CN108459023A - Biradical pseudo-capacitance appearance images detection method - Google Patents
Biradical pseudo-capacitance appearance images detection method Download PDFInfo
- Publication number
- CN108459023A CN108459023A CN201810255942.2A CN201810255942A CN108459023A CN 108459023 A CN108459023 A CN 108459023A CN 201810255942 A CN201810255942 A CN 201810255942A CN 108459023 A CN108459023 A CN 108459023A
- Authority
- CN
- China
- Prior art keywords
- flaw
- image
- capacitance
- biradical
- pseudo
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- 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
Abstract
The invention discloses a kind of biradical pseudo-capacitance appearance images detection methods, include the following steps:The first step:Register the deep intensity reference image in each expression face to be measured of capacitance and shallow intensity reference image, setting detection flaw amount upper limit value;Second step:Sample to be tested is placed on a conveyor, and detection device indicates that face carries out capturing image to be checked to capacitance;Third walks:It extracts in image to be checked and is deeper partly used as flaw than deep intensity reference image, detect flaw amount;4th step:Part more shallow than shallow intensity reference image in the image to be checked is extracted as flaw, detects flaw amount;5th step:Measure sample maximum flaw detection values, comprehensive judgement result;6th step:According to judgement as a result, sample product have sorted storage by screening plant.It is compared respectively using sample image and two benchmark images with concentration difference, clarification in certain roles, on the basis of not influencing to differentiate defective products, eliminates the erroneous judgement that concentration difference is brought, effectively improve Detection accuracy.
Description
Technical field
The present invention relates to capacitance appearance detection field more particularly to a kind of biradical pseudo-capacitance appearance images detection methods.
Background technology
When manufacturing capacitance, need to show the information such as capacitance size, operating voltage on capacitance shell, current printing
Technique is to be carried out expression face by print using ink, and this mode of printing can have that expression face is incomplete, reprints, deviates or even nothing
By bad printing phenomenons such as prints, cause message identification unclear, user is in use, be easy to cause misuse, so as to cause with this electricity
The product of container production is unable to normal use or causes the damage of product, or even causes more serious consequence.
Visual inspection is used substantially currently, being detected to the printing of capacitance appearance, detection speed is slow, is easy error,
Some producers then introduce intelligent checking system, can effectively improve detection efficiency and accuracy, what such existing detecting system used
Sample image and a benchmark image are carried out black and white contrast to find out flaw amount by the comparison of single benchmark image, have in high precision,
The ability of height identification, but since existing ink is by the horizontal instability of print, there are concentration difference between non-defective unit, but this concentration difference
When the different difference for being more than non-defective unit with defective products, system is susceptible to erroneous judgement, cannot correctly detect and distinguish non-defective unit and defective products, influences
Detection accuracy.
Invention content
In order to overcome the problems referred above, the present invention provides a kind of high biradical pseudo-capacitance appearance images detection methods of accuracy.
The technical solution adopted by the present invention is:
Biradical pseudo-capacitance appearance images detection method, includes the following steps:
The first step:The benchmark image in capacitance shell expression face to be measured is registered, it is each to indicate that deep intensity reference is registered in face respectively
Image and shallow intensity reference image, setting detection flaw amount upper limit value;
Second step:Sample to be tested is placed on a conveyor, starts detection device and face, which carries out capture and waits, to be indicated to capacitance
Examine image;
Third walks:It extracts than the darker part of deep intensity reference image in the image to be checked, and by extraction unit
It is allocated as flaw, detecting flaw amount;
4th step:Extract part more shallow than the color of shallow intensity reference image in the image to be checked, and by extraction unit
It is allocated as flaw, detecting flaw amount;
5th step:It obtains sample maximum flaw detection values, is compared with flaw amount upper limit value, and provide comprehensive judgement knot
Fruit;
6th step:According to judgement as a result, sample product have sorted storage by screening plant.
Conveying device in the second step is set as endless belt conveyer.
Detection device in the second step includes the CCD camera mounted on conveying device side and top.
Further, it is fixedly installed lighting source above the conveying device.
Further, the CCD camera and lighting source are each attached in mounting bracket.
Screening plant in 6th step includes the bad output mechanism being arranged in conveying device side, described bad
Output mechanism corresponding position is provided with defective product box, and the delivery device tip is provided with non-defective unit case.
The beneficial effects of the invention are as follows:
The biradical pseudo-capacitance appearance images detection method of the present invention is suitable for capacitance ink and is detected by print, using sample image
It is compared respectively with two benchmark images with concentration difference, the two does not interfere with each other, clarification in certain roles, comprehensive judgement, in not shadow
It rings on the basis of differentiating defective products, eliminates the erroneous judgement that concentration difference is brought, effectively improve Detection accuracy.
Description of the drawings
The biradical pseudo-capacitance appearance images detection method of the present invention is described further below in conjunction with attached drawing and example.
Fig. 1 is capacitive detection system structural schematic diagram.
Drawing reference numeral explanation:1, capacitance to be checked;2, endless belt conveyer;3, CCD camera;4, lighting source;5, mounting bracket;
6, bad output mechanism;7, defective product box;8, non-defective unit case.
Specific implementation mode
As shown in Figure 1, one of embodiment provided by the invention, biradical pseudo-capacitance appearance images detection method, including it is following
Step:
The first step:The benchmark image in capacitance shell expression face to be measured is registered, it is each to indicate that deep intensity reference is registered in face respectively
Image and shallow intensity reference image, setting detection flaw amount upper limit value;
Second step:Sample to be tested is placed on a conveyor, starts detection device and face, which carries out capture and waits, to be indicated to capacitance
Examine image;
Third walks:It extracts than the darker part of deep intensity reference image in the image to be checked, and by extraction unit
It is allocated as flaw, detecting flaw amount;
4th step:Extract part more shallow than the color of shallow intensity reference image in the image to be checked, and by extraction unit
It is allocated as flaw, detecting flaw amount;
5th step:It obtains sample maximum flaw detection values, is compared with flaw amount upper limit value, and provide comprehensive judgement knot
Fruit;
6th step:According to judgement as a result, sample product have sorted storage by screening plant.
Conveying device in the second step is set as endless belt conveyer.
Detection device in the second step includes the CCD camera mounted on conveying device side and top.
It is fixedly installed lighting source above the conveying device, for illuminating, substantial light is provided for the CCD camera
Line, convenient for the CCD camera quickly, accurately capture image to be checked.
The CCD camera and lighting source are each attached in mounting bracket, say that CCD camera and lighting source position are relatively fixed
Position provides the light of proper angle and brightness convenient for lighting source.
Screening plant in 6th step includes the bad output mechanism being arranged in conveying device side, described bad
Output mechanism corresponding position is provided with defective product box, and the delivery device tip is provided with non-defective unit case.
When detection, the benchmark image in expression face to be measured registered in advance, each expression face to be measured register two in the detection system
A benchmark image, respectively one deep intensity reference image and a shallow intensity reference image, after the completion of registration, the input setting flaw
Defect amount upper limit value.
The conveying device of promising endless belt conveyer 2 is set in detecting system, and 2 both sides of the endless belt conveyer are provided with detection
Device, the detection device are the CCD camera 3 mounted on 2 both sides of endless belt conveyer, and the CCD camera 3 of both sides is respectively used to shoot
The printing image of capacitance side and top, 3 top of CCD camera are provided with lighting source 4, and CCD camera 3 and lighting source 4 are logical
Cross the fixation of mounting bracket 5,3 downstream of the CCD camera is provided with screening plant, including set up separately 2 both sides of endless belt conveyer not
Good output mechanism 6 and defective product box 7, and the non-defective unit case 8 in 2 end of endless belt conveyer is set.
Capacitance 1 to be checked is placed on and is set as on endless belt conveyer 2, under the movement of endless belt conveyer 2,1 quilt of capacitance to be checked
Send the image zooming-out that capacitance 1 top and side to be checked are carried out to 3 lower section of CCD camera.
For printing the capacitance appearance images that ink is white, the image to be checked and the deep intensity reference image pair that extract
Than only detecting the place whiter than deep intensity reference image, and regard it as flaw, exporting flaw amount, then to be checked by what is extracted
Image and shallow intensity reference image comparison, only detect the place more black than shallow intensity reference image, and regard it as flaw, export the flaw
Defect amount detects maximum flaw amount after comparison, by being compared with the flaw amount upper limit value of setting, comprehensive judgement is as a result, according to sentencing
It is fixed that as a result, defective products can be fallen by bad output mechanism 6 in defective product box 7, non-defective unit then stays on endless belt conveyer 2, send to
In the non-defective unit case 8 of end.
The above, only presently preferred embodiments of the present invention, the invention is not limited in the above embodiments, as long as
It reaches the technique effect of the present invention with identical means, should all belong to the scope of protection of the present invention.
Claims (6)
1. biradical pseudo-capacitance appearance images detection method, which is characterized in that include the following steps:
The first step:The benchmark image in capacitance shell expression face to be measured is registered, it is each to indicate that deep intensity reference image is registered in face respectively
With shallow intensity reference image, setting detection flaw amount upper limit value;
Second step:Sample to be tested is placed on a conveyor, starts detection device and face, which carries out capturing figure to be checked, to be indicated to capacitance
Picture;
Third walks:It extracts than the darker part of deep intensity reference image in the image to be checked, and extraction unit is allocated as
For flaw, flaw amount is detected;
4th step:Part more shallow than the color of shallow intensity reference image in the image to be checked is extracted, and extraction unit is allocated as
For flaw, flaw amount is detected;
5th step:It obtains sample maximum flaw detection values, is compared with flaw amount upper limit value, and provide comprehensive judgement result;
6th step:According to judgement as a result, sample product have sorted storage by screening plant.
2. biradical pseudo-capacitance appearance images detection method according to claim 1, it is characterised in that:Conveying in second step
Device is set as endless belt conveyer.
3. biradical pseudo-capacitance appearance images detection method according to claim 1, it is characterised in that:Detection in second step
Device includes the CCD camera mounted on conveying device side and top.
4. biradical pseudo-capacitance appearance images detection method according to claim 3, it is characterised in that:In the conveying device
Side is fixedly installed lighting source.
5. biradical pseudo-capacitance appearance images detection method according to claim 4, it is characterised in that:The CCD camera and
Lighting source is each attached in mounting bracket.
6. biradical pseudo-capacitance appearance images detection method according to claim 1, it is characterised in that:Screening in 6th step
Device includes the bad output mechanism being arranged in conveying device side, and the bad output mechanism corresponding position is provided with defective products
Case, the delivery device tip are provided with non-defective unit case.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810255942.2A CN108459023A (en) | 2018-03-27 | 2018-03-27 | Biradical pseudo-capacitance appearance images detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810255942.2A CN108459023A (en) | 2018-03-27 | 2018-03-27 | Biradical pseudo-capacitance appearance images detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108459023A true CN108459023A (en) | 2018-08-28 |
Family
ID=63237967
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810255942.2A Withdrawn CN108459023A (en) | 2018-03-27 | 2018-03-27 | Biradical pseudo-capacitance appearance images detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108459023A (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1466678A (en) * | 2001-08-31 | 2004-01-07 | ���µ繤��ʽ���� | Image processing inspection system |
CN1732682A (en) * | 2002-12-27 | 2006-02-08 | 株式会社尼康 | Image processing device and image processing program |
CN101403708A (en) * | 2008-10-31 | 2009-04-08 | 广东正业科技有限公司 | External appearance defect examination method for circuit board |
CN101419176A (en) * | 2007-10-26 | 2009-04-29 | 比亚迪股份有限公司 | Surface flaw detecting method and device |
CN201413296Y (en) * | 2009-06-11 | 2010-02-24 | 浙江创鑫木业有限公司 | Device for detecting board surface flaw |
JP2011158367A (en) * | 2010-02-02 | 2011-08-18 | Hitachi Metals Ltd | Method, program and apparatus for inspection of object to be inspected |
CN102288619A (en) * | 2011-07-01 | 2011-12-21 | 明基材料有限公司 | Method and system for detecting defects of three-dimensional optical film |
CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
CN103808732A (en) * | 2014-01-21 | 2014-05-21 | 图灵视控(北京)科技有限公司 | Capacitance detection system and capacitance detection method based on machine vision |
CN105548216A (en) * | 2016-01-15 | 2016-05-04 | 浙江野马电池有限公司 | Visual detection method for appearance of semi-finished battery |
CN205449820U (en) * | 2016-04-01 | 2016-08-10 | 无锡商业职业技术学院 | Machine vision device of detectable ball bearing defect |
CN106662538A (en) * | 2014-08-27 | 2017-05-10 | 科磊股份有限公司 | Pereater detection |
CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
CN106918600A (en) * | 2017-04-07 | 2017-07-04 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection and labeling method based on machine vision |
CN107389693A (en) * | 2017-06-29 | 2017-11-24 | 西安理工大学 | A kind of printed matter defect automatic testing method based on machine vision |
CN207036716U (en) * | 2017-05-02 | 2018-02-23 | 重庆悦美包装工业有限公司 | A kind of packaging bag defect detecting device |
-
2018
- 2018-03-27 CN CN201810255942.2A patent/CN108459023A/en not_active Withdrawn
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1466678A (en) * | 2001-08-31 | 2004-01-07 | ���µ繤��ʽ���� | Image processing inspection system |
CN1732682A (en) * | 2002-12-27 | 2006-02-08 | 株式会社尼康 | Image processing device and image processing program |
CN101419176A (en) * | 2007-10-26 | 2009-04-29 | 比亚迪股份有限公司 | Surface flaw detecting method and device |
CN101403708A (en) * | 2008-10-31 | 2009-04-08 | 广东正业科技有限公司 | External appearance defect examination method for circuit board |
CN201413296Y (en) * | 2009-06-11 | 2010-02-24 | 浙江创鑫木业有限公司 | Device for detecting board surface flaw |
JP2011158367A (en) * | 2010-02-02 | 2011-08-18 | Hitachi Metals Ltd | Method, program and apparatus for inspection of object to be inspected |
CN102288619A (en) * | 2011-07-01 | 2011-12-21 | 明基材料有限公司 | Method and system for detecting defects of three-dimensional optical film |
CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
CN103808732A (en) * | 2014-01-21 | 2014-05-21 | 图灵视控(北京)科技有限公司 | Capacitance detection system and capacitance detection method based on machine vision |
CN106662538A (en) * | 2014-08-27 | 2017-05-10 | 科磊股份有限公司 | Pereater detection |
CN105548216A (en) * | 2016-01-15 | 2016-05-04 | 浙江野马电池有限公司 | Visual detection method for appearance of semi-finished battery |
CN205449820U (en) * | 2016-04-01 | 2016-08-10 | 无锡商业职业技术学院 | Machine vision device of detectable ball bearing defect |
CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
CN106918600A (en) * | 2017-04-07 | 2017-07-04 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection and labeling method based on machine vision |
CN207036716U (en) * | 2017-05-02 | 2018-02-23 | 重庆悦美包装工业有限公司 | A kind of packaging bag defect detecting device |
CN107389693A (en) * | 2017-06-29 | 2017-11-24 | 西安理工大学 | A kind of printed matter defect automatic testing method based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109084957A (en) | The defects detection and color sorting process and its system of photovoltaic solar crystal-silicon battery slice | |
CN103072718B (en) | Machine vision detection system and method for food packaging production line | |
CN208721366U (en) | The defects detection and colour sorting system of photovoltaic solar crystal-silicon battery slice | |
CN101566582B (en) | Medicine bottle label information online detection system in powder injection production based on mechanical vision | |
CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
CN201819669U (en) | Vision inspection system for ceramic tiles | |
CN207185897U (en) | A kind of full cigarette presentation quality on-line measuring device and its cigarette machine | |
CN205436353U (en) | Bearing sorting machine | |
WO2020103310A1 (en) | Mask defect detection device and method | |
CN104118609A (en) | Labeling quality detecting method and device | |
CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
CN109461156A (en) | The threaded closure plug assembly and detection method of view-based access control model | |
CN103743760A (en) | Circuit detection method for PCB board | |
CN108195847A (en) | A kind of relief pattern Online Video detection device and its detection method | |
Gong et al. | Adaptive visual inspection method for transparent label defect detection of curved glass bottle | |
CN207366475U (en) | A kind of relief pattern Online Video detection device | |
CN209631648U (en) | A kind of device by template pattern on-line checking paper print quality | |
CN108459023A (en) | Biradical pseudo-capacitance appearance images detection method | |
CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
CN204758496U (en) | Annular magnetic core terminal surface visual detection machine | |
CN111458345A (en) | Visual detection mechanism for defects of mask | |
CN208721000U (en) | Product size on-line measuring device | |
CN106645189A (en) | Automatic commutator appearance defect online visual detection system | |
CN207816850U (en) | Sheet-fed printed matter online quality control device | |
CN110605244A (en) | Product quality detection device |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180828 |
|
WW01 | Invention patent application withdrawn after publication |