CN117252809A - Identification system and method based on AI industrial vision - Google Patents
Identification system and method based on AI industrial vision Download PDFInfo
- Publication number
- CN117252809A CN117252809A CN202310955155.XA CN202310955155A CN117252809A CN 117252809 A CN117252809 A CN 117252809A CN 202310955155 A CN202310955155 A CN 202310955155A CN 117252809 A CN117252809 A CN 117252809A
- Authority
- CN
- China
- Prior art keywords
- value
- standard
- image
- pixel
- pixel points
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000007547 defect Effects 0.000 claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000002950 deficient Effects 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 description 6
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an identification system and a method based on AI industrial vision, which relate to the technical field of image vision identification, wherein a standard analysis module is used for obtaining pixel values on a standard surface image of a preset model, processing the pixel values to obtain standard deviation and standard value, setting a value range for the pixel values according to the standard deviation and the standard value, taking the pixel values as the standard range, a defect judgment module is used for judging the pixel values in a detection surface image according to the standard range, selecting an azimuth image in a feature model and taking the azimuth image as a target image, comparing the pixel values in the target image with the standard range to obtain abnormal pixel points, judging positions among the abnormal pixel points to obtain defect positions, and marking a product corresponding to the defect positions as a defect product.
Description
Technical Field
The invention belongs to the technical field of image visual recognition, and particularly relates to a recognition system and a recognition method based on AI industrial vision.
Background
Patent publication number CN115937097a discloses an artificial intelligence based industrial robot visual image recognition system comprising: the definition detection module is used for judging whether the imaging definition meets the standard or not and outputting a judging result; the detection unit is used for detecting the imaging module and periodically forming detection information; the first processing unit acquires the evaluation value and outputs a corresponding control strategy; the control unit carries out self-checking on the imaging module according to the output control strategy, judges whether the imaging module has fault characteristics, retrieves by the second processing unit, outputs corresponding response schemes and is executed by the third processing unit; if not, an alarm is issued by the third processing unit. When the imaging module generates internal faults, the imaging module is subjected to self-checking, the generated faults are judged, corresponding solutions are determined, an alarm is sent to a user, the maintenance efficiency of the user is improved, and the maintenance module is quickly restored to a working state.
In industrial production, because the product is all produced and handled for automation equipment, at this moment the product can exist because the unstable defect that causes of equipment in the in-process of carrying out automation treatment, need the manual work to carry out again to the quality of product and control, have caused the waste to the manpower resource.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art; therefore, the invention provides an identification system and a method based on AI industrial vision, which are used for solving the technical problems.
To achieve the above object, an embodiment according to a first aspect of the present invention proposes an AI-industrial vision-based recognition system including:
the product operation module is used for operating the product to be detected, generating a transmission signal and transmitting the transmission signal to the image acquisition module;
the image acquisition module is used for acquiring a product image in the detection area according to the transmission signal and transmitting the acquired product image to the real-time model generation module, wherein the product image comprises a front image, a left side image and a right side image;
the real-time model generation module is used for combining the product image with the preset model to generate a characteristic model, and then the real-time model generation module respectively transmits the preset model and the characteristic model to the standard analysis module, wherein the appearance characteristic on the preset model is set as the image characteristic of the standard product, and the image characteristic of the standard product is marked as the standard surface;
the standard analysis module is used for obtaining the pixel value in the standard surface on the preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, and transmitting the value range to the defect judgment module as the standard range;
the defect judging module is used for judging the pixel value in the detection surface image according to the standard range, selecting one azimuth image in the feature model and using the azimuth image as a target image, comparing the pixel value in the target image with the standard range to obtain abnormal pixel points, judging the positions among the abnormal pixel points to obtain defect positions, marking a product corresponding to the defect positions as a defect product, and generating an alarm signal to be transmitted to the reminding module;
and the reminding module is used for generating prompt information according to the alarm signal and transmitting the prompt information to related management personnel.
Preferably, the standard deviation and the standard value are obtained by respectively:
s1: all pixel values Xa of the standard surface are obtained, a=1, 2, 3, … … and a1 are expressed that a1 pixel points exist, variance is calculated on the pixel values Xa, and a formula is adoptedObtaining the variance sigma of the pixel value 2 At the same time make the variance sigma 2 Performing root processing to obtain a standard deviation sigma, wherein Xaa is the average value of pixel values Xa;
s2: obtaining the maximum value Xd and the minimum value Xx in the pixel values, and adopting a formulaObtaining a spacing distance D, wherein m is a preset value;
s3: then dividing the pixel value into m-1 interval regions according to the interval distance D, namely dividing the pixel value into [ X1, X2 ], [ X2, X3), … …, [ X (m-1), xm ], wherein Xm-X (m-1) =D according to the maximum value and the minimum value;
s4: the pixel values in the detection surface are corresponding to the interval areas, the number of the pixel points in each interval area is obtained, and the number of the pixel points in the interval area is divided by the total number of the pixel points to obtain a probability value Pa of the pixel points in the corresponding interval area;
s5: then adopt the formulaAnd obtaining a standard value mu of the standard surface, wherein Pa is a corresponding probability value in the interval region where the pixel value Xa is located.
Preferably, the method for obtaining the standard range according to the standard deviation and the standard value comprises the following steps:
the pixel value is respectively set to an upper limit value and a lower limit value according to the standard value mu and the standard deviation sigma, namely, the value range of the pixel value is set to [ mu-2sigma, mu+2sigma ], and then the value range of the pixel value is set to be the standard range of the pixel value.
Preferably, the abnormal pixel point is obtained by the following steps:
ST1: firstly, selecting an azimuth image in a product image according to the shape of the feature model, and marking the selected image as a target image;
ST2: acquiring all pixel points in a target image, establishing a two-dimensional rectangular coordinate system by taking the lower left corner in the target image as an origin, and then carrying out position marking on the pixel points according to the positions of the pixel points in the rectangular coordinate system;
ST3: and comparing the value of the pixel point in the target image with a standard range, and marking the pixel point as an abnormal pixel point when the value of the pixel point does not belong to the standard range.
Preferably, the method for judging the defect position comprises the following steps:
and acquiring the position relation among the abnormal pixel points, selecting the position of one pixel point, taking the position as a starting point, and marking the position among the abnormal pixel points as a defect position when the positions of Y abnormal pixel points are adjacent and uninterrupted.
Preferably, another method for judging the defect position is as follows:
when the positions among the abnormal pixel points are discontinuous, obtaining probability values of the abnormal pixel points in the preset area, namely respectively obtaining the number of the abnormal pixel points and the number of all the pixel points in the preset area, dividing the number of the abnormal pixel points by the number of all the pixel points to obtain the probability values of the abnormal pixel points, and marking the corresponding preset area as a defect position when the probability values of the abnormal pixel points are larger than a preset value YS.
Preferably, the system further comprises a repair module for repairing the position of the defective product, wherein the repair module is used for receiving the transmitted information of the defect judging module, repairing the position of the defect in the defective product, and then placing the repaired product into the product operation module.
An AI-industrial vision-based identification method, comprising:
step one: firstly, carrying out image acquisition on a product to be detected, and generating a real-time model;
step two: firstly, obtaining a pixel value on a standard surface image of a preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, and taking the value range as a standard range;
step three: judging pixel values in the detection surface image according to the standard range, selecting one azimuth image in the feature model, taking the azimuth image as a target image, comparing the pixel values in the target image with the standard range to obtain abnormal pixel points, judging positions among the abnormal pixel points to obtain defect positions, marking a product corresponding to the defect positions as a defect product, and generating an alarm signal;
step four: and generating prompt information according to the alarm signal and transmitting the prompt information to related management personnel.
