CN108971025A - A kind of visible detection method and vision detection system - Google Patents
A kind of visible detection method and vision detection system Download PDFInfo
- Publication number
- CN108971025A CN108971025A CN201810942600.8A CN201810942600A CN108971025A CN 108971025 A CN108971025 A CN 108971025A CN 201810942600 A CN201810942600 A CN 201810942600A CN 108971025 A CN108971025 A CN 108971025A
- Authority
- CN
- China
- Prior art keywords
- product
- measured
- detection
- module
- vision
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of visible detection method and vision detection systems, the visible detection method is the following steps are included: detect the position signal of product to be measured, when product to be measured reaches station to be measured, acquire the image information of product to be measured, image information is matched with the multiple normal characteristics of image for surveying product prestored, finds out the normal survey product to match with product to be measured；It transfers and often surveys the corresponding test assignment of product and test parameter；According to the test assignment and test parameter transferred, corresponding testing tool is chosen, vision-based detection is carried out to the product to be measured on station to be measured.The present invention is by the way of vision-based detection, by the image for acquiring the article appearance in hybrid channel in real time, corresponding normal survey product can be matched with automatic identification, it transfers and often surveys the corresponding test assignment of product and test parameter, vision-based detection is carried out to product to be measured, suitable for the detection of different types of product, the application field of vision-based detection is expanded, detection efficiency is improved.
Description
Technical field
The present invention relates to automatic producing technology fields, and in particular to a kind of visible detection method and vision detection system.
Background technique
Machine vision is exactly to replace human eye with machine to measure and judge, i.e., will be ingested mesh by machine vision device
Mark is converted into picture signal, sends dedicated image processing system to, according to the information such as pixel distribution and brightness, color, transformation
At digitized signal；Image processing system carries out various operations to these signals to extract clarification of objective, and then according to differentiation
Result come control scene device action.The core of machine vision is the acquisition and processing of image, and all information derive from
Among image, the quality of image itself is extremely crucial to entire vision system.
Existing vision detection technology has a single function, and a kind of vision inspection apparatus can only generally correspond to a kind of detection individually production
Product, multiple products on a total machine can not be detected and be rejected automatically by vision, and there are certain design limitations
Property, detection efficiency is low.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of visible detection method, it can solve regards in the prior art
Feel the problem that detection method detection mode is single, and application field is limited, detection efficiency is low.In addition, the present invention also provides one kind
Vision detection system.
To solve the above-mentioned problems, the invention adopts the following technical scheme:
The first aspect of the present invention provides a kind of visible detection method, comprising the following steps:
The position signal of step 1, detection product to be measured, when product to be measured reaches station to be measured, the image for acquiring product to be measured is believed
Breath, by image information with prestore it is multiple it is normal survey products characteristics of image match, find out match with product to be measured it is normal
Survey product；
Step 2 is transferred and often surveys the corresponding test assignment of product and test parameter；
The test assignment and test parameter that step 3, basis are transferred, choose corresponding testing tool, to be measured on station to be measured
Product carries out vision-based detection.
As a preferred technical solution, after the step 3 further include: if vision-based detection product to be measured is qualified products,
Then product to be measured is automatically into next production process；If vision-based detection product to be measured is substandard product, rejecting mechanism is automatic
Reject underproof product to be measured.
As a preferred technical solution, in the step 1, the image information of product to be measured is produced with the multiple normal surveys prestored
When the characteristics of image of product is matched, if matching is unsuccessful, a normal survey product prestored is created, the typing normal survey product
Characteristics of image, test assignment, test parameter and testing tool repeat step 1.
The test assignment includes detecting the appearance of product to be measured, color with main feature as a preferred technical solution,
At least one of the presence or absence of；The test parameter includes detecting at least one of color or brightness of light source, point of camera
At least one of resolution or time for exposure.
The color of the step detection light source and the adjusting method of brightness include: as a preferred technical solution,
Obtain the color and luminance information of product to be measured；
According to the color and luminance information of product to be measured, Auto-matching optimum color and brightness, to detection light source be adjusted and
Control.
The second aspect of the present invention provides a kind of vision detection system, applied to above-mentioned visible detection method, comprising:
Position acquisition module calls positioning tool to obtain the signal whether product to be measured reaches station to be measured；Image collection module,
For acquiring the external image of product to be measured；The pre- storing module of image, for being stored to the normal characteristics of image for surveying product；Product
Matching module is matched for the external image to product to be measured with normal product of surveying；Test assignment and parameter memory module are used
The test assignment and test parameter of product Corresponding matching are often surveyed in storage；Information calling module is used for from test assignment and parameter
It is transferred in memory module and often surveys the corresponding test assignment of product and test parameter；Control module is detected, mould is matched according to product
The recognition result of block calls corresponding detection instrument, and detection configuration parameter is loaded from information calling module to vision-based detection
Tool carries out vision-based detection to product to be measured；Light source control module, for carrying out the adjusting of color and brightness to detection light source.
The positioning tool includes positioning tool based on contour feature and based on characteristic point as a preferred technical solution,
Positioning tool
As a preferred technical solution, the detection control module include dimensional measurement module, bar code recognition module, color and
Gray scale detection module, Region Matching detection module, profile defects detection module, determines product hierarchy to be measured at character recognition module
Grade determination module, the data outputting module that is exported for will test data.
It as a preferred technical solution, further include rejecting module, the rejecting module connects the data outputting module, uses
It is rejected in substandard product.
The present invention, by acquiring the image of the article appearance in hybrid channel in real time, is utilized by the way of vision-based detection
Image adaptive algorithm can match corresponding normal survey product with automatic identification, transfer often survey the corresponding test assignment of product with
Test parameter carries out vision-based detection to product to be measured, when matching unsuccessful, creates a new normal survey product information, can
Suitable for the detection of different types of product, the application field of vision-based detection is expanded, detection efficiency is improved.
Detailed description of the invention
Invention is further described in detail with specific embodiment with reference to the accompanying drawing.
Fig. 1 is the flow diagram of visible detection method of the present invention；
Fig. 2 is the flow diagram that light source adjusting method is detected in visible detection method of the present invention；
Fig. 3 is the structural schematic diagram of vision detection system of the present invention；
Fig. 4 is the structural schematic diagram that control module is detected in vision detection system of the present invention.
Wherein, appended drawing reference is described as follows: position acquisition module 1, image collection module 2, product matching module 3,
Information calling module 4, detection control module 5, rejecting module 6, the pre- storing module 7 of image, test assignment and parameter memory module 8,
Light source control module 9, dimensional measurement module 10, data outputting module 11, bar code recognition module 12, color and gray scale detection mould
Block 13, grade determination module 14, Region Matching detection module 15, character recognition module 16, profile defects detection module 17.
Specific embodiment
As shown in Figure 1, a kind of visible detection method, comprising the following steps:
The position signal of step 1, detection product to be measured, when product to be measured reaches station to be measured, the image for acquiring product to be measured is believed
Breath, by image information with prestore it is multiple it is normal survey products characteristics of image match, find out match with product to be measured it is normal
Survey product；If matching is unsuccessful, a normal survey product prestored, the typing normal characteristics of image for surveying product, test times are created
Business, test parameter and testing tool repeat step 1.
Step 2 is transferred and often surveys the corresponding test assignment of product and test parameter；
The test assignment and test parameter that step 3, basis are transferred, choose corresponding testing tool, to be measured on station to be measured
Product carries out vision-based detection.
If step 4, vision-based detection product to be measured are qualified products, product to be measured is automatically into next production process；If
Vision-based detection product to be measured is substandard product, then the underproof product to be measured of rejecting mechanism automatic rejection.
The test assignment includes detecting the appearance of product to be measured, color at least one of the presence or absence of main feature；
The test parameter includes color or at least one of the brightness for detecting light source, the resolution ratio of camera or in the time for exposure extremely
Few one kind.
As shown in Fig. 2, the color of the step detection light source and the adjusting method of brightness include:
Obtain the color and luminance information of product to be measured；
According to the color and luminance information of product to be measured, Auto-matching optimum color and brightness, to detection light source be adjusted and
Control.
As shown in figure 3, a kind of vision detection system, comprising: position acquisition module 1 calls positioning tool to obtain production to be measured
Whether product reach the signal of station to be measured；Image collection module 2, for acquiring the external image of product to be measured；Image prestores mould
Block 7, for being stored to the normal characteristics of image for surveying product；Product matching module 3, for product to be measured external image with
Product is often surveyed to be matched；Test assignment and parameter memory module 8, for store often survey product Corresponding matching test assignment and
Test parameter；Information calling module 4 often surveys the corresponding survey of product for transferring from test assignment and parameter memory module 8
Trial business and test parameter；It detects control module 5 and corresponding detection work is called according to the recognition result of product matching module 3
Tool loads detection configuration parameter to vision-based detection tool from information calling module 4, carries out vision-based detection to product to be measured；Light
Source control module 9, for carrying out the adjusting of color and brightness to detection light source；Module 6 is rejected, the rejecting module 6 connects institute
Data outputting module 11 is stated, for rejecting to substandard product.The positioning tool includes the positioning based on contour feature
Tool and positioning tool based on characteristic point.
As shown in figure 4, the detection control module 5 include dimensional measurement module 10, bar code recognition module 12, color and
Gray scale detection module 13, character recognition module 16, Region Matching detection module 15, profile defects detection module 17, judgement are to be measured
The grade determination module 14 of product hierarchy, the data outputting module 11 exported for will test data.
Use above specific case is illustrated the present invention, is merely used to help understand the present invention, not to limit
The system present invention.For those skilled in the art, according to the thought of the present invention, can also make several simple
It deduces, deform or replaces.
Claims (9)
1. a kind of visible detection method, which comprises the following steps:
The position signal of step 1, detection product to be measured, when product to be measured reaches station to be measured, the image for acquiring product to be measured is believed
Breath, by image information with prestore it is multiple it is normal survey products characteristics of image match, find out match with product to be measured it is normal
Survey product；
Step 2 is transferred and often surveys the corresponding test assignment of product and test parameter；
The test assignment and test parameter that step 3, basis are transferred, choose corresponding testing tool, to be measured on station to be measured
Product carries out vision-based detection.
2. a kind of visible detection method as claimed in claim, it is characterised in that: after the step 3 further include: if vision
Detecting product to be measured is qualified products, then product to be measured is automatically into next production process；If vision-based detection product to be measured is not
Qualified products, the then underproof product to be measured of rejecting mechanism automatic rejection.
3. a kind of visible detection method as described in claim 1, it is characterised in that: in the step 1, by the figure of product to be measured
When being matched as information with the multiple normal characteristics of image for surveying products prestored, if matching is unsuccessful, newly-built one is prestored
Product is often surveyed, typing normal characteristics of image, test assignment, test parameter and the testing tool for surveying product repeats step 1.
4. a kind of visible detection method as described in claim 1, it is characterised in that: the test assignment includes detecting production to be measured
The appearances of product, color are at least one of the presence or absence of main feature；The test parameter includes the color or bright for detecting light source
At least one of degree, at least one of the resolution ratio of camera or time for exposure.
5. a kind of visible detection method as claimed in claim 4, it is characterised in that: detect the color of light source in the test parameter
Coloured silk and the adjusting method of brightness include:
Obtain the color and luminance information of product to be measured；
According to the color and luminance information of product to be measured, Auto-matching optimum color and brightness, to detection light source be adjusted and
Control.
6. a kind of vision detection system is applied to the described in any item visible detection methods of claim 1-5, which is characterized in that
Include:
Position acquisition module calls positioning tool to obtain the signal whether product to be measured reaches station to be measured；Image collection module,
For acquiring the external image of product to be measured；The pre- storing module of image, for being stored to the normal characteristics of image for surveying product；Product
Matching module is matched for the external image to product to be measured with normal product of surveying；Test assignment and parameter memory module are used
The test assignment and test parameter of product Corresponding matching are often surveyed in storage；Information calling module is used for from test assignment and parameter
It is transferred in memory module and often surveys the corresponding test assignment of product and test parameter；Control module is detected, mould is matched according to product
The recognition result of block calls corresponding detection instrument, and detection configuration parameter is loaded from information calling module to vision-based detection
Tool carries out vision-based detection to product to be measured；Light source control module, for carrying out the adjusting of color and brightness to detection light source.
7. a kind of vision detection system as claimed in claim 6, it is characterised in that: the positioning tool includes special based on profile
The positioning tool of sign and the positioning tool based on characteristic point.
8. a kind of vision detection system as claimed in claim 6, it is characterised in that: the detection control module includes that geometry is surveyed
Measure module, bar code recognition module, color and gray scale detection module, character recognition module, Region Matching detection module, profile
Defects detection module, the grade determination module for determining product hierarchy to be measured, the data output exported for will test data
Module.
9. a kind of vision detection system as claimed in claim 6, it is characterised in that: further include rejecting module, the rejecting mould
Block connects the data outputting module, for rejecting to substandard product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810942600.8A CN108971025A (en) | 2018-08-17 | 2018-08-17 | A kind of visible detection method and vision detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810942600.8A CN108971025A (en) | 2018-08-17 | 2018-08-17 | A kind of visible detection method and vision detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108971025A true CN108971025A (en) | 2018-12-11 |
Family
ID=64554069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810942600.8A Pending CN108971025A (en) | 2018-08-17 | 2018-08-17 | A kind of visible detection method and vision detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108971025A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949362A (en) * | 2019-03-01 | 2019-06-28 | 广东九联科技股份有限公司 | A kind of material visible detection method |
| CN110570146A (en) * | 2019-08-23 | 2019-12-13 | 格力电器（武汉）有限公司 | Product sorting method and device and computer readable storage medium |
| CN110880179A (en) * | 2019-12-20 | 2020-03-13 | 易思维（杭州）科技有限公司 | Method for testing working state of visual sensor |
| CN111389750A (en) * | 2020-04-07 | 2020-07-10 | 苏州瀚德光电科技有限公司 | Vision measurement system and measurement method |
| CN111652868A (en) * | 2020-06-01 | 2020-09-11 | 珠海格力智能装备有限公司 | Method and device for setting vision measurement system and method for measuring product |
| CN112077010A (en) * | 2020-08-29 | 2020-12-15 | 胡玮 | Separating mechanical arm based on visual sensing |
| CN114273261A (en) * | 2021-11-10 | 2022-04-05 | 上海艾豚科技有限公司 | Method and system for simultaneously detecting multiple workpiece kits of automotive interior parts |
| CN117929975A (en) * | 2024-03-25 | 2024-04-26 | 四川易景智能终端有限公司 | PCBA board testing method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4703859A (en) * | 1986-10-29 | 1987-11-03 | Pynsky Raymond F | Apparatus and method for testing a can seam |
| CN2740303Y (en) * | 2004-11-16 | 2005-11-16 | 许大红 | Granular material color selector |
| CN1893358A (en) * | 2005-07-07 | 2007-01-10 | 英业达股份有限公司 | Software premounting system and method |
| CN102253048A (en) * | 2011-04-29 | 2011-11-23 | 惠州市钧悦科技有限公司 | Machine vision detection method and system for detection of various products |
| CN204353119U (en) * | 2014-11-27 | 2015-05-27 | 合肥美亚光电技术股份有限公司 | Separation system |
| CN106383131A (en) * | 2016-09-20 | 2017-02-08 | 珠海格力电器股份有限公司 | Visual detection method, device and system for printed matter |
| CN106383121A (en) * | 2016-06-22 | 2017-02-08 | 深圳市联君科技股份有限公司 | Visual detection method and system self-adaptive to multiple brands |
| CN107223257A (en) * | 2017-04-26 | 2017-09-29 | 深圳市汇顶科技股份有限公司 | Method of testing, test server and system |
| CN107470181A (en) * | 2017-09-25 | 2017-12-15 | 中国电力科学研究院 | One kind tears back electric energy meter sorting equipment and method open |
-
2018
- 2018-08-17 CN CN201810942600.8A patent/CN108971025A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4703859A (en) * | 1986-10-29 | 1987-11-03 | Pynsky Raymond F | Apparatus and method for testing a can seam |
| CN2740303Y (en) * | 2004-11-16 | 2005-11-16 | 许大红 | Granular material color selector |
| CN1893358A (en) * | 2005-07-07 | 2007-01-10 | 英业达股份有限公司 | Software premounting system and method |
| CN102253048A (en) * | 2011-04-29 | 2011-11-23 | 惠州市钧悦科技有限公司 | Machine vision detection method and system for detection of various products |
| CN204353119U (en) * | 2014-11-27 | 2015-05-27 | 合肥美亚光电技术股份有限公司 | Separation system |
| CN106383121A (en) * | 2016-06-22 | 2017-02-08 | 深圳市联君科技股份有限公司 | Visual detection method and system self-adaptive to multiple brands |
| CN106383131A (en) * | 2016-09-20 | 2017-02-08 | 珠海格力电器股份有限公司 | Visual detection method, device and system for printed matter |
| CN107223257A (en) * | 2017-04-26 | 2017-09-29 | 深圳市汇顶科技股份有限公司 | Method of testing, test server and system |
| CN107470181A (en) * | 2017-09-25 | 2017-12-15 | 中国电力科学研究院 | One kind tears back electric energy meter sorting equipment and method open |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949362A (en) * | 2019-03-01 | 2019-06-28 | 广东九联科技股份有限公司 | A kind of material visible detection method |
| CN110570146A (en) * | 2019-08-23 | 2019-12-13 | 格力电器（武汉）有限公司 | Product sorting method and device and computer readable storage medium |
| CN110570146B (en) * | 2019-08-23 | 2023-07-18 | 格力电器（武汉）有限公司 | Product sorting method and device and computer readable storage medium |
| CN110880179A (en) * | 2019-12-20 | 2020-03-13 | 易思维（杭州）科技有限公司 | Method for testing working state of visual sensor |
| CN111389750A (en) * | 2020-04-07 | 2020-07-10 | 苏州瀚德光电科技有限公司 | Vision measurement system and measurement method |
| CN111389750B (en) * | 2020-04-07 | 2022-04-12 | 苏州瀚德光电科技有限公司 | Vision measurement system and measurement method |
| CN111652868A (en) * | 2020-06-01 | 2020-09-11 | 珠海格力智能装备有限公司 | Method and device for setting vision measurement system and method for measuring product |
| CN112077010A (en) * | 2020-08-29 | 2020-12-15 | 胡玮 | Separating mechanical arm based on visual sensing |
| CN114273261A (en) * | 2021-11-10 | 2022-04-05 | 上海艾豚科技有限公司 | Method and system for simultaneously detecting multiple workpiece kits of automotive interior parts |
| CN117929975A (en) * | 2024-03-25 | 2024-04-26 | 四川易景智能终端有限公司 | PCBA board testing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108971025A (en) | A kind of visible detection method and vision detection system | |
| CN102253048B (en) | Machine vision detection method and system for detection of various products | |
| CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
| CN111047655B (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
| KR102378186B1 (en) | Artificial intelligence vision inspection system for wiring harness | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| CN108629319B (en) | Image detection method and system | |
| CN106383121B (en) | It is a kind of can adaptive multi-brand visible detection method and system | |
| CN109089013A (en) | A kind of multiple light courcess detection image acquisition methods and Machine Vision Inspecting System | |
| CN206132657U (en) | Gilt quality intelligent detecting system based on machine vision | |
| CN109685760A (en) | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB | |
| CN103744120A (en) | Method and device for assisting identification of contraband | |
| CN112394064A (en) | Point-line measuring method for screen defect detection | |
| CN109444172A (en) | A kind of automatic optical detection device and its method suitable for artificial intelligence detection PCB | |
| CN110018172A (en) | Products detection system and method | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN105844282A (en) | Method for detecting defects of fuel injection nozzle O-Ring through line scanning camera | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| KR20180092033A (en) | Component registration device | |
| CN104637833B (en) | Crystal grain selection method and bad crystal map generation method | |
| CN107545565B (en) | Solar screen plate detection method | |
| CN117197789A (en) | Curtain wall frame identification method and system based on multi-scale boundary feature fusion | |
| CN110210401B (en) | Intelligent target detection method under weak light | |
| CN109635684A (en) | A kind of food traceability system | |
| CN110334713A (en) | A kind of intelligent identification Method of internal lining paper product type |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |