CN202002894U - Quick online paper flaw detecting system based on machine vision - Google Patents
Quick online paper flaw detecting system based on machine vision Download PDFInfo
- Publication number
- CN202002894U CN202002894U CN2011200061859U CN201120006185U CN202002894U CN 202002894 U CN202002894 U CN 202002894U CN 2011200061859 U CN2011200061859 U CN 2011200061859U CN 201120006185 U CN201120006185 U CN 201120006185U CN 202002894 U CN202002894 U CN 202002894U
- Authority
- CN
- China
- Prior art keywords
- paper
- image
- machine vision
- system based
- quick online
- 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.)
- Expired - Fee Related
Links
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model relates to a quick online paper flaw detecting system based on machine vision. The system can accurately detect and identify flaws of paper in high-speed movement, and the flaws include normal flaws such as holes with diameters of more than 0.5mm, dirt/stain, water drops/oil drop marks, damage, drapes, scratches, dark spots, bright spots, edge damage and the like. Simultaneously, the system has the functions of image display, real-time alarming, quality report printing, paper flaw rejection, equipment fault diagnosis and the like. The quick online paper flaw detecting system comprises at least one image acquisition device, the image acquisition device is arranged above a paper roller, is further provided with an adjustable illuminating light source matched with the image acquisition device, and is connected with an image processing computer, and the image processing computer is connected with a background data analysis and management server. Simultaneously, at least one high-speed rotary encoder is mounted on a roller shaft of the paper roller, and is also connected with the background data analysis and management server.
Description
Technical field
The utility model relates to a kind of quick online web inspection system based on machine vision.
Background technology
Under the prerequisite that the paper high-quality is required, paper defects detects and seem particularly important in the modern paper production run.The characteristics of modern paper machine are that amplitude broad, speed are fast, and fabric width surpasses 10 meters, and speed reaches 36 meter per seconds.It is impossible to be detected as the paper paper defects by artificial naked eyes like this.Therefore the manual detection operating speed is slow, needs a large amount of manpowers, and two come a large amount of paper defects defectives is omitted in this simple and work that repeats easily.And after the paper machine speed raising, also be faced with the risk that more defectives appear in paper.Minimum paper defects size is usually less than 1mm
2, this just makes testing difficult more, in order to adapt to this production requirement, can be in increase output by means of the intelligent online measuring technique of " machine vision " technology, and reduction labour intensity and laboring fee are used.The more important thing is, by eliminating because the error that people's fatigue causes obtains higher accuracy.
Common paper defect has: hole, spot, fold, be full of cracks, brocken spectrum, slime spots, trimming breach or the like.From the angle of Flame Image Process, can be divided into high-contrast paper defects and low contrast paper defects to paper defect, high-contrast is meant that the gray-scale value at paper defects place well beyond the normal range of background texture, comprises dirty spot, sizing, hole or the like.The low contrast paper defects is also referred to as faint paper defects, the gray-scale value and the background texture difference that are meant the paper defects place are little, even its gray-scale value is within the normal fluctuating of background texture, but because variation has taken place in the fibre structure at paper defects place, cause to be considered to faint paper defects in appearance, comprise translucent, bubble etc.
Web inspection system based on machine vision technique adopts the CCD camera that detected Target Transformation is become picture signal, send special-purpose image processing system to, according to information such as pixel distribution and brightness, colors, be transformed into digitized signal, image processing system carries out the feature that various computings come extracting objects to these signals, as area, quantity, position, length, again according to default permissibility and other conditions output result, comprise size, angle, number, qualified/defective, have/do not have etc., realize automatic recognition function.
The paper defects monitoring system of domestic enterprise's use at present mainly relies on import equipment, and companies such as Switzerland ABB, U.S. Hnoeywell have developed web inspection system.Wherein, ABB is the producer that develops and develop web inspection system the earliest, and its up-to-date web inspection system is the Web Imaging HDI800 that releases in 2008.Show that according to the data of consulting the web inspection system of the Honeywell company that Mudanjiang Heng Feng paper is already introduced is stable, control is good.Domestic paper defects detection technique research is in the stage of growth, double base company of Zhejiang University has released the SYWIS3000 paper defects and has detected separation system in 2004, be domestic first independently developed web inspection system, do not see the report of relevant system and technical scheme and operating position as yet.
The utility model content
The utility model is exactly for addressing the above problem, a kind of quick online web inspection system based on machine vision is provided, this system can detect and discern the defective of page in the high-speed motion exactly, comprises common deficiencies such as the above hole of diameter 0.5mm, dirty/stain, the water droplet/oil droplet marking, breakage, fold, scratch, blackening, speck, edge breakage.Simultaneity factor has functions such as image demonstration, Realtime Alerts, the printing of quality report table, paper defects rejecting, equipment fault diagnosis.
For achieving the above object, the utility model adopts following technical scheme:
A kind of quick online web inspection system based on machine vision, it comprises at least one image collecting device, and image collecting device is arranged on the paper bowl top, and image collecting device also is provided with the scalable lighting source that matches; Image collecting device is connected with pattern process computer, pattern process computer is connected with management server with the back-end data analysis, simultaneously, at least one high speed rotating scrambler is installed also on the roll shaft of paper bowl, the high speed rotating scrambler also is connected with management server with the back-end data analysis.
Described image collector is changed to industrial high precision linear array scanning formula ccd video camera.
Described scalable lighting source is a scalable LED lighting source.
High precision linear array scanning formula ccd video camera is installed in the top of paper machine in the utility model, the reading speed 20 of every gamma camera, 000 time/second (or 40,000), the vertical paper defects of paper machine detects minimum resolution can reach 0.3mm (depending on paper motor speed and camera number).The ultra-bright LED lighting source suitably highly is installed in the paper web bottom.Light transmissive paper or reflection paper, this depends on the test item of paper defects and becomes paper thickness.Gamma camera CCD linear array is lined by line scan to paper web, generates real-time detection of dynamic image by the high-performance image process computer.Back-end data analysis and management server function mainly are that the defective data to the online detection of paper production line carries out finishing analysis, form defect database efficiently, for later on the data information filing being made in follow-up of product quality analysis etc., and monitor paper production line ruuning situation in real time, the real-time update defective data shows, in time reports to the police when defective reaches alarm criteria.
The beneficial effects of the utility model are: simple in structure, and the accuracy of detection height, speed is fast.
Description of drawings
Fig. 1 detection system structural representation.
Wherein, 1. image collecting device, 2. paper bowl, 3. scalable lighting source, 4. pattern process computer, 5. back-end data analysis and management server, 6. high speed rotating scrambler.
Embodiment
Below in conjunction with accompanying drawing and embodiment the utility model is described further.
Among Fig. 1, it comprises at least one image collecting device 1, and image collecting device 1 is arranged on paper bowl 2 tops, and image collecting device 1 also is provided with the scalable lighting source 3 that matches; Image collecting device 1 is connected with pattern process computer 4, pattern process computer 4 is connected with management server 5 with the back-end data analysis, simultaneously, at least one high speed rotating scrambler 6 also is installed on the roll shaft of paper bowl 2, and high speed rotating scrambler 6 also is connected with management server 5 with the back-end data analysis.
Described image collecting device 1 is industrial high precision linear array scanning formula ccd video camera.
Described scalable lighting source 3 is a scalable LED lighting source.
Industrial high precision linear array scanning formula ccd video camera is that the one dimension wire is arranged, promptly has only delegation's pixel, can only gather the view data of delegation at every turn, have only when video camera and subject just can obtain the two dimensional image that we see usually during in vertical relative motion.So in Vision Builder for Automated Inspection, generally be used for the occasion of measured object continuous motion, be particularly suitable for very fast, the resolution requirement condition with higher of movement velocity.Line-scan digital camera has bigger advantage than area array cameras in the lifting to the paper defects accuracy of detection.
What the video camera photo-sensitive cell adopted is ccd sensor.CCD is a kind of novel photoelectric switching device, it be with electric charge as signal, be to be signal and be different from other most devices with electric current or voltage, its basic function is generation, storage, transmission and the detection of signal charge.The principle of work of CCD is the subject reflection ray to the CCD device, and .CCD gathers corresponding charge according to the power of light. produce the light current pressure signal that is directly proportional with charge quantity of light, through filtering, processing and amplifying, can represent the electric signal a little less than the allergen light intensity or the vision signal of standard by one of driving circuit output.Ccd sensor all has higher performance at aspects such as sensitivity, resolution, noise controls.
The data-interface of industrial high precision linear array scanning formula ccd video camera adopts Gigabit Ethernet.The Gigabit Ethernet transmission speed can reach per second 1000 megabits (being 1Gbps), fast 10 times than Fast Ethernet (FASTEthernet).Advantages such as the validity with network reliability height, management and error correction instrument is strong, extensibility good, price is low.Gigabit Ethernet is still used traditional CSMA/CD agreement, the frame length of frame format, because the Gigabit Ethernet frequency range is higher, so the service that it provides is more guaranteed.Gigabit Ethernet is also supported between the switch in addition, switch is connected with full duplex between the terminal, supports the half-duplex connected mode of shared network, and uses repeater and CSMA/CD collision detection mechanism.Adopt the bus of gigabit Ethernet bus as web inspection system, have that transmission speed is fast, long transmission distance, reliability height, product maturation, be easy to expansion, cheap, and can accomplish on a large scale, fast, the advantage of multiple spot configuration, have very high cost performance.
Can calculate imageing sensor number and the sensor setting height(from bottom) that needs by geometrical optics knowledge, pinhole imaging system formula and ccd image sensor target surface size formula.
L＝n
p×s
p
In the formula: L---imageing sensor target surface length; n
p---image-position sensor pixel number; s
p---the imageing sensor pixel dimension.
Light source:
Desirable light source should be bright, and is evenly, stable.What native system adopted is that the led array module is as lighting source.About 30,000 hours of serviceable life of led light source (interruption longer service life).Can be made into different shape, size and various irradiating angle; Shades of colour can be made as required, and brightness can be regulated at any time; By heat abstractor, radiating effect is better, and luminance brightness is more stable; Reaction is quick, can reach high-high brightness in 10 microseconds or shorter time; Power supply has external trigger, can be by computer control, and toggle speed is fast.
The directional light transmission illumination system that employing is made up of led array and cylindrical lens can adapt to the paper defects surface quality well and detect.Simultaneously, as long as regulate the size of current that external power source is supplied with, just can guarantee to obtain different LED luminosity under the still uniform prerequisite of illumination.Like this, can obtain good paper image, guarantee the stable and accuracy requirement that detection system is measured.
The realization of testing the speed of high speed rotating scrambler:
Adopt the high speed rotating scrambler to send pulse and measuring speed.The high speed rotating scrambler can send in real time pulse accurately, the high speed rotating scrambler corresponding power voltage that adopt in the laboratory is DC5-24V, three phase places outputs (A phase B phase Z phase), the highest response frequency is 100KHZ, resolution is 600 pulse revolutions, adopts the way of output of open collector (NPN) output.Allow the highest rotation speed 6,000r/min can adapt to the web inspection system of high-speed cruising.The high speed rotating scrambler whenever turns around and sends 600 pulses, pulse of every transmission, the distance of paper operation can obtain Lm by the mechanical drive correlation computations, under a certain paper travelling speed, the pulse number N of rotary encoder transmission p.s., the paper travelling speed that can get this moment is: v=L*N (m/s).Design of System Software
Carry out the back-end data analysis by software after generating real-time detection of dynamic image by the high-performance image process computer, defective data to the online detection of paper production line carries out finishing analysis, the high efficiency key of this system is in the design of paper defects detection algorithm, avoided computation process consuming time, algorithm is simply efficient, to complicated situation, take place simultaneously as various types of paper defects, and quantity is more, and whole testing process also can be finished in 20ms, to comparatively simple situation, as has only single paper defects, and during negligible amounts, can be controlled in the 10ms, concrete testing process is as follows:
1) image acquisition and demonstration
The drainage pattern of image mainly can be divided into inter-sync and synchronously outer.
Inter-sync pattern (Free Run Mode) is to go to do the exposure capture according to the inner sequential that produces of video camera itself.Presentation card can't be dominated the time point of video camera capture under this synchronous mode running, and presentation card is the role who is in passive reception data.Time shutter equates with line cycle length, produces rising square wave capture signal that exposes to start with by one group of internal control signal, just image is sent when the rising square-wave signal in next bar line cycle is come in.
External synchronization mode (External Synchronization Mode).Under this pattern, video camera itself can't initiatively produce sequential and go the capture that exposes, the signal of being sent here by the outside is as the synchronous triggering signal, mainly is to get the rising square wave capture signal that exposes to start with, by decision exposure capture time cycle length and the line cycle of outer sync signal.This web inspection system adopts the External synchronization mode images acquired.Record paper machine speed by high-precision rotary encoder, calculate the line frequency that camera is gathered under this speed according to the real-time speed of a motor vehicle again, send trigger pulse to camera, realize the function of image acquisition via the high-speed figure output card.Adopt outer synchronous triggering pattern, can avoid images acquired distortion (speed of a motor vehicle height, line frequency is low, image is compressed, on the contrary images acquired is stretched), guarantee the final accuracy of Processing Algorithm.
According to the line frequency of the speed of a motor vehicle and accuracy of detection adjustment high precision linear array scanning formula ccd video camera, the number of scanning lines of every two field picture is set, will start capture card, the gray level image that collects is saved in internal memory and demonstration.
2) cavity detection
Because what adopt is backlight, the image hole place of gathering is obviously than other regional luminance height, so adopt the simplest method at hole: earlier every two field picture is carried out binaryzation, gray scale might be a hole greater than the connected domain of the pixel formation of setting threshold, connected domain is carried out mark, pixel in the same connected domain is labeled as same numeral, element marking numeral in the different connected domains is different, calculate the area of each connected domain, think noise for area less than the connected domain of setting value (determining) according to accuracy of detection, do not consider, area is thought hole greater than the connected domain of setting value, calculate each regional barycenter, obtain the centre coordinate of hole, and the number of statistics hole, be saved in corresponding array together with the area of corresponding hole.
3) blackspot detects
If paper is by dirty point or be stained with foreign matter, what present on image is blackspot, the lowest part of the grey scale pixel value entire image gray-scale value at blackspot place, can adopt as detecting hole method with direct binaryzation, the concrete method that adopts is: earlier every two field picture is carried out binaryzation, gray scale might be a blackspot less than the connected domain of the pixel formation of setting threshold, connected domain is carried out mark, pixel in the same connected domain is labeled as same numeral, element marking numeral in the different connected domains is different, calculate the area of each connected domain, think noise for area less than the connected domain of setting value (determining) according to accuracy of detection, do not consider, area is thought blackspot greater than the connected domain of setting value, calculate each regional barycenter, obtain the centre coordinate of blackspot, and the number of statistics blackspot, be saved in corresponding array together with the area of corresponding blackspot.
4) speck detects
Speck refers to that fibrage is thinner on the page, but does not penetrate fully, and its penetrability is big part than other positions of page, so the grey scale pixel value at the speck place that presents on image is the gray-scale value that is higher than the entire image gray-scale value and is lower than hole.Therefore the detection method that is adopted need consider to make speck and hole to distinguish, the concrete method that adopts is: earlier every two field picture is carried out binaryzation, this binaryzation is different from the binaryzation of hole and blackspot, mainly is that the binaryzation that speck adopts needs two setting threshold A, B (wherein A is the threshold value in the cavity detection).Gray scale might be a speck less than setting threshold A and the connected domain that constitutes greater than the pixel of setting threshold B, connected domain is carried out mark, pixel in the same connected domain is labeled as same numeral, element marking numeral in the different connected domains is different, calculate the area of each connected domain, think noise for area less than the connected domain of setting value (determining) according to accuracy of detection, do not consider, area is thought speck greater than the connected domain of setting value, calculate each regional barycenter, obtain the centre coordinate of speck, and the number of statistics speck, be saved in corresponding array together with the area of corresponding speck.
5) other complicated paper defects detect
General other complicated paper defects such as paper fold, weak contrast's scratch etc. roughly are wire, and available quick curve detection algorithm carries out Flame Image Process.Earlier image is carried out gaussian filtering and reduce noise as far as possible, carry out rim detection then, obtain the edge image of binaryzation, carry out quick Curvelet conversion, if transformation space has tangible clear zone, illustrate to have paper defects in the paper, find the maximum of points of handling the back data coefficient, thereby determine paper defects position and size.
6) preservation and the analysis of the preservation of paper defects image and paper defects data
Will be for detecting the gray level image that contains paper defects by real-time being saved in the hard disk, convenient consulting and analyzing to paper defects.Set up the paper defects database, real-time detected paper defects data are saved in the middle of the database, and classify and gather, obtain into the volume form of paper paper defects, content comprises paper defects type, quantity, position and area, volume length, time, history curve, and the chart of generation is all printable.Real-time generation paper defects analog image in main interface simultaneously, make things convenient for the user to check paper defects analog image and historical data at any time, can find the concrete data of actual paper defects image and paper defects according to the simulation paper defects symbol that in the paper defects analog image, occurs, as paper defects type, position and area etc.
Claims (3)
1. the quick online web inspection system based on machine vision is characterized in that it comprises at least one image collecting device, and image collecting device is arranged on the paper bowl top, and image collecting device also is provided with the scalable lighting source that matches; Image collecting device is connected with pattern process computer, pattern process computer is connected with management server with the back-end data analysis, simultaneously, at least one high speed rotating scrambler is installed also on the roll shaft of paper bowl, the high speed rotating scrambler also is connected with management server with the back-end data analysis.
2. the quick online web inspection system based on machine vision as claimed in claim 1 is characterized in that, described image collector is changed to industrial high precision linear array scanning formula ccd video camera.
3. the quick online web inspection system based on machine vision as claimed in claim 1 is characterized in that, described scalable lighting source is a scalable LED lighting source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011200061859U CN202002894U (en) | 2011-01-10 | 2011-01-10 | Quick online paper flaw detecting system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011200061859U CN202002894U (en) | 2011-01-10 | 2011-01-10 | Quick online paper flaw detecting system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202002894U true CN202002894U (en) | 2011-10-05 |
Family
ID=44705631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011200061859U Expired - Fee Related CN202002894U (en) | 2011-01-10 | 2011-01-10 | Quick online paper flaw detecting system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202002894U (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102721702A (en) * | 2012-06-27 | 2012-10-10 | 山东轻工业学院 | Distributed paper defect detection system and method based on embedded processor |
| CN103134427A (en) * | 2013-03-07 | 2013-06-05 | 苏州吉视电子科技有限公司 | Recognizing device and method for ring parts |
| CN103175840A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | Offset plate surface detection method and system based on machine vision |
| CN103175841A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | CTP (Computer to Plate) plate surface detection method and system based on machine vision |
| CN103175838A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | PS (Presensitized Plate) plate surface detection system based on machine vision |
| CN103175842A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | CTCP (Computer-to-conventional Plate) plate surface detection method and system based on machine vision |
| CN103175850A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | Detection method and system for material surface detects of wide-range high-speed production line |
| CN103364412A (en) * | 2012-04-10 | 2013-10-23 | 北京兆维电子(集团)有限责任公司 | Online offset plate testing and stacking system |
| CN103507408A (en) * | 2013-09-19 | 2014-01-15 | 安庆市康明纳包装有限公司 | Automatic detecting device of printing machine |
| CN103913460A (en) * | 2013-01-04 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | Online paper defect detecting system |
| CN104246483A (en) * | 2012-02-17 | 2014-12-24 | 斯蒂芬·克雷布斯 | Apparatus and method for inspecting printed images |
| CN104267041A (en) * | 2014-09-12 | 2015-01-07 | 北京慧眼智行科技有限公司 | High-speed online detection system and method of presswork |
| CN104408727A (en) * | 2014-12-03 | 2015-03-11 | 歌尔声学股份有限公司 | Image edge stain detection method and system |
| CN104568949A (en) * | 2014-12-23 | 2015-04-29 | 宁波亚洲浆纸业有限公司 | Method and device for quantitative detection of ink explosion degree of paperboard |
| CN104849285A (en) * | 2015-05-18 | 2015-08-19 | 无锡惠科电工高新技术有限公司 | Linear scanning honeycomb ceramic detection device and detection method |
| CN106204590A (en) * | 2016-07-11 | 2016-12-07 | 陕西科技大学 | A kind of paper defect testing method processed based on gray level image labelling |
| CN107012717A (en) * | 2017-04-06 | 2017-08-04 | 南京三宝弘正视觉科技有限公司 | A kind of paper production control device and method |
| CN111426693A (en) * | 2020-04-26 | 2020-07-17 | 湖南恒岳重钢钢结构工程有限公司 | Quality defect detection system and detection method thereof |
| CN112422952A (en) * | 2020-10-22 | 2021-02-26 | 西安数合信息科技有限公司 | Intelligent detection integrated workstation |
| CN113155851A (en) * | 2021-04-30 | 2021-07-23 | 西安交通大学 | Copper-clad plate surface defect visual online detection method and device based on deep learning |
-
2011
- 2011-01-10 CN CN2011200061859U patent/CN202002894U/en not_active Expired - Fee Related
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103175850A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | Detection method and system for material surface detects of wide-range high-speed production line |
| CN103175840A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | Offset plate surface detection method and system based on machine vision |
| CN103175841A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | CTP (Computer to Plate) plate surface detection method and system based on machine vision |
| CN103175838A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | PS (Presensitized Plate) plate surface detection system based on machine vision |
| CN103175842A (en) * | 2011-12-21 | 2013-06-26 | 北京兆维电子(集团)有限责任公司 | CTCP (Computer-to-conventional Plate) plate surface detection method and system based on machine vision |
| CN103175841B (en) * | 2011-12-21 | 2015-03-18 | 北京兆维电子(集团)有限责任公司 | CTP (Computer to Plate) plate surface detection method and system based on machine vision |
| CN103175842B (en) * | 2011-12-21 | 2015-08-05 | 北京兆维电子(集团)有限责任公司 | Based on CTCP version surface inspecting method and the system of machine vision |
| CN104246483A (en) * | 2012-02-17 | 2014-12-24 | 斯蒂芬·克雷布斯 | Apparatus and method for inspecting printed images |
| CN103364412A (en) * | 2012-04-10 | 2013-10-23 | 北京兆维电子(集团)有限责任公司 | Online offset plate testing and stacking system |
| CN102721702A (en) * | 2012-06-27 | 2012-10-10 | 山东轻工业学院 | Distributed paper defect detection system and method based on embedded processor |
| CN103913460A (en) * | 2013-01-04 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | Online paper defect detecting system |
| CN103134427A (en) * | 2013-03-07 | 2013-06-05 | 苏州吉视电子科技有限公司 | Recognizing device and method for ring parts |
| CN103507408A (en) * | 2013-09-19 | 2014-01-15 | 安庆市康明纳包装有限公司 | Automatic detecting device of printing machine |
| CN104267041B (en) * | 2014-09-12 | 2017-02-15 | 北京慧眼智行科技有限公司 | High-speed online detection system and method of presswork |
| CN104267041A (en) * | 2014-09-12 | 2015-01-07 | 北京慧眼智行科技有限公司 | High-speed online detection system and method of presswork |
| CN104408727A (en) * | 2014-12-03 | 2015-03-11 | 歌尔声学股份有限公司 | Image edge stain detection method and system |
| CN104408727B (en) * | 2014-12-03 | 2017-06-20 | 歌尔股份有限公司 | A kind of image border smear detecting method and system |
| CN104568949A (en) * | 2014-12-23 | 2015-04-29 | 宁波亚洲浆纸业有限公司 | Method and device for quantitative detection of ink explosion degree of paperboard |
| CN104849285A (en) * | 2015-05-18 | 2015-08-19 | 无锡惠科电工高新技术有限公司 | Linear scanning honeycomb ceramic detection device and detection method |
| CN106204590A (en) * | 2016-07-11 | 2016-12-07 | 陕西科技大学 | A kind of paper defect testing method processed based on gray level image labelling |
| CN107012717A (en) * | 2017-04-06 | 2017-08-04 | 南京三宝弘正视觉科技有限公司 | A kind of paper production control device and method |
| CN111426693A (en) * | 2020-04-26 | 2020-07-17 | 湖南恒岳重钢钢结构工程有限公司 | Quality defect detection system and detection method thereof |
| CN112422952A (en) * | 2020-10-22 | 2021-02-26 | 西安数合信息科技有限公司 | Intelligent detection integrated workstation |
| CN113155851A (en) * | 2021-04-30 | 2021-07-23 | 西安交通大学 | Copper-clad plate surface defect visual online detection method and device based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN202002894U (en) | Quick online paper flaw detecting system based on machine vision | |
| CN202221415U (en) | Surface defect online detection system for wide breadth paper | |
| CN209300267U (en) | A kind of cigarette appearance images processing control system and its on-line measuring device | |
| CN100394166C (en) | On-line datecting device for printed matter quality | |
| CN100535647C (en) | On-line detection device of defects in float glass based on machine vision | |
| CN2795852Y (en) | Automatic detector for glazed tile surface property | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN202010662U (en) | Real-time inspection and grading system device for fruit appearance quality | |
| CN101750422A (en) | On-line automatic detection device for glass defect | |
| CN108956645A (en) | A kind of the optical mirror slip defect detecting device and method of more vision systems | |
| CN101105459A (en) | Empty bottle mouth defect inspection method and device | |
| CN103230882A (en) | Optical detection apparatus of parts | |
| CN103163141A (en) | Strip steel surface online detection system and method based on embedded image processing system | |
| CN208721366U (en) | The defects detection and colour sorting system of photovoltaic solar crystal-silicon battery slice | |
| CN102305793A (en) | Method and equipment for detecting appearance quality of product | |
| WO2014139231A1 (en) | System and method for testing and regulating uniformity of light intensity of light source | |
| CN102601131A (en) | Steel billet surface quality online detection device | |
| CN206772850U (en) | CCD lines for Intelligent Measurement surface defects of products sweep camera system | |
| CN204007540U (en) | Roll Testing Cylindricity Error device based on ccd image | |
| CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
| CN208459716U (en) | A kind of liquid crystal display detection device | |
| CN103257145A (en) | Method for detecting raw silk appearance quality | |
| CN116256373A (en) | Perovskite battery film surface defect detection method | |
| CN110702699B (en) | Rolled glass defect detection device and method | |
| CN112304876A (en) | Cotton color degree detection device and detection method based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20111005 Termination date: 20120110 |