Compared with the prior art, the invention has the beneficial effects that: obtaining a pixel value on a standard surface image of a preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, taking the pixel value as the standard range, judging the pixel value in a detection surface image according to the standard range, selecting one azimuth image in a feature model, taking the azimuth image as a target image, comparing the pixel value in the target image with the standard range to obtain abnormal pixel points, judging positions among the abnormal pixel points to obtain a defect position, marking a product corresponding to the defect position as a defective product, automatically identifying the product defect by adopting an AI industrial vision mode, reducing the workload of workers, simultaneously ensuring the quality of parts, and improving the yield of the parts.
Drawings
FIG. 1 is a schematic diagram of a system frame of the present invention;
fig. 2 is a schematic diagram of a flow frame of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 and fig. 2, the present application provides an identification system based on AI industrial vision, which includes a product operation module, an image acquisition module, a real-time model generation module, a standard analysis module, a defect judgment module, a reminding module, and a repair module;
embodiment one:
the product operation module is used for operating the processed product to be detected, namely, the processed product is transmitted to the next processing area, and meanwhile, a transmission signal is generated in the operation process and is transmitted to the image acquisition module;
the image acquisition module is used for receiving the transmission signal, acquiring the product image in the detection area, and transmitting the acquired product image to the real-time model generation module, wherein the acquisition of the product image covers the omnibearing image of the target product, and the specific product image comprises a front image, a left side image and a right side image;
the real-time model generation module is used for constructing and generating a real-time model of the transmitted product to be detected according to the product image, wherein a model of the corresponding product to be detected is preset in the real-time model generation module, when the product image is received, the product image is marked as a main appearance characteristic and is adapted to a position corresponding to the appearance of the preset model, so that a characteristic model is formed, the characteristic model constructed by the real-time model generation module corresponds to the corresponding product to be detected one by one, the constructed characteristic model and the preset model are transmitted to the defect judgment module by the real-time model generation module, and meanwhile, the appearance characteristic of the preset model in the real-time model generation module is a standard surface, namely the appearance characteristic of the preset model is the image characteristic of the standard product;
the standard analysis module is used for analyzing the obtained image of the standard surface of the model and the pixel value on the standard surface, and the specific analysis method is as follows:
s1: all pixel values Xa of the standard surface are obtained, a=1, 2, 3, … … and a1 are expressed that a1 pixel points exist, variance is calculated on the pixel values Xa, and a formula is adoptedObtaining the variance sigma of the pixel value 2 At the same time make the variance sigma 2 Performing root processing to obtain a standard deviation sigma, wherein Xaa is the average value of pixel values Xa;
s2: obtaining the maximum value Xd and the minimum value Xx in the pixel values, and adopting a formulaObtaining a spacing distance D, wherein m is a preset value, and a specific value of the spacing distance D is set by related professionals;
s3: then dividing the pixel value into m-1 interval regions according to the interval distance D, namely dividing the pixel value into [ X1, X2 ], [ X2, X3), … …, [ X (m-1), xm ], wherein Xm-X (m-1) =D according to the maximum value and the minimum value;
s4: the pixel values in the detection surface are corresponding to the interval areas, the number of the pixel points in each interval area is obtained, and the number of the pixel points in the interval area is divided by the total number of the pixel points to obtain a probability value Pa of the pixel points in the corresponding interval area;
s5: then adopt the formulaObtaining a standard value mu of a standard surface, wherein Pa is a probability value corresponding to an interval region where a pixel value Xa is located;
s6: respectively taking an upper limit value and a lower limit value for the pixel value according to the standard value mu and the standard deviation sigma, namely setting the value range of the pixel value as [ mu-2sigma, mu+2sigma ], setting the value range of the pixel value as the standard range of the pixel value, and transmitting the value range to a defect judging module;
the defect judging module is used for judging the pixel value of the detection surface image according to the standard value range, and the specific judging method comprises the following steps:
ST1: firstly, selecting an azimuth image in a product image according to the shape of the feature model, and marking the selected image as a target image;
ST2: acquiring all pixel points in a target image, establishing a two-dimensional rectangular coordinate system by taking the lower left corner in the target image as an origin, and then carrying out position marking on the pixel points according to the positions of the pixel points in the rectangular coordinate system;
ST3: comparing the value of the pixel point in the target image with a standard range, and marking the pixel point as an abnormal pixel point when the value of the pixel point does not belong to the standard range;
ST4: acquiring all abnormal pixel points and corresponding positions in a target image, and judging the defect positions according to the position relation among the abnormal pixel points, wherein the specific defect position judging method comprises the following steps of:
ST41: acquiring the position relation among abnormal pixel points, selecting the position of one pixel point, taking the position as a starting point, and marking the positions among the abnormal pixel points as defect positions when the positions among Y abnormal pixel points are adjacent and uninterrupted, wherein Y is a threshold value, and the specific value is taken by related professionals;
ST42: when the positions among the abnormal pixel points are discontinuous, acquiring probability values of the abnormal pixel points in a preset area, namely respectively acquiring the number of the abnormal pixel points and the number of all the pixel points in the preset area, dividing the number of the abnormal pixel points by the number of all the pixel points to obtain the probability values of the abnormal pixel points, and marking the corresponding preset area as a defect position when the probability values of the abnormal pixel points are larger than a preset value YS, wherein the preset area and the preset value YS are respectively valued by corresponding related personnel;
ST43: then marking the product corresponding to the defect position as a defect product, generating an alarm signal and transmitting the alarm signal to a reminding module;
the reminding module is used for receiving the alarm signal, generating a prompt message and transmitting the prompt message to related management personnel.
Embodiment two:
on the basis of the first embodiment, the device further comprises a repair module for repairing the position of the defective product, wherein the repair module is used for receiving the transmitted information of the defect judging module, repairing the position of the defect in the defective product, and then placing the repaired product into the product operation module;
embodiment III:
an identification method based on AI industrial vision comprises the following specific implementation steps:
step one: firstly, carrying out image acquisition on a product to be detected, and generating a real-time model;
step two: firstly, obtaining a pixel value on a standard surface image of a preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, and taking the value range as a standard range;
step three: judging pixel values in the detection surface image according to the standard range, selecting one azimuth image in the feature model, taking the azimuth image as a target image, comparing the pixel values in the target image with the standard range to obtain abnormal pixel points, judging positions among the abnormal pixel points to obtain defect positions, marking a product corresponding to the defect positions as a defect product, and generating an alarm signal;
step four: and generating prompt information according to the alarm signal and transmitting the prompt information to related management personnel.
The partial data in the formula are all obtained by removing dimension and taking the numerical value for calculation, and the formula is a formula closest to the real situation obtained by simulating a large amount of collected data through software; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or are obtained through mass data simulation.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. An AI-industrial vision-based recognition system, comprising:
the product operation module is used for operating the product to be detected, generating a transmission signal and transmitting the transmission signal to the image acquisition module;
the image acquisition module is used for acquiring a product image in the detection area according to the transmission signal and transmitting the acquired product image to the real-time model generation module, wherein the product image comprises a front image, a left side image and a right side image;
the real-time model generation module is used for combining the product image with the preset model to generate a characteristic model, and then the real-time model generation module respectively transmits the preset model and the characteristic model to the standard analysis module, wherein the appearance characteristic on the preset model is set as the image characteristic of the standard product, and the image characteristic of the standard product is marked as the standard surface;
the standard analysis module is used for obtaining the pixel value in the standard surface on the preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, and transmitting the value range to the defect judgment module as the standard range;
the defect judging module is used for judging the pixel value in the detection surface image according to the standard range, selecting one azimuth image in the feature model and using the azimuth image as a target image, comparing the pixel value in the target image with the standard range to obtain abnormal pixel points, judging the positions among the abnormal pixel points to obtain defect positions, marking a product corresponding to the defect positions as a defect product, and generating an alarm signal to be transmitted to the reminding module;
and the reminding module is used for generating prompt information according to the alarm signal and transmitting the prompt information to related management personnel.
2. The AI-industry vision-based recognition system of claim 1, wherein the standard deviation and the standard value are obtained by the following methods:
s1: all pixel values Xa of the standard surface are obtained, a=1, 2, 3, … … and a1 are expressed that a1 pixel points exist, variance is calculated on the pixel values Xa, and a formula is adoptedObtaining the variance sigma of the pixel value 2 At the same time make the variance sigma 2 Performing root processing to obtain a standard deviation sigma, wherein Xaa is the average value of pixel values Xa;
s2: obtaining the maximum value Xd and the minimum value Xx in the pixel values, and adopting a formulaObtaining a spacing distance D, wherein m is a preset value;
s3: then dividing the pixel value into m-1 interval regions according to the interval distance D, namely dividing the pixel value into [ X1, X2 ], [ X2, X3), … …, [ X (m-1), xm ], wherein Xm-X (m-1) =D according to the maximum value and the minimum value;
s4: the pixel values in the detection surface are corresponding to the interval areas, the number of the pixel points in each interval area is obtained, and the number of the pixel points in the interval area is divided by the total number of the pixel points to obtain a probability value Pa of the pixel points in the corresponding interval area;
s5: then adopt the formulaAnd obtaining a standard value mu of the standard surface, wherein Pa is a corresponding probability value in the interval region where the pixel value Xa is located.
3. The AI-industry vision-based recognition system of claim 2, wherein the standard range is obtained according to standard deviation and standard value by:
the pixel value is respectively set to an upper limit value and a lower limit value according to the standard value mu and the standard deviation sigma, namely, the value range of the pixel value is set to [ mu-2sigma, mu+2sigma ], and then the value range of the pixel value is set to be the standard range of the pixel value.
4. The AI-industrial-vision-based recognition system of claim 1, wherein the abnormal pixel points are obtained by:
ST1: firstly, selecting an azimuth image in a product image according to the shape of the feature model, and marking the selected image as a target image;
ST2: acquiring all pixel points in a target image, establishing a two-dimensional rectangular coordinate system by taking the lower left corner in the target image as an origin, and then carrying out position marking on the pixel points according to the positions of the pixel points in the rectangular coordinate system;
ST3: and comparing the value of the pixel point in the target image with a standard range, and marking the pixel point as an abnormal pixel point when the value of the pixel point does not belong to the standard range.
5. The AI-industry vision-based recognition system of claim 1, wherein the defect location determination method comprises:
and acquiring the position relation among the abnormal pixel points, selecting the position of one pixel point, taking the position as a starting point, and marking the position among the abnormal pixel points as a defect position when the positions of Y abnormal pixel points are adjacent and uninterrupted.
6. The AI-industry vision-based recognition system of claim 5, wherein the other determination method of the defect location is:
when the positions among the abnormal pixel points are discontinuous, obtaining probability values of the abnormal pixel points in the preset area, namely respectively obtaining the number of the abnormal pixel points and the number of all the pixel points in the preset area, dividing the number of the abnormal pixel points by the number of all the pixel points to obtain the probability values of the abnormal pixel points, and marking the corresponding preset area as a defect position when the probability values of the abnormal pixel points are larger than a preset value YS.
7. The AI-industry vision-based recognition system of claim 1, further comprising a repair module configured to repair the location of the defective product, the repair module configured to receive the transmitted information from the defect determination module, repair the location of the defect in the defective product, and then place the repaired product into the product operation module.
8. An identification method based on AI industrial vision, which is applied to the identification system of any one of the above claims 1-7, and is characterized by comprising the following steps:
step one: firstly, carrying out image acquisition on a product to be detected, and generating a real-time model;
step two: firstly, obtaining a pixel value on a standard surface image of a preset model, processing the pixel value to obtain a standard deviation and a standard value, setting a value range for the pixel value according to the standard deviation and the standard value, and taking the value range as a standard range;
step three: judging pixel values in the detection surface image according to the standard range, selecting one azimuth image in the feature model, taking the azimuth image as a target image, comparing the pixel values in the target image with the standard range to obtain abnormal pixel points, judging positions among the abnormal pixel points to obtain defect positions, marking a product corresponding to the defect positions as a defect product, and generating an alarm signal;
step four: and generating prompt information according to the alarm signal and transmitting the prompt information to related management personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310955155.XA CN117252809A (en) | 2023-08-01 | 2023-08-01 | Identification system and method based on AI industrial vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310955155.XA CN117252809A (en) | 2023-08-01 | 2023-08-01 | Identification system and method based on AI industrial vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117252809A true CN117252809A (en) | 2023-12-19 |
Family
ID=89125456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310955155.XA Pending CN117252809A (en) | 2023-08-01 | 2023-08-01 | Identification system and method based on AI industrial vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117252809A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437224A (en) * | 2023-12-20 | 2024-01-23 | 山东特联信息科技有限公司 | Gas cylinder defect image data processing system and method based on artificial intelligence |
-
2023
- 2023-08-01 CN CN202310955155.XA patent/CN117252809A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437224A (en) * | 2023-12-20 | 2024-01-23 | 山东特联信息科技有限公司 | Gas cylinder defect image data processing system and method based on artificial intelligence |
| CN117437224B (en) * | 2023-12-20 | 2024-03-29 | 山东特联信息科技有限公司 | Gas cylinder defect image data processing system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117252809A (en) | Identification system and method based on AI industrial vision | |
| CN112419298B (en) | Bolt node plate rust detection method, device, equipment and storage medium | |
| CN116337868B (en) | Surface defect detection method and detection system | |
| CN116823531B (en) | Building energy consumption management system based on BIM building | |
| CN116719293B (en) | Production monitoring method and system for cold-rolled steel strip | |
| CN115826516A (en) | Intelligent stainless steel chain production management method and system | |
| CN110749532A (en) | Hydraulic engineering seepage intelligent monitoring system and method | |
| CN117518939B (en) | Industrial control system based on big data | |
| CN117853295A (en) | Safety environmental protection emergency system based on industry interconnection and digital panorama | |
| CN116678368B (en) | BIM technology-based intelligent acquisition method for assembled steel structure data | |
| CN117834821A (en) | Intelligent interaction type security monitoring system | |
| CN116736814A (en) | Control method and system of production equipment for manufacturing cable protection tube | |
| CN106447732A (en) | Method for obtaining abnormal area by parallax information and three-dimensional information | |
| US11320809B2 (en) | Factory management system and control system | |
| CN115311560A (en) | Method and device for identifying hidden danger of external damage of power transmission channel | |
| CN116449761B (en) | Intelligent pump station intelligent control system and method | |
| CN117911415B (en) | Automatic equipment supervision system and method based on machine vision | |
| CN118116100B (en) | Intelligent inspection system and method based on digital twinning | |
| CN118429605B (en) | Equipment abnormality analysis method based on analysis model | |
| CN117310495B (en) | Durability comprehensive detection system of new energy motor | |
| CN117152355A (en) | Visual supervision system based on factory data | |
| CN117901121A (en) | Robot wireless communication system based on edge calculation | |
| CN118334401A (en) | Fungus bed renovation monitoring method and system | |
| CN117269332A (en) | Ultrasonic-based coal mine equipment defect detection and analysis system | |
| CN117454752A (en) | Main water pump equipment comprehensive risk analysis based on predictive model |
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 |