CN211505244U - Cement substrate pore structure image acquisition, recognition and analysis equipment - Google Patents
Cement substrate pore structure image acquisition, recognition and analysis equipment Download PDFInfo
- Publication number
- CN211505244U CN211505244U CN202020072975.6U CN202020072975U CN211505244U CN 211505244 U CN211505244 U CN 211505244U CN 202020072975 U CN202020072975 U CN 202020072975U CN 211505244 U CN211505244 U CN 211505244U
- Authority
- CN
- China
- Prior art keywords
- microscope
- image acquisition
- vertical rod
- light source
- support
- 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.)
- Expired - Fee Related
Links
- 239000011148 porous material Substances 0.000 title claims abstract description 34
- 239000004568 cement Substances 0.000 title claims abstract description 23
- 239000000758 substrate Substances 0.000 title claims abstract description 14
- 238000004458 analytical method Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims description 23
- 238000001514 detection method Methods 0.000 abstract description 26
- 238000013461 design Methods 0.000 abstract description 4
- 238000002360 preparation method Methods 0.000 abstract description 2
- 239000000463 material Substances 0.000 description 12
- 230000011218 segmentation Effects 0.000 description 12
- 238000012360 testing method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 3
- 229910052753 mercury Inorganic materials 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007493 shaping process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000009435 building construction Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Abstract
The utility model discloses a cement substrate pore structure image acquisition, discernment and analytical equipment, the utility model discloses the device includes: carry appearance system and image acquisition system, wherein, carry appearance system by workstation, 2 vertical slip tables, horizontal slip table, put the thing platform and constitute, image acquisition system comprises vertical pole, 2 clamps, micro-support, microscope, camera, gimbal mount, universal flexible cantilever support, light source. The utility model discloses the advantage can be according to the position of adjustment sample, light source, microscope, camera to in carrying out sample image sample, utilize the degree of depth learning system to carry out the analysis, carry out preliminary treatment, concrete feature mark, preparation label set, acquire characteristic detection model parameter, analysis to the image sample, finally obtain the pore characteristic. The utility model provides a structural design is reasonable, easy operation, detection efficiency are high and can reduce the cement substrate pore structure image acquisition, discernment and analytical equipment who detects the cost effectively.
Description
Technical Field
The utility model relates to a material check out test set field, concretely relates to cement substrate pore structure image acquisition, discernment and analytical equipment.
Background
In the field of building materials, the pore characteristics of concrete are closely related to the macroscopic performance of concrete, so that the method plays an important role in the research and quality detection of concrete materials, and the measurement and determination of the pore structure of a cement base material have an important significance in determining the concrete properties, thereby ensuring the reliable quality and reliability of building construction.
At present, the pore structure testing technology for cement-based materials mainly adopts a traditional analytical instrument to determine the structure of the material, extracts the pore characteristics of concrete, analyzes and calculates the pore size distribution and the porosity of the concrete, provides a reference basis for researching the macroscopic performance of the concrete, and conjectures the overall performance of the material from the local pore structure characteristics, mainly according to the stereological theory.
The current common pore structure testing technologies mainly comprise: mercury intrusion method, nitrogen adsorption method, electron microscope scanning method, image binarization method, etc. For example: a method (CN201810108085.3) for predicting the elastic modulus of a cement-based material based on a mercury intrusion test comprises the steps of obtaining a cement-based material sample, carrying out a mercury intrusion test on the dried sample, calculating the relation between the accumulated porosity and the pore diameter, converting the accumulated porosity into relative compactness, representing the relative compactness and the pore diameter in a log-log coordinate system, determining a region in which the relative compactness and the pore diameter are linearly related, obtaining the slope of the region in which the relative compactness and the pore diameter are linearly related, and determining characteristic parameters of a porous structure of the cement-based material according to the range and the slope of the linear correlation; a cement concrete hole structure characteristic analysis system and a test method (CN201710943670.0) thereof are disclosed, wherein the early stage significant black and white distinguishing treatment is carried out on a cement concrete section, the distribution rule of cement concrete inner holes is clearly identified, and the number, the size and the distribution condition of air outlet holes are rapidly and simply calculated by adopting a digital image method. The methods and the technologies realize the measurement of the pore structure of the cement base material to a certain extent, but the methods have the defects of more or less complex sample preparation process, too much time consumption for a large amount of tests, incapability of visually acquiring the pore structure characteristics and the like, and are difficult to accurately, quickly and massively detect the pore characteristics of the concrete.
In summary, although the improvement measures for improving the heat exchange performance actually play a role to a great extent at present, some problems also exist, so that the defects and shortcomings of the prior art need to be overcome, and the cement base material hole structure detection equipment and the corresponding method which are reasonable in structural design, simple to operate, high in detection efficiency and capable of effectively reducing the detection cost are provided.
SUMMERY OF THE UTILITY MODEL
The utility model aims at solving and absorbing the process that has existence in the cement substrate pore structure detection technology complicated, consuming time many, the problem that detection efficiency is low, provide a structural design is reasonable, easy operation, detection efficiency height and can reduce the cement substrate pore structure image acquisition, discernment and analytical equipment who detects the cost effectively.
The utility model discloses the technical scheme who adopts: the utility model discloses a device includes: the device comprises a sample carrying system and an image acquisition system, wherein the sample carrying system consists of a workbench, 2 longitudinal sliding tables, a transverse sliding table and an object placing table; the image acquisition system consists of a vertical rod, 2 hoops, a microscope bracket, a microscope, a camera, a universal bracket support, a universal telescopic cantilever bracket and a light source; 2 longitudinal sliding tables are arranged on the upper end face of the workbench in parallel, and a vertical rod is arranged on the edge of the upper end face of the workbench; the number of the longitudinal sliding tables is 2, the longitudinal sliding tables are fixedly arranged on the upper end surface of the workbench, and the longitudinal sliding tables are provided with transverse sliding tables; the transverse sliding table is arranged on the longitudinal sliding table, is perpendicular to the longitudinal sliding table and is arranged in an I shape, and the transverse sliding table is provided with an object placing table; the object placing table is arranged on the transverse changing table; the vertical rod is arranged at the edge of the upper end surface of the workbench, and 2 clamps, micro-brackets and universal bracket supports are arranged on the vertical rod; the number of the clamps is 2, and the clamps are respectively arranged at the lower part and the middle part of the vertical rod; the microscope support is arranged on the vertical rod and is positioned above the hoop in the middle of the vertical rod, one end of the microscope support is connected with the vertical rod, and the other end of the microscope support is a ferrule and is connected with the microscope; the microscope is connected with one end of the microscope bracket with the ferrule, and the eyepiece end of the microscope is connected with the front end of the lens of the camera through mutually embedded threads; the camera is positioned above the microscope, and a lens of the camera is connected with an eyepiece end of the microscope through mutually embedded threads; the universal frame support is arranged on the vertical rod and is positioned above the hoop at the lower part of the vertical rod and below the hoop at the middle part of the vertical rod, and a universal telescopic cantilever support is arranged on the upper end surface of the universal frame support; one end of the universal telescopic cantilever support is arranged on the upper surface of the universal support seat, and the other end of the universal telescopic cantilever support is a free end and is connected with the light source; the light source is connected with the free end of the universal telescopic cantilever support.
Furthermore, the longitudinal sliding table and the transverse sliding table are ball screw stepping motor sliding tables.
Further, put thing platform up end and be the square, be provided with the size and be 11 cm's positioning groove, and put thing platform four sides middle part and respectively set up the fixed buckle of sample.
Furthermore, the light source is a zero-degree annular light source of mechanical vision, the annular light source with the size of 0 degree of irradiation angle and the inner diameter of 100mm is adopted, the center of a light source plane is arranged at the axial line of the microscope and the camera during image acquisition, the distance between the light source plane and a sample plane is controlled to be 1-2 mm, and the light source can enable the substrate and the pores to form sharp contrast to distinguish the two.
A method for acquiring, identifying and analyzing a cement substrate hole structure image adopts a deep learning system, and comprises the following specific implementation steps:
step (I): the sample is placed on the object placing table, the positions of the object placing table, the light source, the microscope and the camera are adjusted, the sample is observed, the image sample of the sample is collected through the camera, the collected image sample is sent to an upper computer to be stored, and the number of the image samples is at least 1 ten thousand.
Step (II): preprocessing an image sample, using rapid guide filtering to the acquired concrete section image sample, using a down-sampling method to obtain an input graph and a guide graph required in the guide filtering so as to process the image sample, then averaging the obtained images, and then normalizing.
Step (three): the method comprises the steps of marking concrete features in an image sample respectively, manufacturing a label set corresponding to the image sample, wherein the concrete features comprise aggregates, normal pores and communicated pores, and the label set manufacturing comprises example marking, label classification and storage of the concrete features.
Step (IV): and (3) performing offline learning, training and generating concrete characteristic detection model parameters adaptive to online use through a convolutional neural network.
Step (V): and sending the concrete characteristic detection model parameters obtained by successful training to an upper computer for automatic on-line machine identification, segmentation and statistics of the pore characteristics in the concrete sample.
Further, the step (iv) includes the following substeps: adopting a characteristic image pyramid algorithm to compress or amplify the image to form pictures with different dimensions as model input, and performing convolution characteristic extraction on the pictures with different dimensions or different scales and sizes to obtain a characteristic set capable of reflecting multi-dimensional information; enhancing the feature set of each dimension obtained by the feature image pyramid algorithm by adopting a bottom-up path, namely transmitting the strong positioning feature of the low-dimension layer to the high-dimension layer through the feature image pyramid algorithm; carrying out region feature aggregation operation on each dimension feature enhanced by the bottom-up path by using a RegionOfInterestalign method; and then carrying out feature fusion on the obtained full-connection layer of each dimension, and shaping the fused full-connection layer to obtain concrete feature detection model parameters.
Further, the step (five) includes the following substeps: inputting an image to be detected, inputting the whole image into a concrete characteristic detection model, and extracting characteristics; generating an example segmentation mask image by using a concrete feature detection model, wherein the example segmentation mask image comprises an original image, a prediction example segmentation mask and a prediction classification label; and classifying, counting and calculating the characteristic regions obtained by segmentation in the example segmentation mask image to obtain concrete section quantitative information.
The utility model has the advantages that: (1) compared with the common light source, the zero-degree annular light source can form the sharp contrast between the material matrix and the pores when being irradiated on the concrete, has better effect than the common light source, more accurate detection and analysis result and higher efficiency; (2) the deep learning system is adopted for detection and analysis, so that the pretreatment of a sample is reduced, the detection operation is greatly simplified, the detection time is saved, and the detection is quicker; (3) the utility model consists of a carrying system and an image acquisition system, wherein the arrangement of each device is clear at a glance, the structure is simple and clear, the function exertion is not influenced, and the structural design is reasonable; (4) the device of the utility model is simple, has no special equipment, has concise and clear using and operating steps, can freely change the relative positions of the light source, the sample, the microscope and the camera as required through the ingenious cooperation among all the parts, simplifies the process flow, has simple operation and low cost, and also improves the detection efficiency; (5) the utility model is simple in operation, the image sample is swift, and the analysis step is succinct, therefore save time, detection efficiency is high.
Drawings
Fig. 1 is a schematic view of the overall structure of the present invention.
Fig. 2 to 7 are schematic views of the partial structure of the present invention.
In the figure: 1-workstation, 2 vertical slip table one, 3 vertical slip table two, 4 horizontal slip table, 5 put the thing platform, 6-vertical pole, 7 clamp one, 8 clamp two, 9-microsupport, 10-microscope, 11-camera, 12-gimbal support, 13-universal flexible cantilever support, 14-light source.
The specific implementation mode is as follows:
the present invention will be described in detail with reference to the accompanying drawings and specific examples.
As shown in the figure, the utility model discloses a device includes: the sample carrying system comprises a working table 1, a longitudinal sliding table I2, a longitudinal sliding table II 3, a transverse sliding table 4 and an object placing table 5; the image acquisition system consists of a vertical rod 6, a first hoop 7, a second hoop 8, a micro-bracket 9, a microscope 10, a camera 11, a universal bracket support 12, a universal telescopic cantilever bracket 13 and a light source 14; the upper end face of the workbench 1 is provided with a first longitudinal sliding table 2 and a second longitudinal sliding table 3 in parallel, and the edge of the upper end face of the workbench 1 is provided with a vertical rod 6; the longitudinal sliding table I2 and the longitudinal sliding table II 3 are fixedly arranged on the upper end surface of the workbench 1, and the longitudinal sliding table I2 and the longitudinal sliding table II 3 are provided with transverse sliding tables 4; the transverse sliding table 4 is arranged on the first longitudinal sliding table 2 and the second longitudinal sliding table 3, is perpendicular to the first longitudinal sliding table 2 and the second longitudinal sliding table 3, and is arranged in an I shape, and the transverse sliding table 4 is provided with an object placing table 5; the object placing table 5 is arranged on the transverse changing table 4; the vertical rod 6 is arranged on the edge of the upper end face of the workbench 1, and a first hoop 7, a second hoop 8, a micro-bracket 9 and a universal bracket support 12 are arranged on the vertical rod 6; the first hoop 7 and the second hoop 8 are respectively arranged at the middle part and the lower part of the vertical rod 6; the microscope support 9 is arranged on the vertical rod 6 and is positioned above the first hoop 7, one end of the microscope support 9 is connected with the vertical rod 6, and the other end of the microscope support is provided with a ferrule and is connected with the microscope 10; the microscope 10 is connected with one end of the microscope support 9 with a ferrule, and the eyepiece end of the microscope 10 is connected with the front end of the lens of the camera 11 through threads which are mutually embedded; the camera 11 is positioned above the microscope 10, and the lens of the camera 11 is connected with the eyepiece end of the microscope 10 through mutually embedded threads; the universal frame support 12 is arranged on the vertical rod 6 and is positioned above the hoop II 8 and below the hoop I7, and a universal telescopic cantilever support 13 is arranged on the upper end face of the universal frame support 12; one end of the universal telescopic cantilever support 13 is arranged on the upper surface of the universal frame support 12, and the other end of the universal telescopic cantilever support 13 is a free end and is connected with the light source 14; the light source 14 is connected to the free end of the gimbal arm 13.
Furthermore, the longitudinal sliding table I2, the longitudinal sliding table II 3 and the transverse sliding table 4 are ball screw stepping motor sliding tables.
Further, put 5 up end of thing platform for the square, be provided with the size for 11 cm's positioning groove, and put 5 four sides middle parts of thing platform and respectively set up the fixed buckle of sample.
Further, the light source 14 is a machine vision zero-degree annular light source, an annular light source with the size of 0 degree of irradiation angle and the inner diameter of 100mm is adopted, the center of the plane of the light source 14 is arranged at the axial line of the microscope 10 and the camera 11 when image acquisition is carried out, and the distance between the center and the sample plane is controlled to be 1-2 mm.
A method for acquiring, identifying and analyzing a cement substrate hole structure image adopts a deep learning system, and comprises the following specific implementation steps:
step (I): the sample is placed on the object placing table 5, the positions of the object placing table 5, the light source 14, the microscope 10 and the camera 11 are adjusted, the sample is observed, the sample image is collected through the camera 11, the collected sample image is sent to an upper computer to be stored, and at least 1 ten thousand sample images are obtained.
Step (II): preprocessing an image sample, using rapid guide filtering to the acquired concrete section image sample, using a down-sampling method to obtain an input graph and a guide graph required in the guide filtering so as to process the image sample, then averaging the obtained images, and then normalizing.
Step (three): the method comprises the steps of marking concrete features in an image sample respectively, manufacturing a label set corresponding to the image sample, wherein the concrete features comprise aggregates, normal pores and communicated pores, and the label set manufacturing comprises example marking, label classification and storage of the concrete features.
Step (IV): and (3) performing offline learning, training and generating concrete characteristic detection model parameters adaptive to online use through a convolutional neural network.
Step (V): and sending the concrete characteristic detection model parameters obtained by successful training to an upper computer for automatic on-line machine identification, segmentation and statistics of the pore characteristics in the concrete sample.
Further, the step (iv) includes the following substeps: adopting a characteristic image pyramid algorithm to compress or amplify the image to form pictures with different dimensions as model input, and performing convolution characteristic extraction on the pictures with different dimensions or different scales and sizes to obtain a characteristic set capable of reflecting multi-dimensional information; enhancing the feature set of each dimension obtained by the feature image pyramid algorithm by adopting a bottom-up path, namely transmitting the strong positioning feature of the low-dimension layer to the high-dimension layer through the feature image pyramid algorithm; carrying out region feature aggregation operation on each dimension feature enhanced by the bottom-up path by using a RegionOfInterestalign method; and then carrying out feature fusion on the obtained full-connection layer of each dimension, and shaping the fused full-connection layer to obtain concrete feature detection model parameters.
Further, the step (five) includes the following substeps: inputting an image to be detected, inputting the whole image into a concrete characteristic detection model, and extracting characteristics; generating an example segmentation mask image by using a concrete feature detection model, wherein the example segmentation mask image comprises an original image, a prediction example segmentation mask and a prediction classification label; and classifying, counting and calculating the characteristic regions obtained by segmentation in the example segmentation mask image to obtain concrete section quantitative information.
The above embodiments are merely preferred embodiments of the present invention, and it should be noted that, for those skilled in the art, a plurality of modifications and improvements can be made without departing from the concept or principle of the present invention, and all of them belong to the protection scope of the present invention.
Claims (4)
1. The utility model provides a cement substrate pore structure image acquisition, discernment and analytical equipment which characterized in that: the method comprises the following steps: the device comprises a sample carrying system and an image acquisition system, wherein the sample carrying system consists of a workbench, 2 longitudinal sliding tables, a transverse sliding table and an object placing table; the image acquisition system consists of a vertical rod, 2 hoops, a microscope bracket, a microscope, a camera, a universal bracket support, a universal telescopic cantilever bracket and a light source; 2 longitudinal sliding tables are arranged on the upper end face of the workbench in parallel, and a vertical rod is arranged on the edge of the upper end face of the workbench; the number of the longitudinal sliding tables is 2, the longitudinal sliding tables are fixedly arranged on the upper end surface of the workbench, and the longitudinal sliding tables are provided with transverse sliding tables; the transverse sliding table is arranged on the longitudinal sliding table, is perpendicular to the longitudinal sliding table and is arranged in an I shape, and the transverse sliding table is provided with an object placing table; the object placing table is arranged on the transverse changing table; the vertical rod is arranged at the edge of the upper end surface of the workbench, and 2 clamps, micro-brackets and universal bracket supports are arranged on the vertical rod; the number of the clamps is 2, and the clamps are respectively arranged at the lower part and the middle part of the vertical rod; the microscope support is arranged on the vertical rod and is positioned above the hoop in the middle of the vertical rod, one end of the microscope support is connected with the vertical rod, and the other end of the microscope support is a ferrule and is connected with the microscope; the microscope is connected with one end of the microscope bracket with the ferrule, and the eyepiece end of the microscope is connected with the front end of the lens of the camera through mutually embedded threads; the camera is positioned above the microscope, and a lens of the camera is connected with an eyepiece end of the microscope through mutually embedded threads; the universal frame support is arranged on the vertical rod and is positioned above the hoop at the lower part of the vertical rod and below the hoop at the middle part of the vertical rod, and a universal telescopic cantilever support is arranged on the upper end surface of the universal frame support; one end of the universal telescopic cantilever support is arranged on the upper surface of the universal support seat, and the other end of the universal telescopic cantilever support is a free end and is connected with the light source; the light source is connected with the free end of the universal telescopic cantilever support.
2. The cement substrate pore structure image acquisition, identification and analysis device of claim 1, wherein: the longitudinal sliding table and the transverse sliding table are ball screw stepping motor sliding tables.
3. The cement substrate pore structure image acquisition, identification and analysis device of claim 1, wherein: put thing platform up end and be the square, be provided with the size for 11 cm's positioning groove, and put thing platform four sides middle part and respectively set up the fixed buckle of sample.
4. The cement substrate pore structure image acquisition, identification and analysis device of claim 1, wherein: the light source is a machine vision zero-degree annular light source, the annular light source with the size of 0 degree of irradiation angle and the inner diameter of 100mm is adopted, the center of a light source plane is arranged at the axis of the microscope and the camera when image acquisition is carried out, and the distance between the light source plane and a sample plane is controlled to be 1-2 mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020072975.6U CN211505244U (en) | 2020-01-14 | 2020-01-14 | Cement substrate pore structure image acquisition, recognition and analysis equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020072975.6U CN211505244U (en) | 2020-01-14 | 2020-01-14 | Cement substrate pore structure image acquisition, recognition and analysis equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN211505244U true CN211505244U (en) | 2020-09-15 |
Family
ID=72400014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020072975.6U Expired - Fee Related CN211505244U (en) | 2020-01-14 | 2020-01-14 | Cement substrate pore structure image acquisition, recognition and analysis equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN211505244U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112179902A (en) * | 2020-09-29 | 2021-01-05 | 中材海外工程有限公司 | Cement quality detection method and cement quality detection system |
| CN112927184A (en) * | 2021-01-15 | 2021-06-08 | 重庆交通大学 | Self-compacting concrete performance detection method and device based on deep learning |
-
2020
- 2020-01-14 CN CN202020072975.6U patent/CN211505244U/en not_active Expired - Fee Related
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112179902A (en) * | 2020-09-29 | 2021-01-05 | 中材海外工程有限公司 | Cement quality detection method and cement quality detection system |
| CN112927184A (en) * | 2021-01-15 | 2021-06-08 | 重庆交通大学 | Self-compacting concrete performance detection method and device based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN211505244U (en) | Cement substrate pore structure image acquisition, recognition and analysis equipment | |
| CN108956645A (en) | A kind of the optical mirror slip defect detecting device and method of more vision systems | |
| CN101782527B (en) | Full-automatic fracture image analyzer | |
| CN102636496B (en) | Defect width calibration standardizing method in optical surface defect dark field detection | |
| CN1760437A (en) | Automatic system for assessing grade of cloth inspection objectively | |
| CN101424645A (en) | Soldered ball surface defect detection device and method based on machine vision | |
| CN111462075B (en) | Rapid refocusing method and system for full-slice digital pathological image fuzzy region | |
| CN111340798A (en) | Application of deep learning in product appearance flaw detection | |
| CN103499301A (en) | Bast-fiber fineness automatic analyzer and application thereof | |
| CN111626333A (en) | Intelligent detection equipment and method for cement substrate hole structure | |
| CN111855578B (en) | Pathological section scanner | |
| CN112730326A (en) | Intelligent identification device and method for rock slices | |
| CN111579466B (en) | Household sperm detection device and detection method | |
| CN111795894A (en) | Non-contact type method and system for measuring large deformation of uniaxial stretching of high polymer plastic material | |
| CN113935971A (en) | Method and device for detecting surface defects of composite material | |
| CN113155814A (en) | Portable colorimetric array image acquisition device based on optical fiber array and detection method | |
| US20070103668A1 (en) | System, method and apparatus for fiber sample preparation for image analysis | |
| AU2020207942B2 (en) | Printed coverslip and slide for identifying reference focal plane for light microscopy | |
| CN104483317A (en) | High-throughput digital full-field metallographic in-situ statistic characterization analyzer and analysis method | |
| CN112964732A (en) | Spinning cake defect visual detection system and method based on deep learning | |
| CN109410210B (en) | Commodity bar code printing quality detection method based on machine vision | |
| CN101788503B (en) | Bare chip defect detecting system for detecting defects at back face of bare chip and using method thereof | |
| CN114219780A (en) | Deep learning-based method for detecting and segmenting nail fold microcirculation blood vessel | |
| CN211825761U (en) | Rolled glass defect detection device | |
| CN209840969U (en) | Adsorption type standard rod aperture measuring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200915 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |