeenth obtaining unit, configured to input the warping height and the length of the curved edge of the first plate into a warping degree calculation formula, and obtain a warping degree of the first plate;
and the first correcting unit is used for correcting the first plate quality result according to the warping degree of the first plate.
7. A machine vision based sheet material measuring electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on and executable on said memory, said transceiver, said memory and said processor being connected via said bus, characterized in that said computer program when executed by said processor performs the steps of a machine vision based sheet material measuring method as claimed in any one of claims 1-5.
8. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in a machine vision-based sheet material measuring method as claimed in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504912.9A CN114199892B (en) | 2021-12-10 | 2021-12-10 | Plate measuring method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504912.9A CN114199892B (en) | 2021-12-10 | 2021-12-10 | Plate measuring method and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114199892A CN114199892A (en) | 2022-03-18 |
| CN114199892B true CN114199892B (en) | 2022-11-18 |
Family
ID=80651991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111504912.9A Active CN114199892B (en) | 2021-12-10 | 2021-12-10 | Plate measuring method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114199892B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564337A (en) * | 2022-10-24 | 2023-01-03 | 南珠建材(清远)有限公司 | Quality evaluation method and system for concrete pipe pile |
| CN115854897A (en) * | 2022-12-27 | 2023-03-28 | 东莞诺丹舜蒲胶辊有限公司 | Rubber roller laser intelligent detection method, device, equipment and medium |
| CN116258947B (en) * | 2023-03-07 | 2023-08-18 | 浙江研几网络科技股份有限公司 | Industrial automatic processing method and system suitable for home customization industry |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107775620A (en) * | 2016-08-28 | 2018-03-09 | 山东智衡减振科技股份有限公司 | A kind of spring blank end mark detection device and mark detection method |
| CN108362703A (en) * | 2017-12-14 | 2018-08-03 | 北京木业邦科技有限公司 | A kind of veneer detection method and detection device based on artificial intelligence |
| CN109916923A (en) * | 2019-04-25 | 2019-06-21 | 广州宁基智能系统有限公司 | A kind of customization plate automatic defect detection method based on machine vision |
| CN113066079A (en) * | 2021-04-19 | 2021-07-02 | 北京滴普科技有限公司 | Method, system and storage medium for automatically detecting wood defects |
| CN113362276A (en) * | 2021-04-26 | 2021-09-07 | 广东大自然家居科技研究有限公司 | Visual detection method and system for plate |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI267737B (en) * | 2004-11-02 | 2006-12-01 | Taiwan Tft Lcd Ass | Method and device for detecting flat panel display device by visual model |
| JP5861462B2 (en) * | 2012-01-17 | 2016-02-16 | オムロン株式会社 | Inspection standard registration method for solder inspection and board inspection apparatus using the method |
| CN105466951B (en) * | 2014-09-12 | 2018-11-16 | 江苏明富自动化科技股份有限公司 | A kind of automatic optical detection device and its detection method |
| CN109964234A (en) * | 2017-02-17 | 2019-07-02 | 欧姆龙株式会社 | Assess the quality of the product of such as semiconductor substrate |
| JP7087397B2 (en) * | 2018-01-17 | 2022-06-21 | 東京エレクトロン株式会社 | Substrate defect inspection equipment, substrate defect inspection method and storage medium |
| US10679333B2 (en) * | 2018-03-14 | 2020-06-09 | Kla-Tencor Corporation | Defect detection, classification, and process window control using scanning electron microscope metrology |
| US11842472B2 (en) * | 2020-03-31 | 2023-12-12 | International Business Machines Corporation | Object defect correction |
| CN111912856A (en) * | 2020-07-30 | 2020-11-10 | 北京首钢股份有限公司 | Plate and strip surface defect analysis system |
| CN112102254A (en) * | 2020-08-21 | 2020-12-18 | 佛山职业技术学院 | Wood surface defect detection method and system based on machine vision |
-
2021
- 2021-12-10 CN CN202111504912.9A patent/CN114199892B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107775620A (en) * | 2016-08-28 | 2018-03-09 | 山东智衡减振科技股份有限公司 | A kind of spring blank end mark detection device and mark detection method |
| CN108362703A (en) * | 2017-12-14 | 2018-08-03 | 北京木业邦科技有限公司 | A kind of veneer detection method and detection device based on artificial intelligence |
| CN109916923A (en) * | 2019-04-25 | 2019-06-21 | 广州宁基智能系统有限公司 | A kind of customization plate automatic defect detection method based on machine vision |
| CN113066079A (en) * | 2021-04-19 | 2021-07-02 | 北京滴普科技有限公司 | Method, system and storage medium for automatically detecting wood defects |
| CN113362276A (en) * | 2021-04-26 | 2021-09-07 | 广东大自然家居科技研究有限公司 | Visual detection method and system for plate |
Non-Patent Citations (1)
| Title |
|---|
| 基于多光源照明的低对比度冲压字符识别算法研究;张建峰;《中国优秀硕士学位论文全文数据库信息科技辑》;20180615(第6期);第I138-1430页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114199892A (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114199892B (en) | Plate measuring method and system based on machine vision | |
| CN114994061B (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN110610061B (en) | Concrete slump high-precision prediction method fusing multi-source information | |
| KR20200081340A (en) | Method and apparatus for architectural drawing analysing | |
| CN112613097A (en) | BIM rapid modeling method based on computer vision | |
| JP6920972B2 (en) | Method for optimizing simulation conditions, manufacturing process simulation equipment, manufacturing process simulation system and program | |
| CN109226282B (en) | Steel plate on-line solid solution post-rolling rapid cooling method based on Internet of things | |
| US10670515B2 (en) | Detecting edge cracks | |
| CN114638486A (en) | Steel pipe quality tracing method and system based on intelligent identification and recognition system | |
| CN107194432B (en) | Refrigerator door body identification method and system based on deep convolutional neural network | |
| CN110837782B (en) | Method for identifying fracture information according to material stretching process monitoring video | |
| Cui et al. | Real-time detection of wood defects based on SPP-improved YOLO algorithm | |
| CN113421174A (en) | Intellectual property value evaluation reference method and system based on big data | |
| CN110490165B (en) | Dynamic gesture tracking method based on convolutional neural network | |
| KR20220052798A (en) | Method for generating image data for machine learning and apparatus thereof | |
| CN101799925B (en) | Performance analysis method for automatic segmentation result of image | |
| TW202333014A (en) | Systems and methods for manufacturing processes | |
| Kuo et al. | An integrated curvature surface inspection and prediction system for 5-axis synchronization machining | |
| CN113744198B (en) | Bidirectional positioning method and system for processing waste products of injection needles | |
| Song et al. | A Digital Twin Model for Automatic Width Control of Hot Rolling Mill | |
| CN117591283B (en) | Cloud cutting equipment management method and system based on cross-platform data fusion | |
| CN113112515B (en) | Evaluation method for pattern image segmentation algorithm | |
| CN107908832B (en) | Air conditioning system model identification and conversion method and terminal equipment | |
| Mawas et al. | Filament Extraction in 3D Printing of Shotcrete Walls from Terrestrial Laser Scanner Data | |
| CN114494741A (en) | CAD plan layout house type comparison method based on improved Purchase analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221122 Address after: 226001 202, Building 8, Yingnuoyuan Science Park, No. 2, Panxiang Road, Nantong Development Zone, Jiangsu Province Patentee after: Nantong Hongxin Intelligent Technology Co.,Ltd. Address before: Room 407, No. 72, Waihuan West Road, Chongchuan District, Nantong City, Jiangsu Province, 226000 Patentee before: Jiangsu Raymer Intelligent Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |