CN110751229A - Visual inspection system and method - Google Patents
Visual inspection system and method Download PDFInfo
- Publication number
- CN110751229A CN110751229A CN201911042641.2A CN201911042641A CN110751229A CN 110751229 A CN110751229 A CN 110751229A CN 201911042641 A CN201911042641 A CN 201911042641A CN 110751229 A CN110751229 A CN 110751229A
- Authority
- CN
- China
- Prior art keywords
- identification code
- unit
- sample
- visual inspection
- feeding mechanism
- 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.)
- Granted
Links
- 238000011179 visual inspection Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000000463 material Substances 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 27
- 238000004891 communication Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 abstract description 57
- 230000000007 visual effect Effects 0.000 abstract description 25
- 238000013473 artificial intelligence Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000009434 installation Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001292396 Cirrhitidae Species 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a visual inspection system and a visual inspection method. The system comprises an identification system, wherein the identification system comprises an image acquisition unit, a feature identification unit, a feature comparison unit, an identification code search unit and a material determination unit. The method comprises the following steps: collecting image information of materials of the disordered sample; processing image information of the material and identifying characteristics of the material; comparing the identified characteristic data with the characteristic data of the known sample, and judging whether the material is the known sample according to the comparison result; searching the identification code in the database when the material is judged to be a known sample; and when the identification code is searched, determining the type of the material according to the identification code. The system and the method utilize an AI algorithm to intelligently identify and classify materials; by combining a robot, the feeding mechanism which is matched with the robot automatically is selected according to the type and the model of the material by visual detection; the robot replaces the manual work to carry out feeding mechanism's regulation, realizes automatic intelligent detection.
Description
Technical Field
The invention relates to image processing and artificial intelligence technology, in particular to a visual inspection system and a visual inspection method.
Background
In the currently developed visual inspection equipment, a special feeding mechanism is needed to convey an object to be inspected to an appointed detection position according to a set posture for visual inspection. For visual inspection, each object to be inspected needs to be provided with a specific feeding mechanism (or detection tool). When the kind or the model of the object to be detected is switched, the feeding mechanism (or the detection tool) needs to be manually switched and adjusted. A large amount of time and labor are needed for each switching, and automatic intelligent detection cannot be really realized.
Disclosure of Invention
The invention aims to provide a visual detection system and a visual detection method, wherein the intelligent identification and classification of materials are carried out by utilizing an Artificial Intelligence (AI) algorithm, and the visual detection system automatically selects and matches a proper feeding mechanism according to the types and models of the materials.
In order to solve the technical problems, the invention adopts the following technical scheme:
in one aspect, the present invention is directed to a visual inspection system. The vision inspection system includes an identification system, the identification system including: the image acquisition unit is used for acquiring the image information of the material of the disorder sample; the characteristic identification unit is used for processing the image information of the material and identifying the characteristics of the material; the characteristic comparison unit is used for comparing the identified characteristics with the characteristics of the known sample and judging whether the material is the known sample according to the comparison result; the identification code searching unit is used for searching the identification code in the database when the material is judged to be a known sample; and the material determining unit is used for determining the type of the material according to the identification code when the identification code is searched.
Optionally, for the visual inspection system, the recognition system further comprises: and the communication unit is used for sending the identification code.
Optionally, the visual inspection system further comprises a scheduling system, the scheduling system comprising: the communication unit is used for receiving the identification code; the query unit is used for querying whether a feeding mechanism corresponding to the identification code exists in the tool library or not according to the identification code; and the tool selection unit is used for controlling the robot to select the corresponding feeding mechanism to grab and install when the feeding mechanism exists.
Optionally, for the visual inspection system, the scheduling system further comprises: and the tool adjusting unit is used for adjusting at least one of the position parameters and the size parameters of the feeding mechanism according to the characteristic data corresponding to the identification code.
Optionally, the visual inspection system further comprises a sample training system, the sample training system comprising: the classification unit is used for classifying the samples according to types and/or models and then acquiring image information; the characteristic training unit is used for processing the image information of the sample and performing characteristic training; and the identification code generating unit is used for respectively generating unique identification codes for various samples and storing the generated identification codes and the characteristic data into a database.
In another aspect, the present invention provides a visual inspection method. The visual inspection method comprises the following steps: collecting image information of materials of the disordered sample; processing image information of the material and identifying characteristics of the material; comparing the identified characteristic data with the characteristic data of the known sample, and judging whether the material is the known sample according to the comparison result; searching the identification code in the database when the material is judged to be a known sample; and when the identification code is searched, determining the type of the material according to the identification code.
Optionally, the visual inspection method further includes: inquiring whether a feeding mechanism corresponding to the identification code exists in the tool library or not according to the identification code; and when the feeding mechanism exists, the robot is controlled to select the corresponding feeding mechanism to grab and install.
Optionally, for the visual inspection method, after the control robot selects the corresponding feeding mechanism for grabbing and installing, the method further includes: and adjusting at least one of the position parameter and the size parameter of the feeding mechanism according to the characteristic data corresponding to the identification code.
Optionally, for the visual inspection method, the feature data of the known sample is obtained through a sample training process.
Optionally, for the visual inspection method, the sample training process comprises: classifying the samples according to types and/or models and then acquiring image information; processing image information of a sample and performing feature training; respectively generating unique identification codes for various samples, and storing the generated identification codes and the characteristic data into a database.
Compared with the prior art, the technical scheme of the invention has the following main advantages:
the visual inspection system and the visual inspection method provided by the embodiment of the invention utilize an Artificial Intelligence (AI) algorithm to carry out intelligent identification and classification on materials; by combining a robot, a visual detection system can automatically select and match a proper feeding mechanism (or a detection tool) according to the type and the model of the material; the robot replaces the manual work to carry out the regulation of feeding mechanism (or be called and detect the frock), realizes automatic intelligent detection.
The visual detection system and the method of the embodiment of the invention reduce the inaccurate detection parameters caused by manually adjusting the feeding mechanism (or called as a detection tool), improve the accuracy and the operation efficiency of the visual detection, greatly save manpower and material resources, and can be applied to the related visual detection projects such as the automatic screw visual detection project, the manual operator visual detection project, the square display visual detection project and the like which are developed and completed at present.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic illustration of an example provided out-of-order sample;
FIG. 2 is a schematic illustration of sequential samples provided by an example;
FIG. 3 is a schematic diagram of a visual inspection system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a visual inspection system according to an exemplary embodiment;
FIG. 5 is a schematic diagram of an exemplary recognition process;
FIG. 6 is a schematic diagram of a tooling selection flow provided by an example;
FIG. 7 is a schematic diagram of a training flow provided by an example;
fig. 8 is a flowchart of a visual inspection method according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Before describing the visual inspection system and method provided by the embodiments of the present invention, the terminology is explained first.
1) The sample to be detected refers to a material which needs to be subjected to visual detection, and comprises various hardware such as screws, nuts, bolts and gaskets and various standard pieces commonly used in industrial scenes, commercial scenes and household scenes. 2) The disorder sample refers to a state of the sample to be tested when the sample is not sorted, as shown in fig. 1, the sample only includes an object (or material) with a unique type and a unique model, and the sample is used for an Artificial Intelligence (AI) classifier to identify and identify the material. 3) The sequential samples refer to the state of the disordered samples after being sorted and arranged by a specific feeding mechanism (or referred to as a detection tool), as shown in fig. 2, the postures of the samples are uniform and arranged in sequence, and the visual detection system performs fine detection on the samples independently.
Fig. 3 is a schematic structural diagram of a visual inspection system according to an embodiment of the present invention. As shown in fig. 3, the visual inspection system provided in this embodiment includes a recognition system 310. Functionally, the recognition system 310 includes an image acquisition unit 311, a feature recognition unit 312, a feature comparison unit 313, an identification code search unit 314, and a material determination unit 315. The image collecting unit 311 is configured to collect image information of the material of the disorder sample. The feature recognition unit 312 is configured to process image information of the material and perform feature recognition on the material. The feature comparison unit 313 is used for comparing the identified features with the features of the known samples, and judging whether the material is the known sample according to the comparison result. The identifier searching unit 314 is configured to search the database for the identifier when the material is determined to be a known sample. The material determining unit 315 is configured to determine the type of the material according to the identification code when the identification code is searched.
The recognition system 310 is used to identify and classify material of the out-of-order sample. Fig. 4 is a schematic structural diagram of a visual inspection system provided as an example. As shown in fig. 4, the system core may be an AI processor, which may include an AI classifier. The recognition system 310 may include an image acquisition unit 311 for taking a picture by a camera and a light source to obtain information for processing. Functionally, the AI processor includes a feature identification unit, a feature collation unit, an identification code search unit, and a material determination unit.
The identification system 310 may also include a communication unit 316. The communication unit 316 is used for sending the identification code.
Fig. 5 is a schematic diagram of an exemplary recognition process. As shown in fig. 5, the incoming material triggers the sensor of the identification system 310, and the identification system 310 controls the camera and the light source to work, so that the material can take a picture. And after the photographing is finished, the AI processor identifies the material characteristics and judges whether the material characteristics are known samples. If the sample is unknown, an alarm is given to prompt that the sample is abnormal, and the identification process is terminated. If the sample is known, an AI classifier in the AI processor starts to determine key data such as the type, model and the like of the sample and searches the database for the identification code. If the identification code does not exist, an alarm is given to prompt that the sample is abnormal, and the identification process is terminated. If the identification code exists, the identification code is sent to the dispatching system through the communication unit, and then an identification process is finished.
The visual inspection system of this embodiment may also include a scheduling system 320. Functionally, the scheduling system 320 may include a communication unit 321, a query unit 322, and a tool selection unit 323. The communication unit 320 is used for receiving the identification code. The query unit is used for querying whether a feeding mechanism or a detection tool corresponding to the identification code exists in the tool library or not according to the identification code. The tool selection unit is used for controlling the robot to select the corresponding feeding mechanism or the detection tool to grab and install when the feeding mechanism or the detection tool exists.
The scheduling system 320 may also include a tooling adjustment unit 324. The tool adjusting unit 324 is configured to adjust at least one of a position parameter and a size parameter of the feeding mechanism (or referred to as a detection tool) according to the feature data corresponding to the identification code.
As shown in fig. 4, the dispatching system 320 may include, in hardware, a communication module, a controller, a robot, and a feeding mechanism (or referred to as a detection tool). The feeding mechanism (or referred to as a detection tool) includes, but is not limited to, at least one of a feeder, a vibration disk, a straight vibration rail and the like. The dispatching system 320 is used for receiving the material information sent by the identification system 310, and controlling the robot to select a feeding mechanism (or referred to as a detection tool) matched with the material to be detected to install and adjust according to the content contained in the material information. The feeding mechanism (or called as a detection tool) which is installed and debugged can sort out-of-order samples so that a visual detection system can perform fine detection on the samples.
Fig. 6 is a schematic diagram of a tooling selection flow provided by an example. As shown in fig. 6, the communication unit 321 of the dispatching system 320 waits for data reception, performs parsing after receiving the data, obtains an identification code, and queries whether a feeding mechanism (or referred to as a detection tool) corresponding to the identification code exists in a tool library according to the identification code. If not, the tool is lack through alarm prompt, and the tool selects to execute the flow to terminate. If the tool exists, the robot is controlled to select a corresponding feeding mechanism (or called as a detection tool) to carry out grabbing and installation, important parameters such as position parameters, size parameters and the like of the feeding mechanism (or called as the detection tool) are adjusted according to the characteristic data corresponding to the identification code, and after the adjustment is finished, a tool selection process is finished.
The visual inspection system of this embodiment may also include a sample training system. The sample training system may include a classification unit, a feature training unit, and an identification code generation unit. The classification unit is used for classifying the samples according to types and models and then acquiring image information. The characteristic training unit is used for processing the image information of the sample and performing characteristic training. The identification code generating unit is used for respectively generating unique identification codes for various samples and storing the identification codes and the characteristic data into a database.
FIG. 7 is a schematic diagram of a training flow provided by an example. As shown in fig. 7, the disordered samples are firstly classified individually according to types and/or models, then the identification system takes pictures to obtain the samples, the samples obtained by taking pictures are random, the magnitude of the picture of the sample depends on the complexity of the sample, and the magnitude is selected from thousands, tens of thousands and hundreds of thousands. And after the photographing is finished, carrying out feature training, generating a unique identification code according to each sample after the training is finished, and uniformly storing the identification code and the feature data into a database. At this point, a training procedure ends.
Fig. 8 is a flowchart of a visual inspection method according to an embodiment of the present invention.
As shown in fig. 8, in step S810, image information of the material of the disorder sample is collected.
In step S820, the image information of the material is processed and the characteristic of the material is identified.
In step S830, the identified feature data is compared with the feature data of the known sample, and whether the material is the known sample is determined according to the comparison result.
In step S840, when the material is determined to be a known sample, the database is searched for an identification code.
In step S850, when the identification code is searched, the type of the material is determined according to the identification code.
The visual inspection method of this embodiment may further include: inquiring whether a feeding mechanism (or a detection tool) corresponding to the identification code exists in a tool library or not according to the identification code; when the feeding mechanism (or called as a detection tool) exists, the robot is controlled to select the corresponding feeding mechanism (or called as a detection tool) to perform grabbing and installation.
After the control robot selects the corresponding feeding mechanism (or referred to as a detection tool) to perform grabbing and installation, the visual detection method of the embodiment may further include: and adjusting at least one of the position parameter and the size parameter of the feeding mechanism (or called as a detection tool) according to the characteristic data corresponding to the identification code.
In this embodiment, the feature data of the known sample may be obtained through a sample training process. The sample training process may include: classifying the samples according to types and/or models and then acquiring image information; processing image information of a sample and performing feature training; respectively generating unique identification codes for various samples, and storing the identification codes and the characteristic data into a database.
The embodiment of the invention provides a visual detection system and a visual detection method, wherein the visual detection system can be built on different platforms, including but not limited to Windows, Linux and other system platforms. The visual inspection method provided by the embodiment of the present invention can be implemented by various programming languages, including but not limited to C, C + +, C #, JAVA, and/or Python, as an algorithmic idea. The deep learning algorithm applied by the AI classifier in the system includes, but is not limited to, a Multi-layer perceptron (MLP), a Gaussian Mixture Model (GMM), and/or a Support Vector Machine (SVM), and one or more of them may be used in combination. Model building platforms include, but are not limited to, Halcon, OpenCV, and/or MATLAB, among others, and support migration replacement.
The visual inspection system and the visual inspection method provided by the embodiment of the invention utilize an Artificial Intelligence (AI) algorithm to carry out intelligent identification and classification on materials; by combining a robot, a visual detection system can automatically select and match a proper feeding mechanism (or a detection tool) according to the type and the model of the material; the robot replaces the manual work to carry out the regulation of feeding mechanism (or be called and detect the frock), realizes automatic intelligent detection.
The visual detection system and the method of the embodiment of the invention reduce the inaccurate detection parameters caused by manually adjusting the feeding mechanism (or called as a detection tool), improve the accuracy and the operation efficiency of the visual detection, greatly save manpower and material resources, and can be applied to the related visual detection projects such as the automatic screw visual detection project, the manual operator visual detection project, the square display visual detection project and the like which are developed and completed at present.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the claims, and all equivalent structures or equivalent processes that are transformed by the content of the specification and the drawings, or directly or indirectly applied to other related technical fields are included in the scope of the claims.
Claims (10)
1. A visual inspection system comprising an identification system, the identification system comprising:
the image acquisition unit is used for acquiring the image information of the material of the disorder sample;
the characteristic identification unit is used for processing the image information of the material and identifying the characteristics of the material;
the characteristic comparison unit is used for comparing the identified characteristics with the characteristics of the known sample and judging whether the material is the known sample according to the comparison result;
the identification code searching unit is used for searching the identification code in the database when the material is judged to be a known sample;
and the material determining unit is used for determining the type of the material according to the identification code when the identification code is searched.
2. The visual inspection system of claim 1, wherein the recognition system further comprises: and the communication unit is used for sending the identification code.
3. The visual inspection system of claim 2, further comprising a scheduling system, the scheduling system comprising:
the communication unit is used for receiving the identification code;
the query unit is used for querying whether a feeding mechanism corresponding to the identification code exists in the tool library or not according to the identification code;
and the tool selection unit is used for controlling the robot to select the corresponding feeding mechanism to grab and install when the feeding mechanism exists.
4. The visual inspection system of claim 3, wherein the scheduling system further comprises:
and the tool adjusting unit is used for adjusting at least one of the position parameters and the size parameters of the feeding mechanism according to the characteristic data corresponding to the identification code.
5. The visual inspection system of claim 1, further comprising a sample training system, the sample training system comprising:
the classification unit is used for classifying the samples according to types and/or models and then acquiring image information;
the characteristic training unit is used for processing the image information of the sample and performing characteristic training;
and the identification code generating unit is used for respectively generating unique identification codes for various samples and storing the generated identification codes and the characteristic data into a database.
6. A method of visual inspection, comprising:
collecting image information of materials of the disordered sample;
processing image information of the material and identifying characteristics of the material;
comparing the identified characteristic data with the characteristic data of the known sample, and judging whether the material is the known sample according to the comparison result;
searching the identification code in the database when the material is judged to be a known sample;
and when the identification code is searched, determining the type of the material according to the identification code.
7. The visual inspection method of claim 6, further comprising:
inquiring whether a feeding mechanism corresponding to the identification code exists in the tool library or not according to the identification code;
and when the feeding mechanism exists, the robot is controlled to select the corresponding feeding mechanism to grab and install.
8. The visual inspection method of claim 7, wherein after the controlling the robot selects the corresponding feeding mechanism for the grabbing and installing, further comprising:
and adjusting at least one of the position parameter and the size parameter of the feeding mechanism according to the characteristic data corresponding to the identification code.
9. The visual inspection method of claim 6, wherein the feature data of the known sample is obtained by a sample training process.
10. The visual inspection method of claim 9, wherein the sample training process comprises:
classifying the samples according to types and/or models and then acquiring image information;
processing image information of a sample and performing feature training;
respectively generating unique identification codes for various samples, and storing the generated identification codes and the characteristic data into a database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042641.2A CN110751229B (en) | 2019-10-30 | 2019-10-30 | Visual inspection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042641.2A CN110751229B (en) | 2019-10-30 | 2019-10-30 | Visual inspection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110751229A true CN110751229A (en) | 2020-02-04 |
| CN110751229B CN110751229B (en) | 2023-07-28 |
Family
ID=69281063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911042641.2A Active CN110751229B (en) | 2019-10-30 | 2019-10-30 | Visual inspection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751229B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340450A (en) * | 2020-02-28 | 2020-06-26 | 上海必耀科技有限公司 | Material information batch new building system and method for batch new building of materials |
| CN117104831A (en) * | 2023-09-01 | 2023-11-24 | 中信戴卡股份有限公司 | Robot 3D recognition and processing method and system for knuckle workpiece |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130279748A1 (en) * | 2012-04-20 | 2013-10-24 | Robert D. Hastings | Object identification using optical code reading and object recognition |
| CN105321860A (en) * | 2014-06-27 | 2016-02-10 | 旺矽科技股份有限公司 | Full automatic feeding/discharging device and control method |
| CN105701476A (en) * | 2016-02-04 | 2016-06-22 | 合肥泰禾光电科技股份有限公司 | Machine vision-based automatic identification system and method for production line products |
| CN109760054A (en) * | 2019-01-30 | 2019-05-17 | 重庆两江微链智能科技有限公司 | Robot autonomous learning system and robot control method |
| CN109969178A (en) * | 2019-03-26 | 2019-07-05 | 齐鲁工业大学 | Based on the autonomous handling device of the more materials of multielement bar and method |
-
2019
- 2019-10-30 CN CN201911042641.2A patent/CN110751229B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130279748A1 (en) * | 2012-04-20 | 2013-10-24 | Robert D. Hastings | Object identification using optical code reading and object recognition |
| CN105321860A (en) * | 2014-06-27 | 2016-02-10 | 旺矽科技股份有限公司 | Full automatic feeding/discharging device and control method |
| CN105701476A (en) * | 2016-02-04 | 2016-06-22 | 合肥泰禾光电科技股份有限公司 | Machine vision-based automatic identification system and method for production line products |
| CN109760054A (en) * | 2019-01-30 | 2019-05-17 | 重庆两江微链智能科技有限公司 | Robot autonomous learning system and robot control method |
| CN109969178A (en) * | 2019-03-26 | 2019-07-05 | 齐鲁工业大学 | Based on the autonomous handling device of the more materials of multielement bar and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340450A (en) * | 2020-02-28 | 2020-06-26 | 上海必耀科技有限公司 | Material information batch new building system and method for batch new building of materials |
| CN117104831A (en) * | 2023-09-01 | 2023-11-24 | 中信戴卡股份有限公司 | Robot 3D recognition and processing method and system for knuckle workpiece |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110751229B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105817430B (en) | Product inspection method based on machine vision | |
| CN102253048B (en) | Machine vision detection method and system for detection of various products | |
| CN110751229B (en) | Visual inspection system and method | |
| CN107944504B (en) | Board recognition and machine learning method and device for board recognition and electronic equipment | |
| CN113870260A (en) | Welding defect real-time detection method and system based on high-frequency time sequence data | |
| CN101271515A (en) | Image detection device capable of recognizing multi-angle objective | |
| CN113723325B (en) | Frock defect detecting system of prefabricated component of assembled | |
| CN103785622A (en) | Machine-vision-based part sorting device and method | |
| CN113361539A (en) | Instrument reading method and device of underground inspection robot and electronic equipment | |
| CN108563204B (en) | Control method, control device, electronic equipment and computer-readable storage medium | |
| CN111453247A (en) | Garbage classification method and intelligent household appliance | |
| WO2021030322A1 (en) | System and method of object detection using ai deep learning models | |
| CN114943751A (en) | Material tracking and positioning method and system based on direction vector in cloud PLC environment | |
| Moirogiorgou et al. | Intelligent robotic system for urban waste recycling | |
| CN110618129A (en) | Automatic power grid wire clamp detection and defect identification method and device | |
| CN114359552A (en) | Instrument image identification method based on inspection robot | |
| Duan et al. | A real-time machine vision system for bottle finish inspection | |
| CN116481585B (en) | Product full detection system and method based on machine vision | |
| CN115687961B (en) | Automatic welding procedure intelligent recognition method based on pattern recognition | |
| JPH03171375A (en) | Method and apparatus for detecting object in assembling line | |
| CN114553599B (en) | Garden monitoring system and method based on edge calculation | |
| CN112927170B (en) | Automatic defect removing method in semiconductor manufacturing process | |
| EP3992738A1 (en) | Fluorescent inspection visual data processing system and processing method thereof based on mes | |
| CN112215149B (en) | Fitting sorting system and method based on visual detection | |
| CN114192447A (en) | Garbage sorting method based on image recognition |
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 |