CN112668620A - Machine vision identification method and device and readable storage medium - Google Patents
Machine vision identification method and device and readable storage medium Download PDFInfo
- Publication number
- CN112668620A CN112668620A CN202011525855.8A CN202011525855A CN112668620A CN 112668620 A CN112668620 A CN 112668620A CN 202011525855 A CN202011525855 A CN 202011525855A CN 112668620 A CN112668620 A CN 112668620A
- Authority
- CN
- China
- Prior art keywords
- component
- identified
- characteristic information
- label
- information
- 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 25
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 206010027175 memory impairment Diseases 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Abstract
The invention relates to the technical field of machine vision, and provides a machine vision identification method, a device and a readable storage medium, wherein the method comprises the steps of allocating a unique corresponding first label for a component to be identified; distributing a unique corresponding second label for the cable in the component to be identified; acquiring image information of a component to be identified; determining first characteristic information of the component to be identified based on the image information, the first label and the second label; and comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, determining that the component to be identified passes the detection, and if the first characteristic information is inconsistent with the second characteristic information, determining that the component to be identified does not pass the detection. Whether the component passes the detection or not can be automatically judged, and the problem of high false detection rate in the existing detection method can be solved.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a machine vision identification method and device and a readable storage medium.
Background
In the industrial field, when some industrial control cabinets are subjected to factory inspection and before power-on test, whether the connection of components in the cabinets is correct needs to be judged. However, the manual visual detection has the problems of wrong detection and missed detection. In the process of checking products, misjudgment can be generated on identification of components and cables due to fatigue or mood factors of operators, or key detection point features are missed in manual detection due to reasons of incomplete transmission of latest detection standard information or negligence and forgetfulness of operators, so that errors exist in product detection, rework cost, after-sale cost and even batch recall risks are increased. Therefore, the problem of high false detection rate of the existing detection method for the components is solved.
Disclosure of Invention
The invention provides a machine vision identification method, a device and a readable storage medium, which aim to solve the problem of high false detection rate in the existing detection method.
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a machine vision recognition method, including:
allocating a unique corresponding first label for the component to be identified;
distributing a unique corresponding second label for the cable in the component to be identified;
acquiring image information of the component to be identified;
determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, determining that the component to be identified passes the detection, and if the first characteristic information is inconsistent with the second characteristic information, determining that the component to be identified does not pass the detection.
Optionally, the assigning a unique corresponding first tag to the component to be identified includes:
determining the name information of the component to be identified;
and generating a two-dimensional code carrying the name information as a first label uniquely corresponding to the component to be identified.
Optionally, the allocating a unique corresponding second tag to the cable in the component to be identified includes:
determining identification information of the cable;
and generating a bar code carrying the identification information as a second label uniquely corresponding to the cable.
Optionally, the first characteristic information or the second characteristic information each includes bar code data, two-dimensional code data, an outline, a size, a color, a model, a number of wiring holes, and at least one of a number of cables, a color of the cables, and a wire diameter.
In a second aspect, the present invention also provides a machine vision recognition apparatus, including:
the first generation module is used for allocating a unique corresponding first label for the component to be identified;
the second generation module is used for distributing a unique corresponding second label for the cable in the component to be identified;
the image acquisition module is used for acquiring the image information of the component to be identified;
the identification module is used for determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and the comparison module is used for comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, the component to be identified is considered to pass the detection, and if the first characteristic information is inconsistent with the second characteristic information, the component to be identified is considered to not pass the detection.
Optionally, the image acquisition module is a video camera or an industrial camera.
In a third aspect, the present invention also provides a machine vision recognition apparatus, including a processor, a memory, and a program or instructions stored on the memory and executable on the processor, where the program or instructions, when executed by the processor, implement the steps of the machine vision recognition method according to the first aspect.
In a fourth aspect, the present invention also provides a readable storage medium on which a program or instructions are stored, which when executed by a processor, implement the steps of the machine vision recognition method according to the first aspect.
Has the advantages that:
the invention provides a machine vision identification method, a device and a readable storage medium, wherein the machine vision identification method comprises the steps of allocating a unique corresponding first label for a component to be identified; distributing a unique corresponding second label for the cable in the component to be identified; acquiring image information of a component to be identified; determining first characteristic information of the component to be identified based on the image information, the first label and the second label; and comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, determining that the component to be identified passes the detection, and if the first characteristic information is inconsistent with the second characteristic information, determining that the component to be identified does not pass the detection. Therefore, whether the component passes the detection or not can be automatically judged, and the problem of high false detection rate in the existing detection method can be solved.
Drawings
FIG. 1 is a flow chart of a machine vision recognition method in accordance with a preferred embodiment of the present invention;
fig. 2 is a schematic block diagram of a machine vision recognition device according to a preferred embodiment of the present invention.
Detailed Description
The technical solutions of the present invention are described clearly and completely below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a machine vision recognition method, including:
allocating a unique corresponding first label for the component to be identified;
distributing a unique corresponding second label for the cable in the component to be identified;
acquiring image information of a component to be identified;
determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, determining that the component to be identified passes the detection, and if the first characteristic information is inconsistent with the second characteristic information, determining that the component to be identified does not pass the detection.
In this embodiment, the components to be identified may be various electrical components in an electrical control, and are not exhaustive here.
In this embodiment, the first label may be a two-dimensional code or a bar code, and the second label may also be a two-dimensional code or a bar code, which is only an example and is not limited herein, alternatively, in other possible embodiments, other types of labels may also be used as the first label or the second label, but whatever the change is made, and the protection scope of the embodiments of the present application is within the scope of the present application.
Specifically, in this embodiment, a two-dimensional code will be described as an example of a first label and a barcode will be described as an example of a second label.
In this embodiment, the image information may be acquired by an image capturing device such as a video camera, an industrial camera, a professional camera, etc., which are only used as examples and are not limited herein, and alternatively, in other feasible embodiments, other types of image capturing devices may also be used. However, any modification thereof is within the scope of the embodiments of the present application.
The machine vision identification method can automatically judge whether the component passes the detection or not, and can solve the problem of high false detection rate in the existing detection method.
Optionally, assigning a unique corresponding first tag to the component to be identified includes:
determining the name information of the component to be identified;
and generating a two-dimensional code carrying name information as a first label uniquely corresponding to the component to be identified.
In this embodiment, according to the name information of the component to be recognized, a two-dimensional code carrying the name information is generated, and the two-dimensional code is arranged on the component to be recognized. For example, the two-dimensional code may be disposed on a piece of paper by printing, and the piece of paper may be attached to the component to be identified.
Optionally, assigning a uniquely corresponding second tag to the cable in the component to be identified includes:
determining identification information of the cable;
a barcode carrying identification information is generated as a second label uniquely corresponding to the cable.
In this embodiment, a barcode carrying identification information is generated according to identification information of a cable in a component to be identified, and the barcode is disposed on the cable in the component to be identified. For example, the barcode may be printed on a piece of paper, and the paper may be attached to the cable in the component to be identified.
The advantage that machine vision can be fine behind increase two-dimensional code and bar code utilizes discernment two-dimensional code or bar code swift, more convenient more accurate location database information, also avoided simultaneously because of shooting the angle difference can't discern current, set up the problem of Arabic figure on components and parts.
Optionally, the first characteristic information or the second characteristic information each includes bar code data, two-dimensional code data, outline, size, color, model of the electrical component, number of the wiring holes, and at least one of number of cables, color of the cables, and diameter of the cables.
Specifically, first, a two-dimensional code is added to the electrical component to represent the component name (e.g., 18T1), and a bar code is added to the cable to represent the cable identification number. The position name of the hole position needing wiring in the electric element is defined. Establishing a table, inputting the data corresponding to the electrical element and the content to be identified, as shown in table 1:
TABLE 1 Electrical component related data
The characteristic data of various components are recorded into the database, so that a standard database is formed, and the comparison and judgment of the actually acquired image and the database characteristic can be realized by utilizing the database information. The characteristics of the electrical elements are digitally processed and recorded into the database, so that when the characteristic contents need to be increased, reduced or modified, only the database table needs to be modified and maintained, and the machine vision system does not need to be greatly changed.
Specifically, when detecting, utilize the cell-phone camera to shoot each components and parts that need detect, the two-dimensional code on the automatic identification components and parts to whether the line diameter, colour, cable identification number etc. of the cable of automatic identification, judgement access this components and parts are unanimous with the standard in the database, and will judge that the result shows and supply operating personnel to refer to. For example, utilize cell-phone APP to shoot the components and parts in the regulator cubicle, discern the two-dimensional code information (components and parts sign) on its electrical component on APP, transmit picture and two-dimensional code information data into the server and carry out picture analysis and processing, compare analysis processing result and database data by the server, thereby judge whether the characteristics that components and parts model, size, wiring position, cable line footpath, cable colour, cable sign etc. need discernment are correct in the picture, synthesize the recognition situation of each item characteristic, finally give the judgement result, and will judge that the content feeds back to and show in the cell-phone APP. The effect of machine vision judgment is achieved.
It should be noted that, the existing component identification adopts a manual identification mode, because a human operator sees that the probability of the wrong connection of the electrical component is small and the electrical component is easily identified from the appearance, but as the types of the electrical components are more and more, the electrical components produced by the same company are likely to have the same appearance and color, and the electrical components need to be identified by specific models. Therefore, by adopting the machine vision identification method, the relevant characteristic information of the wiring cable can be identified and whether the electrical element meets the standard requirement can be identified by utilizing vision identification.
Referring to fig. 2, an embodiment of the present application further provides a machine vision recognition apparatus, including:
the first generation module is used for allocating a unique corresponding first label for the component to be identified;
the second generation module is used for distributing a unique corresponding second label for the cable in the component to be identified;
the image acquisition module is used for acquiring the image information of the component to be identified;
the identification module is used for determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and the comparison module is used for comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, the component to be identified is considered to pass the detection, and if the first characteristic information is inconsistent with the second characteristic information, the component to be identified is considered to not pass the detection.
The machine vision recognition device can realize each real-time instance in the machine vision recognition method, and can achieve the same technical effect, and the details are not repeated here.
Optionally, the image acquisition module is a video camera or an industrial camera. By way of example only, and not limitation, other types of image capture modules may be alternatively used, but any transformation thereof is within the scope of the embodiments of the present application.
The embodiment of the present application further provides a machine vision recognition apparatus, which includes a processor, a memory, and a program or an instruction stored on the memory and executable on the processor, and when executed by the processor, the program or the instruction implements the steps of the machine vision recognition method as described above.
Optionally, an embodiment of the present application further provides a readable storage medium, on which a program or instructions are stored, and when executed by a processor, the program or instructions implement the steps of the machine vision identification method as described above.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (8)
1. A machine vision recognition method, comprising:
allocating a unique corresponding first label for the component to be identified;
distributing a unique corresponding second label for the cable in the component to be identified;
acquiring image information of the component to be identified;
determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, determining that the component to be identified passes the detection, and if the first characteristic information is inconsistent with the second characteristic information, determining that the component to be identified does not pass the detection.
2. The machine-vision identification method of claim 1, wherein the assigning of the uniquely corresponding first label to the component to be identified comprises:
determining the name information of the component to be identified;
and generating a two-dimensional code carrying the name information as a first label uniquely corresponding to the component to be identified.
3. The machine-vision identification method of claim 1, wherein the assigning of the uniquely corresponding second label to the cable in the component to be identified comprises:
determining identification information of the cable;
and generating a bar code carrying the identification information as a second label uniquely corresponding to the cable.
4. The machine-vision recognition method of claim 1, wherein the first characteristic information or the second characteristic information each comprises bar code data, two-dimensional code data, electrical component outline, size, color, model, number of wiring holes, and at least one of number of cables, color of cables, and wire diameter.
5. A machine vision recognition device, comprising:
the first generation module is used for allocating a unique corresponding first label for the component to be identified;
the second generation module is used for distributing a unique corresponding second label for the cable in the component to be identified;
the image acquisition module is used for acquiring the image information of the component to be identified;
the identification module is used for determining first characteristic information of the component to be identified based on the image information, the first label and the second label;
and the comparison module is used for comparing the characteristic information with second characteristic information in a preset database, if the first characteristic information is consistent with the second characteristic information, the component to be identified is considered to pass the detection, and if the first characteristic information is inconsistent with the second characteristic information, the component to be identified is considered to not pass the detection.
6. The machine-vision recognition device of claim 5, wherein the image acquisition module is a video camera or an industrial camera.
7. A machine vision recognition apparatus comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the machine vision recognition method of any one of claims 1-4.
8. A readable storage medium, on which a program or instructions are stored, which when executed by a processor, carry out the steps of the machine vision recognition method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011525855.8A CN112668620A (en) | 2020-12-22 | 2020-12-22 | Machine vision identification method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011525855.8A CN112668620A (en) | 2020-12-22 | 2020-12-22 | Machine vision identification method and device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112668620A true CN112668620A (en) | 2021-04-16 |
Family
ID=75407414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011525855.8A Pending CN112668620A (en) | 2020-12-22 | 2020-12-22 | Machine vision identification method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668620A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503190A (en) * | 2002-11-21 | 2004-06-09 | 深圳矽感科技有限公司 | Cable label readig device and method |
| CN107622253A (en) * | 2017-09-30 | 2018-01-23 | 天津帕比特科技有限公司 | A kind of image-recognizing method based on neural network recognization device type |
| CN109583528A (en) * | 2018-11-05 | 2019-04-05 | 广西电网有限责任公司防城港供电局 | Information machine room cable identification and hunting management method based on seven color two dimensional codes |
| CN110119680A (en) * | 2019-04-03 | 2019-08-13 | 上海工程技术大学 | A kind of electrical cabinet wiring automatic errordetecting system based on image recognition |
| CN110503404A (en) * | 2019-08-27 | 2019-11-26 | 中国联合网络通信集团有限公司 | Asset Tag generation method, device, equipment and storage medium |
| CN110609912A (en) * | 2019-08-29 | 2019-12-24 | 百度在线网络技术（北京）有限公司 | Component information recording method, device, equipment and readable storage medium |
| CN111275580A (en) * | 2020-03-17 | 2020-06-12 | 云南电网有限责任公司迪庆供电局 | Power distribution network cable positioning monitoring method |
-
2020
- 2020-12-22 CN CN202011525855.8A patent/CN112668620A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503190A (en) * | 2002-11-21 | 2004-06-09 | 深圳矽感科技有限公司 | Cable label readig device and method |
| CN107622253A (en) * | 2017-09-30 | 2018-01-23 | 天津帕比特科技有限公司 | A kind of image-recognizing method based on neural network recognization device type |
| CN109583528A (en) * | 2018-11-05 | 2019-04-05 | 广西电网有限责任公司防城港供电局 | Information machine room cable identification and hunting management method based on seven color two dimensional codes |
| CN110119680A (en) * | 2019-04-03 | 2019-08-13 | 上海工程技术大学 | A kind of electrical cabinet wiring automatic errordetecting system based on image recognition |
| CN110503404A (en) * | 2019-08-27 | 2019-11-26 | 中国联合网络通信集团有限公司 | Asset Tag generation method, device, equipment and storage medium |
| CN110609912A (en) * | 2019-08-29 | 2019-12-24 | 百度在线网络技术（北京）有限公司 | Component information recording method, device, equipment and readable storage medium |
| CN111275580A (en) * | 2020-03-17 | 2020-06-12 | 云南电网有限责任公司迪庆供电局 | Power distribution network cable positioning monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10566771B2 (en) | Method for mounting electric switching systems and assembly support device for simplifying the assembly of such switching systems | |
| US7507113B2 (en) | Wire harness assembly assist program | |
| JP2008235504A (en) | Assembly inspection device | |
| CN105210160A (en) | Wiring harness production mounting | |
| KR102378186B1 (en) | Artificial intelligence vision inspection system for wiring harness | |
| US20190251384A1 (en) | Method for identifying an object and providing information | |
| CN113066195A (en) | Power equipment inspection method and device, AR glasses and storage medium | |
| JP2020527854A (en) | Methods and systems for determining component lighting settings | |
| US11569010B2 (en) | Apparatus, system and method adapted to enable automated wire reading and manufacture of wire harnesses | |
| JP2015061339A (en) | Wire connection work support system | |
| CN116593894A (en) | Automatic test method, system and automatic test cabinet | |
| CN112668620A (en) | Machine vision identification method and device and readable storage medium | |
| CN112275665B (en) | Anti-mixing method applied to PCB electrical measurement | |
| JP6373670B2 (en) | Component recognition data providing method, component recognition data providing device, and component recognition data providing system | |
| US10061782B2 (en) | Method and apparatus for improving the efficiency of remote diagnosis of electronic and other equipment | |
| US11921494B2 (en) | Rapid automation system and method for line clearance | |
| CN109359706A (en) | Merchandise news intelligent identifying system and method | |
| US20230237642A1 (en) | System and method for tracing components of electronic assembly | |
| US11189115B2 (en) | Method of showing explanation about warning light and program for showing explanation about warning light | |
| KR102278309B1 (en) | Smart factory system and operating method for prevention of materials error insert using optical code and image comparison | |
| TWM528432U (en) | Heat inspection apparatus and system including the same | |
| CN113709065A (en) | Automatic detection method, system, equipment and storage medium for panel light of switch | |
| TWI579581B (en) | Heat Inspection Apparatus, System Including The Same, And Method Thereof | |
| JP6550817B2 (en) | Identification device, identification method and traceability system | |
| EP4358020A1 (en) | Method of detecting errors in the placement of elements in the pcb |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |
|
| RJ01 | Rejection of invention patent application after publication |