CN106970090A - Embryo cloth defective vision detection device and method - Google Patents

Embryo cloth defective vision detection device and method Download PDF

Info

Publication number
CN106970090A
CN106970090A CN201710287368.4A CN201710287368A CN106970090A CN 106970090 A CN106970090 A CN 106970090A CN 201710287368 A CN201710287368 A CN 201710287368A CN 106970090 A CN106970090 A CN 106970090A
Authority
CN
China
Prior art keywords
defect
embryo cloth
detection
size
detection device
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
Application number
CN201710287368.4A
Other languages
Chinese (zh)
Inventor
李力
黄坤山
王华龙
李志鹏
彭博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Original Assignee
Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute filed Critical Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Priority to CN201710287368.4A priority Critical patent/CN106970090A/en
Publication of CN106970090A publication Critical patent/CN106970090A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Treatment Of Fiber Materials (AREA)
  • Ink Jet (AREA)

Abstract

For the deficiency of existing detection technique, with reference to all kinds of weaving mill's demands, the invention provides a kind of embryo cloth defective vision detection device, it at least includes vision-based detection platform and ink-jet marking mechanism, and a kind of embryo cloth Inspection Algorithm progress defects detection identification based on multithreading has been used in combination by vision-based detection platform and has been marked by ink-jet marking mechanism.It can realize embryo cloth defects detection automatically and preserve defective data in the local database, its detection speed and recall rate are far above artificial detection, so as to increase the production efficiency of textile mills, hand labor intensity is greatly reduced, labour expenses of the textile mills in terms of quality testing are reduced.

Description

Embryo cloth defective vision detection device and method
Technical field
The invention belongs to textile technology field, and in particular to one kind knitting embryo cloth visual detection equipment and method.
Background technology
In textile industry, there is flaw in cloth, then price will reduce 45%-65%, and fabric defects has a strong impact on weaving row Industry income.Therefore, Fabric Defect detection is one of major tasks of textile mills.For a long time, cloth detection is general by people Work is completed.Artificial detection speed is general per minute at 15-20 meters.Artificial detection relies on the experience and qualification of perching personnel, Evaluation criterion is unstable inconsistent, thus often produces flase drop and missing inspection, and skilled perching personnel can only also have found about 70% Fault.In addition, cloth defects detection is a heavy tasteless manual labor for workman, and greatly perching is injured The eyesight of workman.The use of automatic piece goods detecting system is that production efficiency improves in textile mills, saves human cost, industrial transformation upgrading The only way which must be passed.
In automatic Check cloth machine field, Domestic and abroad disparity is huge, is especially embodied in accuracy of detection and speed.This present situation with The present situation of machine vision technique has certain relation, i.e. software development kit or platform all to be controlled by external several companies, Domestic no or rare perfect high performance image processing software bag and development platform.In hardware aspect, the current country is just Gradually pursuing, the hardware performance of fewer companies has reached international standards, but core component is also the absence of independence.It is based on This present situation, the data that domestic automatic Check Bu Ji producers can find is considerably less, there is be discussed in detail less.Both at home and abroad can Automatic Check cloth machine can be provided by finding relevant manufacturers, but its technology maturity is not enough, and price height enterprise, stability difference turns into automatic The huge obstacle of Check cloth machine penetrations and promotions.
The content of the invention
For the deficiency of existing detection technique, with reference to all kinds of weaving mill's demands, regarded the invention provides a kind of embryo cloth defect Feel detection device, embryo cloth defects detection can be realized automatically and is preserved defective data in the local database, its detection speed With recall rate far above artificial detection, so as to increase the production efficiency of textile mills, hand labor intensity is greatly reduced, is reduced Labour expenses of the textile mills in terms of quality testing.Present invention also offers a kind of embryo cloth quality inspection based on multithreading simultaneously Method of determining and calculating framework so that the real-time of algorithm is guaranteed.
A kind of embryo cloth defective vision detection device, including vision-based detection platform, industrial computer and display, telltale, spray Black marking mechanism, operating desk, many side rollers, cloth, edge aligning mechanism, winding cloth, light source bracket, unreel cloth, unreel Roller, integral support.
The vision-based detection platform, which includes many line scan cameras, can cover the line style direct projection bar light of whole detection wide cut. The ink-jet marking mechanism is that magnetic valve is at intervals of 100-150 millimeters into nozzle array by plurality of electromagnetic valve group.
After vision-based detection platform is handled image, the position where flaw point is obtained, flaw defect position is transmitted To the control system of ink-jet marking mechanism, defective locations are marked for control system control ink-jet marking mechanism
The embryo cloth defective vision detection device has two kinds of mode of operations, and pattern one is shutdown mode, that is, detects defect Shut down at once afterwards, notify staff to come to handle, shutdown mode comprises the following steps:
Step one:Feeding is initialized, guides the leftover of bolt of cloth successively to pass through punishment in advance side roller II (12), punishment in advance exhibition by staff The cloth of side roller I (11) and winding side roller (14), manually about 1.5 meters of length of winding, forms winding cloth (13)
Step 2:Start detecting system.
Step 3:Single frames input picture is obtained, is schemed by a kind of embryo cloth Inspection Algorithm framework based on multithreading As processing.
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in Local data base, sends defect alarm command to control system, performs step 5.If there is no defect, then step 6 is performed.
Step 5:Control system receives defect alarm command, shuts down at once, is alarmed by warning lamp (9), notifies live work Come to handle as personnel.
Step 6:If detection is not completed also, perform step 3 and start next circulation.If detection is completed, printing detection Report.
The embryo cloth defective vision detection device mode of operation two is automatic marking mode, is comprised the following steps:
Step one:Feeding is initialized, guides the leftover of bolt of cloth successively to pass through punishment in advance side roller II (12), punishment in advance exhibition by staff The cloth of side roller I (11) and winding side roller (14), manually about 1.5 meters of length of winding, forms winding cloth (13)
Step 2:Start detecting system.
Step 3:Single frames input picture is obtained, is schemed by a kind of embryo cloth Inspection Algorithm framework based on multithreading As processing.
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in Local data base, sends defective locations data to control system, performs step 5.If there is no defect, then step 6 is performed.
Step 5:Control system control ink jet printing mechanism (3) injection can fading ink defective locations are marked.
Step 6:If detection is not completed also, perform step 3 and start next circulation.If detection is completed, printing detection Report.
A kind of embryo cloth Inspection Algorithm framework based on multithreading, comprises the following steps:
Step one:Input picture is obtained.Camera input image I is obtained from imaging systeminput, input image size for (m × 1024)×(n×1024)
Step 2:Image block.Input picture is divided into m1×n1Individual unit_size × unit_size cell picture
Wherein 0≤i≤m1,0≤j≤n1
Step 3:Newly-built size is m1×n1Thread queue Ti,j, to cell pictureCarry out block texture special Levy extraction.Obtain block texture feature vectorWherein 0≤i≤m1,0≤j≤ n1
Step 4:It is rightFurther subdivision, is divided into size for patch_size × patch_size, overlay region Domain is the fritter that size is over_size
Wherein
Step 5:WithTexture boot vector is tieed up, each is calculated Grain distribution, obtains shortage probability distributed image defect_priori,j
Step 6:To defect_priori,jCarry out binary conversion treatment and obtain defect_segprior i,j, extract shortage probability Pixel more than 75%, such as following formula:
According to defect_segprior I, jThe defect area size defect_area being partitioned intoi,jWith defect number defect_ counti,jJudgeIn whether there is defect, and defect information write into Databasce is preserved.If meeting following Condition, then it is assumed thatMiddle existing defects, such as following formula:
Wherein Tr is the defect threshold value that user sets.
Step 7:Discharge thread queuing memory Ti,j
Brief description of the drawings
Fig. 1 is the integrally-built front view of embryo cloth defective vision detection device
Fig. 2 is the integrally-built rear view of embryo cloth defective vision detection device
The partial view of Fig. 3 embryo cloth defective vision detection device vision-based detection platforms and ink jet printing mechanism
Fig. 4 is the system flow chart under shutdown mode
Fig. 5 is the system flow chart under automatic marking mode
Fig. 6 is a kind of embryo cloth Inspection Algorithm block flow diagram based on multithreading
Label declaration:
1. vision-based detection platform, 2. industrial computers and display, 3. ink jet printing mechanism, 4. operating desks, 5. winding sides Roller, 6. punishment in advance cloth, 7. edge aligning mechanisms, 8. winding cloth, 9. telltales, 10. light source brackets, 11. punishment in advance side roller I, 12. punishment in advance side roller II, 13. winding cloth, 14. winding cloth side rollers, 15. integral supports, 16. encoders, 17. regard Feel hardware platform magnification region, 18. cloth to be checked, 19. light sources, 20. industrial cameras, the 21. industrial camera visuals field, 22. ink nozzles.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail:
For the deficiency of existing detection technique, with reference to all kinds of weaving mill's demands, regarded the invention provides a kind of embryo cloth defect Feel detection device, embryo cloth defects detection can be realized automatically and is preserved defective data in the local database, its detection speed With recall rate far above artificial detection, so as to increase the production efficiency of textile mills, hand labor intensity is greatly reduced, is reduced Labour expenses of the textile mills in terms of quality testing.Present invention also offers a kind of embryo cloth quality inspection based on multithreading simultaneously Method of determining and calculating framework so that the real-time of algorithm is guaranteed.Scheme highest detection speed reaches 6.5 meter per seconds, maximum detection wide cut For 2 meters.
The vision-based detection platform, which includes 4 line scan cameras, can cover the line style direct projection bar light of whole detection wide cut. The ink-jet marking mechanism is to constitute nozzle array by multiple valves, and nozzle pitch is 120 millimeters.
After vision-based detection platform (1) is handled image, the position where flaw point is obtained, flaw defect position is passed The control system of ink-jet marking mechanism (3) is passed, defective locations are marked for control system control ink-jet marking mechanism.
The embryo cloth defective vision detection device has two kinds of mode of operations, and pattern one is shutdown mode, is illustrated in figure 4 mould The flow chart of formula one, that is, detect after defect and shut down at once, notifies staff to come to handle, shutdown mode comprises the following steps:
Step one:Feeding is initialized, guides the leftover of bolt of cloth successively to pass through punishment in advance side roller II (12), punishment in advance exhibition by staff The cloth of side roller I (11) and winding side roller (14), manually about 1.5 meters of length of winding, forms winding cloth (13)
Step 2:Start detecting system.
Step 3:IMAQ is carried out by encoder triggering camera, single frames input picture is obtained afterwards, by one kind based on many The embryo cloth Inspection Algorithm framework of thread carries out image procossing.
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in Local data base, sends defect alarm command to control system, performs step 5.If there is no defect, then step 6 is performed.
Step 5:Control system receives defect alarm command, shuts down at once, is alarmed by warning lamp (9), notifies live work Come to handle as personnel.
Step 6:If detection is not completed also, perform step 3 and start next circulation.If detection is completed, printing detection Report.
The embryo cloth defective vision detection device mode of operation two is automatic marking mode, is illustrated in figure 5 pattern second-rate Cheng Tu, comprises the following steps:
Step one:Feeding is initialized, guides the leftover of bolt of cloth successively to pass through punishment in advance side roller II (12), punishment in advance exhibition by staff The cloth of side roller I (11) and winding side roller (14), manually about 1.5 meters of length of winding, forms winding cloth (13)
Step 2:Start detecting system.
Step 3:Single frames input picture is obtained, is schemed by a kind of embryo cloth Inspection Algorithm framework based on multithreading As processing.
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in Local data base, sends defective locations data to control system, performs step 5.If there is no defect, then step 6 is performed.
Step 5:Control system control ink jet printing mechanism (3) injection can fading ink defective locations are marked.
Step 6:If detection is not completed also, perform step 3 and start next circulation.If detection is completed, printing detection Report.
A kind of embryo cloth Inspection Algorithm framework based on multithreading, is illustrated in figure 6 algorithm flow chart, including following step Suddenly:
Step one:Input picture is obtained.Camera input image I is obtained from imaging systeminput, input image size for (m × 1024) × (n × 1024), wherein m=4, n=1.
Step 2:Image block.Input picture is divided into m1×n1Individual unit_size × unit_size cell picture
Wherein 0≤i≤m1,0≤j≤n1。m1=16, n1=4, unit_size=256
Step 3:Newly-built size is m1×n1Thread queue Ti,j, to cell pictureCarry out block texture special Levy extraction.Obtain block texture feature vectorWherein 0≤i≤m1,0≤j≤ n1
Step 4:It is rightFurther subdivision, is divided into size for patch_size × patch_size, overlay region Domain is the fritter that size is over_sizeWherein patch_size=16, over_size=8
Wherein 0≤u≤30,0≤v≤30
Step 5:WithTexture boot vector is tieed up, each is calculated Grain distribution, obtains shortage probability distributed image defect_priori,j
Step 6:To defect_priori,jCarry out binary conversion treatment and obtain defect_segprior i,j, extract shortage probability Pixel more than 75%, such as following formula:
Wherein, unitsize=256
According to defect_segprior i,jThe defect area size defect_area being partitioned intoi,jWith defect number defect_ counti,jJudgeIn whether there is defect, and defect information write into Databasce is preserved.If meeting following Condition, then it is assumed thatMiddle existing defects, such as following formula:
Wherein Tr is the defect threshold value that user sets.
Tr=25 in this example, corresponds to actual flaw size for 0.5mm × 0.5mm
Step 7:Discharge thread queuing memory Ti,j

Claims (5)

1. a kind of embryo cloth defective vision detection device, including vision-based detection platform and ink-jet marking mechanism, it is characterised in that
The vision-based detection platform includes many line scan cameras, and the ink-jet marking mechanism includes the spray that plurality of electromagnetic valve is controlled Mouth array and control system,
The vision-based detection platform scanner simultaneously obtains the image of the embryo cloth and the flaw point of the embryo cloth is obtained after being handled The position at place, and the position where flaw point is passed to the control system of ink-jet marking mechanism, control system control ink-jet The position is marked marking mechanism.
2. embryo cloth defective vision detection device as claimed in claim 1, the embryo cloth defective vision detection device has two kinds of works Operation mode, mode of operation one is shutdown mode, and mode of operation two is automatic marking mode.
3. embryo cloth defective vision detection device as claimed in claim 2, wherein the shutdown mode comprises the following steps:
Step one:Initialize feeding;
Step 2:Start the embryo cloth defective vision detection device;
Step 3:Single frames input picture is obtained, image procossing is carried out by the embryo cloth Inspection Algorithm based on multithreading;
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in locally Database, sends defect alarm command to control system, performs step 5, if there is no defect, then perform step 6;
Step 5:Control system receives defect alarm command, shuts down at once, is alarmed by warning lamp, notifies field personnel Come to handle;
Step 6:If detection is not completed also, step 3 is performed, if detection is completed, examining report is printed.
4. embryo cloth defective vision detection device as claimed in claim 2, wherein automatic marking mode comprises the following steps:
Step one:Initialize feeding;
Step 2:Start the embryo cloth defective vision detection device;
Step 3:Single frames input picture is obtained, image procossing is carried out by the embryo cloth Inspection Algorithm based on multithreading;
Step 4:Judge to whether there is defect in single frames input picture, if defect is present, defective data is saved in locally Database, sends defective locations data to control system, performs step 5, if there is no defect, then perform step 6;
Step 5:The injection of control system control ink-jet marking mechanism can fading ink defective locations are marked;
Step 6:If detection is not completed also, step 3 is performed, if detection is completed, examining report is printed.
5. the embryo cloth defective vision detection device as described in claim 3 or 4, wherein the embryo cloth quality based on multithreading Detection algorithm, comprises the following steps:
Step one:Input picture is obtained, and input picture I is obtained from the vision-based detection platforminput, input image size for (m × 1024)×(n×1024);
Step 2:Image block, is divided into m by input picture1×n1Individual, size is
Unit_size × unit_size cell pictureWherein 0≤i≤m1,0≤j≤n1,Unit_size=256 or 128;
Step 3:Newly-built size is m1×n1Thread queue Ti,j, to cell pictureBlock textural characteristics are carried out to carry Take, obtain block texture feature vector
Step 4:It is rightFurther subdivision, is divided into that size is patch_size × patch_size and overlapping region is Size is over_size fritter
Wherein
0 ≤ u ≤ u n i t _ s i z e - p a t c h _ s i z e p a t c h _ s i z e - o v e r _ s i z e , 0 ≤ v ≤
u n i t _ s i z e - p a t c h _ s i z e p a t c h _ s i z e - o v e r _ s i z e ;
Step 5:WithFor dimension texture boot vector, each is calculatedTexture Distribution, obtains shortage probability distributed image defect_priori,j
Step 6:According to defect_priori,jJudgeIn whether there is defect, by defect information write into Databasce Preserved;
Step 7:Discharge thread queuing memory Ti,j
CN201710287368.4A 2017-04-27 2017-04-27 Embryo cloth defective vision detection device and method Pending CN106970090A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710287368.4A CN106970090A (en) 2017-04-27 2017-04-27 Embryo cloth defective vision detection device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710287368.4A CN106970090A (en) 2017-04-27 2017-04-27 Embryo cloth defective vision detection device and method

Publications (1)

Publication Number Publication Date
CN106970090A true CN106970090A (en) 2017-07-21

Family

ID=59332832

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710287368.4A Pending CN106970090A (en) 2017-04-27 2017-04-27 Embryo cloth defective vision detection device and method

Country Status (1)

Country Link
CN (1) CN106970090A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107703152A (en) * 2017-10-27 2018-02-16 深圳精创视觉科技有限公司 The automatic indication device of optical film shortcoming
CN109145985A (en) * 2018-08-21 2019-01-04 佛山职业技术学院 A kind of detection and classification method of Fabric Defects Inspection
CN109283193A (en) * 2018-10-22 2019-01-29 上海易清智觉自动化科技有限公司 Cotton tyre cord flaw on-line checking and identity device
CN110702691A (en) * 2019-10-29 2020-01-17 无锡精质智能装备有限公司 Fabric quality detection system
CN110793973A (en) * 2019-11-12 2020-02-14 广东骉马机器人科技有限公司 Leather surface defect detecting system
CN114397308A (en) * 2022-03-25 2022-04-26 江苏贝尔特福新材料有限公司 Detection equipment for automatically identifying fabric flaws and use method

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102169093A (en) * 2010-12-20 2011-08-31 湖南大学 Multi-station machine vision imaging detection method and system based on graphics processor
CN102323272A (en) * 2011-08-10 2012-01-18 合肥望远电子科技有限公司 Filter paper defect detecting system and detection method thereof based on machine vision technique
CN202175829U (en) * 2010-12-27 2012-03-28 中国船舶重工集团公司第七一五研究所 On-line real-time detection system for gray fabric flaw based on machine vision
CN202330297U (en) * 2011-11-28 2012-07-11 陕西长岭纺织机电科技有限公司 Device for automatically detecting texture defects
CN103344648A (en) * 2013-07-10 2013-10-09 鞍钢股份有限公司 Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU)
CN104458766A (en) * 2014-12-31 2015-03-25 江南大学 Cloth surface blemish detection method based on structure texture method
CN105044126A (en) * 2015-07-22 2015-11-11 瑞安市质量技术监督检测院 Visual detection system for large-width continuous surface defects
CN205317684U (en) * 2015-12-22 2016-06-15 无锡市同威软件有限公司 Flaw detecting system dyes cloth based on image

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102169093A (en) * 2010-12-20 2011-08-31 湖南大学 Multi-station machine vision imaging detection method and system based on graphics processor
CN202175829U (en) * 2010-12-27 2012-03-28 中国船舶重工集团公司第七一五研究所 On-line real-time detection system for gray fabric flaw based on machine vision
CN102323272A (en) * 2011-08-10 2012-01-18 合肥望远电子科技有限公司 Filter paper defect detecting system and detection method thereof based on machine vision technique
CN202330297U (en) * 2011-11-28 2012-07-11 陕西长岭纺织机电科技有限公司 Device for automatically detecting texture defects
CN103344648A (en) * 2013-07-10 2013-10-09 鞍钢股份有限公司 Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU)
CN104458766A (en) * 2014-12-31 2015-03-25 江南大学 Cloth surface blemish detection method based on structure texture method
CN105044126A (en) * 2015-07-22 2015-11-11 瑞安市质量技术监督检测院 Visual detection system for large-width continuous surface defects
CN205317684U (en) * 2015-12-22 2016-06-15 无锡市同威软件有限公司 Flaw detecting system dyes cloth based on image

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107703152A (en) * 2017-10-27 2018-02-16 深圳精创视觉科技有限公司 The automatic indication device of optical film shortcoming
CN109145985A (en) * 2018-08-21 2019-01-04 佛山职业技术学院 A kind of detection and classification method of Fabric Defects Inspection
CN109283193A (en) * 2018-10-22 2019-01-29 上海易清智觉自动化科技有限公司 Cotton tyre cord flaw on-line checking and identity device
CN109283193B (en) * 2018-10-22 2024-04-26 上海易清智觉自动化科技有限公司 Tire cord flaw on-line detection and identification device
CN110702691A (en) * 2019-10-29 2020-01-17 无锡精质智能装备有限公司 Fabric quality detection system
CN110793973A (en) * 2019-11-12 2020-02-14 广东骉马机器人科技有限公司 Leather surface defect detecting system
CN114397308A (en) * 2022-03-25 2022-04-26 江苏贝尔特福新材料有限公司 Detection equipment for automatically identifying fabric flaws and use method
CN114397308B (en) * 2022-03-25 2022-07-01 江苏贝尔特福新材料有限公司 Detection equipment for automatically identifying fabric flaws and use method

Similar Documents

Publication Publication Date Title
CN106970090A (en) Embryo cloth defective vision detection device and method
US8237828B2 (en) Device for inspection of print products
CN109484045B (en) Automated image sensor calibration
CN108162600A (en) The method and test pattern of failure print nozzles in detection and compensation ink-jet printer
CN101158650A (en) On-line detecting method of machine vision system for printed calico flaw
CN110154190A (en) A kind of household plate production line and detection method with online vision-based detection function
CN102262093A (en) Machine vision-based on-line detection method for printing machine
CN101445977A (en) Method and device for the automated identification of bobbin tubes
WO1992008967A1 (en) Methods and apparatus for fabric inspection
CN206945566U (en) Embryo cloth defective vision detection device
US20190263163A1 (en) Nozzle operating situation checking method for inkjet printing apparatus, an inkjet printing apparatus, and a program thereof
US20100039510A1 (en) Method and DEVICE for PRINT INSPECTION
CN109664611B (en) Printing machine
CN114486903B (en) Gray-scale self-adaptive coiled material detection system, device and algorithm
CN107155094A (en) Using the vision inspections method of multiple video cameras
CN110940670A (en) Flexible printing label printing head draft detection system based on machine vision and implementation method thereof
EP3699578A1 (en) System for improved fabric inspection
CN110443803A (en) A kind of printed matter picture quality detection method and device
KR20230137584A (en) Vision inspection system for defect detection of fabric
CN210604354U (en) Cloth pattern and character online acquisition device
DE112020006158T5 (en) Image good/bad learning device, image good/bad determining device and image reading device
CN210775274U (en) System for automatically detecting and eliminating defects of pipe-making printing
CN209102635U (en) A kind of cloth inspecting machine with fabric defects instruction function
US20220261975A1 (en) Inspection method and apparatus
CN205691516U (en) Outer package label detection device

Legal Events

Date Code Title Description
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: 20170721