CN102323272A - Filter paper defect detecting system and detection method thereof based on machine vision technique - Google Patents
Filter paper defect detecting system and detection method thereof based on machine vision technique Download PDFInfo
- Publication number
- CN102323272A CN102323272A CN201110227240A CN201110227240A CN102323272A CN 102323272 A CN102323272 A CN 102323272A CN 201110227240 A CN201110227240 A CN 201110227240A CN 201110227240 A CN201110227240 A CN 201110227240A CN 102323272 A CN102323272 A CN 102323272A
- Authority
- CN
- China
- Prior art keywords
- filter paper
- defects
- indicia
- industrial computer
- machine 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
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to filter paper defect detecting system and detection method thereof based on machine vision technique, this system comprises frame, machine vision device, industrial computer and indicia of defects printer; Said machine vision device comprises light source and some high speed cameras; Said industrial computer comprises the central microprocessor and the display of built-in embedded image process software; Said indicia of defects printer comprises scrambler and several indicia of defects printers.The present invention is according to characteristics of product to be detected; Adopt the discrete Gaussian function of two-dimentional zero-mean to do that smothing filtering is removed noise and based on roof like edge sub-pixel location algorithm; Product is carried out the defect recognition of its image; High speed camera carries out characteristic to material to be detected and picks up, through central microprocessor control indicia of defects printer.The present invention's ability real-time online is stablized precise and high efficiency and is detected the filter paper defective, and the elements of a fix carry out the indicia of defects printing automatically, report to the police automatically, show testing result in real time.
Description
?
Technical field
The present invention relates to a kind of filter paper defect detecting system and detection method thereof, be used for the online detection of filter paper defective is handled based on machine vision technique.
?
Background technology
The main material of the filter paper Chang Zuowei filter core of cotton fibre is the critical component of filtrator.But the surface of this filter paper has countless aperture feed flow attitude particles or vapour particles to pass through, and the relatively large solid particles of volume then can not pass through.Gaseous state, solid matter separation that the liquid state that this character of filter paper is applied to mix, solid matter separate and mix are so filter paper quality quality directly influences the quality of filtrator.Defective to filter paper material; Like through hole, Bao Qu (non-logical, but belong to improper thickness), mashed limit, stain, break, aberration, disappearance, wire drawing, twill, broken hole etc., basically all adopt the human eye determining method; Maybe can't judge not service test means or inspection-free etc.Obviously, human eye is judged shortcomings such as having precision, efficient are low, loss height.
Most of defect detecting systems adopt the silicon photocell sensed light signal in the prior art, and its shortcoming is that resolution is low, for the defect recognition ability of smaller aperture due.Simultaneously, its optical system imaging quality is poor, and light path can not be adjusted, and the imaging consistance is relatively poor.In addition, adopt the silicon photocell sensed light signal, needing increases input, conversion, amplification and disposal system, and the components and parts data of circuit are huge, and circuit board quantity is many, has reduced the reliability of system, and stabilization of equipment performance is relatively poor.
Machine vision technique applies to semiconductor and IC industry production and detection at present more, and domestic aspect is at the early-stage, basically all in visual pattern processing, aberration context of detection.
?
Summary of the invention
To the problem that exists in the above-mentioned prior art; The object of the present invention is to provide a kind of filter paper defect detecting system based on machine vision technique; It can stablize precise and high efficiency identification filter paper defective by real-time online, and the elements of a fix carry out the indicia of defects printing automatically, report to the police automatically; Automatic statistical analysis filter paper quality shows testing result in real time.
The technical scheme that the present invention is taked for its purpose of realization is: based on the filter paper defect detecting system of machine vision technique, comprise frame, machine vision device, industrial computer and indicia of defects printer; Said machine vision device comprises light source and some high speed cameras; Said industrial computer comprises the central microprocessor and the display of built-in embedded image process software; Said indicia of defects printer comprises scrambler and several indicia of defects printers; Said high speed camera, scrambler, display and indicia of defects printer all are connected with the central microprocessor of industrial computer.
Said light source adopts LED or other linear light sorurces, is arranged on the panel below of said frame; Said high speed camera adopts linear array or area array CCD camera, is fixed on the cross tube of said frame, and interface and said industrial computer communication through being provided with on the camera; Said industrial computer is arranged on the base plate of frame; Said indicia of defects printer comprises seal and cylinder, and seal is fixed on the cylinder piston rod termination, and cylinder is fixed on the sill of said frame; The linear velocity of establishing said scrambler detects roller, be arranged on the filter paper upside that will detect.
Another object of the present invention provides a kind of detection method of filter paper defect detecting system, comprises the steps:
1), measures the travel distance of filter paper, and the travel distance of filter paper is sent to industrial computer through scrambler;
2), after industrial computer obtains the travel distance of filter paper, take pictures by the central microprocessor control high speed camera of industrial computer;
3), central microprocessor reads the photo that takes from high speed camera, be spliced into picture and with its preset threshold comparison, judge whether defectiveness;
4) if defectiveness by central microprocessor control indicia of defects printer, is laid mark on the corresponding zone that has a defective locations of filter paper;
5), central microprocessor real time record defective data, report to the police automatically, the automatic statistical analysis paper quality shows testing result in real time.
Workflow of the present invention:
This system powers on, and starts industrial computer, the central microprocessor operation; Open light source, the filter paper medium begins to walk about, and scrambler is along with walking about of filter paper transmitted travel distance to industrial computer; Take pictures by central microprocessor control high speed camera; Read view data in the high speed camera in real time, be spliced into picture and with its preset threshold comparison, judge whether defectiveness; As filter paper through hole, Bao Qu, mashed limit, stain occur, break, defectives such as aberration, disappearance, wire drawing, twill, broken hole, by central microprocessor control indicia of defects printer prints indicia of defects this zone filter paper is carried out the defective sign.
Beneficial effect of the present invention: utilize machine vision technique to gather the image information of filter paper fast; Real-time online is stablized the defect recognition that precise and high efficiency carries out filter paper; Automatically the elements of a fix are by indicia of defects printer prints indicia of defects, and this system also establishes automatic warning, automatic statistical analysis filter paper quality; Show testing result in real time, realize the robotization that the filter paper defect recognition is handled.
?
Description of drawings
Making the enforcement mode below in conjunction with accompanying drawing and tool is described further the present invention.
Fig. 1 arranges synoptic diagram for master's TV structure of the present invention;
Fig. 2 arranges synoptic diagram for spatial structure of the present invention;
Fig. 3 is the online detection synoptic diagram of the present invention;
Fig. 4 is a syndeton block diagram of the present invention;
Fig. 5 is a workflow block diagram of the present invention.
Among the figure: the 1-high speed camera, the 2-frame, the 3-cylinder, the 4-scrambler, the 5-linear velocity detects roller, 6-stabilized voltage supply, 7-display, 8-alarm, 9-seal, 10-light source, 11-industrial computer, 12-filter paper.
?
Embodiment
Shown in Fig. 1-4, the present invention includes frame 2, machine vision device, industrial computer 11 and indicia of defects printer; Machine vision device comprises light source 10 and some high speed cameras 1; Industrial computer 11 comprises central microprocessor, the display 7 of built-in embedded image process software; The indicia of defects printer comprises scrambler 4 and several indicia of defects printers.High speed camera 1, scrambler 4, display 7 and indicia of defects printer all are connected with the central microprocessor of industrial computer 11.Light source adopts LED or other linear light sorurces, is arranged on the panel below of frame 2.High speed camera 1 adopts linear array or area array CCD camera, is fixed on the cross tube of frame 2, and interface and industrial computer communication through being provided with on the high speed camera; The industrial computer main frame is arranged on the base plate of frame 2; The indicia of defects printer comprises seal 9 and cylinder 3, and seal 9 is fixed on the cylinder piston rod termination, and cylinder 9 is fixed on the sill of frame 2; The linear velocity of establishing scrambler 4 detects roller 5, be arranged on the filter paper upside that will detect.Total system is through stabilized voltage supply 6 power supplies.
Image has various interference unavoidably in the process of imaging, digitizing and transmission, form noise.These noises make the pixel gray-scale value on the image can not correctly reflect the light intensity value of space object corresponding point, have reduced the quality of image.The noise that video camera produces is one of overriding noise in the imaging system, and the pixels dithers error that produces in the video signal digitization process also is a kind of overriding noise source.
The built-in embedded image process software of central microprocessor adopts the discrete Gaussian function of two-dimentional zero-mean to do that smothing filtering is removed noise and based on roof like edge sub-pixel location algorithm; Improve the positional precision of detected material body characteristics, obtain the higher detection precision.
Image processing software is through analysis image pixel gray matrix information; Extract the independent statistical characteristic value of image, set up corresponding image statistics characteristic model space, calculate the similarity coefficient matrix of each images category; The method of utilization cluster analysis; Realization is to the identification of defective, and when paper defective during greater than preset threshold, the output processing signals is stamped sign through industrial computer control indicia of defects printer in filter paper defective locations zone.
As shown in Figure 5, the detection method of filter paper defective comprises the steps:
1), measures the travel distance of filter paper, and the travel distance of filter paper is sent to industrial computer through scrambler;
2), after industrial computer obtains the travel distance of filter paper, take pictures by central microprocessor control high speed camera;
3), central microprocessor reads the photo that takes from high speed camera, be spliced into picture and with its preset threshold comparison, judge whether defectiveness;
4) if defectiveness, central microprocessor control indicia of defects printer is laid mark on the corresponding zone that has a defective locations of filter paper.
5), central microprocessor real time record defective data, report to the police automatically, the automatic statistical analysis paper quality shows testing result in real time.
The online detection of system of the present invention can be stablized precise and high efficiency and detected the filter paper defective, comprises through hole, Bao Qu (non-leading to; But be to belong to improper thickness), mashed limit, stain, break, aberration, disappearance, wire drawing, twill, broken hole etc., the elements of a fix carry out indicia of defects and print automatically, report to the police automatically; Show testing result in real time; Improve the quality of product, substitute the inaccuracy of manual detection, realize the modern production of automation and intelligentification.
The present invention adopts the discrete Gaussian function of two-dimentional zero-mean to make smothing filtering and removes noise and based on roof like edge sub-pixel location algorithm, product is carried out the defect recognition of its image according to characteristics of product to be detected.High speed camera carries out characteristic to material to be detected and picks up, through control indicia of defects printer after the central microprocessor software processes.
Judgement of the present invention and controlling index
A, detect defective in 0.35 second ultrashort time and whether exist;
B, accuracy of detection 0.5mm;
C, exposure and gain are multistage adjustable;
D, storage, query function with record, classification, statistics, defective;
E, have quick startup, function such as detect, stop, promptly stopping;
F, bottom layer driving precise marking function;
G, precision area: 1mm
2Live width: 0.25mm;
The anti-interface of dazzling of h, the outfit bright high life linear light sorurce of pollution-free height and human eye;
I, the man-machine friendly interface of outfit technical grade controlling computer.
The present invention can be used for the application industry of filter paper manufacturing, filter paper, also can be used for like product or other product industries, like product scopes such as cloth weaving, system jar industry, paper-making industry, leather, printing and dyeing, glass, nonwoven fabrics.
Claims (3)
1. based on the filter paper defect detecting system of machine vision technique, it is characterized in that: this system comprises frame, machine vision device, industrial computer and indicia of defects printer; Said machine vision device comprises light source and some high speed cameras; Said industrial computer comprises the central microprocessor and the display of built-in embedded image process software; Said indicia of defects printer comprises scrambler and several indicia of defects printers; Said high speed camera, scrambler, display and indicia of defects printer all are connected with the central microprocessor of industrial computer.
2. the filter paper defect detecting system based on machine vision technique according to claim 1 is characterized in that: said light source adopts the LED linear light sorurce, is arranged on the panel below of said frame; Said high speed camera adopts linear array or area array CCD camera, is fixed on the cross tube of said frame, and interface and said industrial computer communication through being provided with on the camera; Said industrial computer is arranged on the base plate of frame; Said indicia of defects printer comprises seal and cylinder, and seal is fixed on the cylinder piston rod termination, and cylinder is fixed on the sill of said frame; The linear velocity of establishing said scrambler detects roller, be arranged on the filter paper upside that will detect.
3. the detection method of the filter paper defect detecting system based on machine vision technique according to claim 1 is characterized in that: comprise the steps:
1), measures the travel distance of filter paper, and the travel distance of filter paper is sent to industrial computer through scrambler;
2), after industrial computer obtains the travel distance of filter paper, take pictures by the central microprocessor control high speed camera of industrial computer;
3), central microprocessor reads the photo that takes from high speed camera, be spliced into picture and with its preset threshold comparison, judge whether defectiveness;
4) if defectiveness by central microprocessor control indicia of defects printer, is laid mark on the corresponding zone that has a defective locations of filter paper;
5), central microprocessor real time record defective data, report to the police automatically, the automatic statistical analysis paper quality shows testing result in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110227240A CN102323272A (en) | 2011-08-10 | 2011-08-10 | Filter paper defect detecting system and detection method thereof based on machine vision technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110227240A CN102323272A (en) | 2011-08-10 | 2011-08-10 | Filter paper defect detecting system and detection method thereof based on machine vision technique |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102323272A true CN102323272A (en) | 2012-01-18 |
Family
ID=45451057
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110227240A Pending CN102323272A (en) | 2011-08-10 | 2011-08-10 | Filter paper defect detecting system and detection method thereof based on machine vision technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102323272A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102608038A (en) * | 2011-12-09 | 2012-07-25 | 桐昆集团股份有限公司 | Flatly-drawn composite combined filament yarn three-step color judging method |
CN102788804A (en) * | 2012-08-27 | 2012-11-21 | 浙江仙鹤特种纸有限公司 | Paper inspection bench |
CN104458749A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Real-time aluminum profile surface defect detection system based on machine vision |
CN106706657A (en) * | 2015-11-17 | 2017-05-24 | 北大方正集团有限公司 | On-line detection system and method based on ink jet printing |
CN106970090A (en) * | 2017-04-27 | 2017-07-21 | 佛山市南海区广工大数控装备协同创新研究院 | Embryo cloth defective vision detection device and method |
CN107044987A (en) * | 2017-04-07 | 2017-08-15 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection unit and its characterization processes |
CN107247058A (en) * | 2017-07-04 | 2017-10-13 | 浙江恒石纤维基业有限公司 | Glass tricot machine foreign matter on-line measuring device |
CN108020559A (en) * | 2017-12-29 | 2018-05-11 | 德清炬诚电子科技有限公司 | Bubble-cap class packs medicine visual detection equipment |
CN109580633A (en) * | 2018-11-30 | 2019-04-05 | 佛山职业技术学院 | A kind of method of plank automatic contacting face production equipment and plank automatic contacting face |
CN110369321A (en) * | 2019-07-04 | 2019-10-25 | 海安交睿机器人科技有限公司 | A kind of transformer core automatic overlapping and assembling visual identifying system and method |
CN110378618A (en) * | 2019-07-26 | 2019-10-25 | 杭州安脉盛智能技术有限公司 | Quality evaluating method and system based on online pipe tobacco surface defects detection |
CN110756457A (en) * | 2019-10-17 | 2020-02-07 | 广州乔拓科技有限公司 | Automatic wall and floor tile identifying and classifying system and method |
CN113262551A (en) * | 2021-04-08 | 2021-08-17 | 中国铝业股份有限公司 | Filtering condition monitoring method of aluminum oxide flat disc filter and related equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US2930228A (en) * | 1956-11-30 | 1960-03-29 | United States Steel Corp | Apparatus for detecting and recording defects in a strip |
US5745217A (en) * | 1996-03-29 | 1998-04-28 | Eastman Kodak Company | System for detecting, coding, avoiding, and removing defects on a photosensitive web |
CN1264836A (en) * | 1999-02-25 | 2000-08-30 | 希尔德科股份有限公司 | Break monitoring system for web in papermaking machine |
CN1503051A (en) * | 2002-11-21 | 2004-06-09 | 伊斯曼柯达公司 | Printing apparatus having a media defect detection system |
CN102033068A (en) * | 2009-09-24 | 2011-04-27 | 苏州维世迅机器视觉技术有限公司 | Product on-line detector |
-
2011
- 2011-08-10 CN CN201110227240A patent/CN102323272A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US2930228A (en) * | 1956-11-30 | 1960-03-29 | United States Steel Corp | Apparatus for detecting and recording defects in a strip |
US5745217A (en) * | 1996-03-29 | 1998-04-28 | Eastman Kodak Company | System for detecting, coding, avoiding, and removing defects on a photosensitive web |
CN1264836A (en) * | 1999-02-25 | 2000-08-30 | 希尔德科股份有限公司 | Break monitoring system for web in papermaking machine |
CN1503051A (en) * | 2002-11-21 | 2004-06-09 | 伊斯曼柯达公司 | Printing apparatus having a media defect detection system |
CN102033068A (en) * | 2009-09-24 | 2011-04-27 | 苏州维世迅机器视觉技术有限公司 | Product on-line detector |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102608038A (en) * | 2011-12-09 | 2012-07-25 | 桐昆集团股份有限公司 | Flatly-drawn composite combined filament yarn three-step color judging method |
CN102788804A (en) * | 2012-08-27 | 2012-11-21 | 浙江仙鹤特种纸有限公司 | Paper inspection bench |
CN102788804B (en) * | 2012-08-27 | 2014-12-31 | 浙江仙鹤特种纸有限公司 | Paper inspection bench |
CN104458749A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Real-time aluminum profile surface defect detection system based on machine vision |
CN106706657A (en) * | 2015-11-17 | 2017-05-24 | 北大方正集团有限公司 | On-line detection system and method based on ink jet printing |
CN107044987B (en) * | 2017-04-07 | 2023-08-15 | 江苏博虏智能科技有限公司 | Surface defect detection unit and detection process for fabric |
CN107044987A (en) * | 2017-04-07 | 2017-08-15 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection unit and its characterization processes |
CN106970090A (en) * | 2017-04-27 | 2017-07-21 | 佛山市南海区广工大数控装备协同创新研究院 | Embryo cloth defective vision detection device and method |
CN107247058A (en) * | 2017-07-04 | 2017-10-13 | 浙江恒石纤维基业有限公司 | Glass tricot machine foreign matter on-line measuring device |
CN108020559A (en) * | 2017-12-29 | 2018-05-11 | 德清炬诚电子科技有限公司 | Bubble-cap class packs medicine visual detection equipment |
CN109580633A (en) * | 2018-11-30 | 2019-04-05 | 佛山职业技术学院 | A kind of method of plank automatic contacting face production equipment and plank automatic contacting face |
CN110369321A (en) * | 2019-07-04 | 2019-10-25 | 海安交睿机器人科技有限公司 | A kind of transformer core automatic overlapping and assembling visual identifying system and method |
CN110378618A (en) * | 2019-07-26 | 2019-10-25 | 杭州安脉盛智能技术有限公司 | Quality evaluating method and system based on online pipe tobacco surface defects detection |
CN110756457A (en) * | 2019-10-17 | 2020-02-07 | 广州乔拓科技有限公司 | Automatic wall and floor tile identifying and classifying system and method |
CN113262551A (en) * | 2021-04-08 | 2021-08-17 | 中国铝业股份有限公司 | Filtering condition monitoring method of aluminum oxide flat disc filter and related equipment |
CN113262551B (en) * | 2021-04-08 | 2022-04-26 | 中国铝业股份有限公司 | Filtering condition monitoring method of aluminum oxide flat disc filter and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102323272A (en) | Filter paper defect detecting system and detection method thereof based on machine vision technique | |
CN202177587U (en) | Filter paper defect detecting system based on machine vision technology | |
CN208206822U (en) | Pcb board defect automatic checkout system based on machine vision | |
CN101226108B (en) | Method for testing droplet distribution consistency degree | |
CN201218723Y (en) | Optoelectronic non-contact type image detection apparatus | |
CN103091331B (en) | System and method for visual inspection on burrs and stain defects of radio frequency identification (RFID) antennae | |
CN103913468A (en) | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line | |
CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
CN100559234C (en) | The installment state inspection method of electronic unit, the installment state testing fixture of electronic unit and the manufacture method of electronic equipment | |
CN105184793A (en) | Electric energy meter sample appearance and PCB element detection method | |
CN105067639A (en) | Device and method for automatically detecting lens defects through modulation by optical grating | |
CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
CN106248686A (en) | Glass surface defects based on machine vision detection device and method | |
KR101256369B1 (en) | Flat display pannel test equipment and test method using multi ccd camera | |
CN103913461A (en) | TFT-LCD lighting automatic optical inspection based image processing method | |
CN102837497B (en) | Precision detection device and precision detection method of printing machine | |
CN102866166A (en) | Automatic optic detecting system and method | |
CN110567976A (en) | mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
CN106896115A (en) | Varnished glass Defect Detection device based on area array cameras parallel connection acquisition system | |
CN102854195B (en) | Method for detecting defect coordinates on color filter | |
CN103308524A (en) | PCB automatic optical inspection system | |
CN104568989A (en) | Glass substrate defect detecting method | |
CN103674976A (en) | Optical detection method and system for cellular array type long and thin through holes | |
CN104749801B (en) | High Precision Automatic optical detecting method and system | |
CN111426693A (en) | Quality defect detection system and detection method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120118 |