CN102680479A - System for detecting quality of carpet threads based on visual method - Google Patents
System for detecting quality of carpet threads based on visual method Download PDFInfo
- Publication number
- CN102680479A CN102680479A CN2012101288106A CN201210128810A CN102680479A CN 102680479 A CN102680479 A CN 102680479A CN 2012101288106 A CN2012101288106 A CN 2012101288106A CN 201210128810 A CN201210128810 A CN 201210128810A CN 102680479 A CN102680479 A CN 102680479A
- Authority
- CN
- China
- Prior art keywords
- line
- server
- carpet
- adopts
- unit
- 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
- Image Analysis (AREA)
Abstract
The invention discloses a system for detecting quality of carpet threads based on a visual method, which comprises a light source, a camera set, a high-speed acquisition and processing card and a server, wherein the light source is a linear light source and adopts an oblique illumination way; the camera is a linear camera and the camera set adopts a breadth splicing way; the output cable of the linear camera is connected with the high-speed image acquisition and processing card which is integrated with a field programmable gate array (FPGA) module, and the FPGA module comprises a brightness correction unit, a gray balancing unit, a target segmentation unit, and a region of interest (ROI) unit; the high-speed image acquisition and processing card is in signal connection with the server; and the server comprises a defect judgment module for analyzing an ROI image, and is communicated with a carpet thread controller by a signal card.
Description
(1) technical field
The present invention relates to a kind of visible sensation method detection carpet and knit the line mass system, be applicable to field of textiles.
(2) background technology
China Foshan is the main place of production of knitting the line carpet, but because the shortage of production link checkout equipment causes the ratio of defects of product too high; Not only influenced production efficient, and made product be in low-quality condition at a low price always, market survey can be known; The defective of knitting the line carpet is broken string, multi-thread more than 80%, and present domestic detection method still adopts the working method of artificial online visual detection and off-line sampling observation, and is very fast owing to knitting line carpet operating rate; And testing staff's visual fatigue; Be easy to occur the phenomenon of omission, false retrieval, the off-line sampling observation can not guarantee the quality of product fully, so press for a kind of on-line measuring device.
(3) summary of the invention
The deficiency of the phenomenon of omission, false retrieval appears in working method that the present invention will overcome the sampling observation of the online visual detection of existing manual and off-line easily, detects carpet broken string, multi-thread defective, can knit visible sensation method that the line traffic control machine communicates by letter with carpet simultaneously and detect carpet and knit the line mass system but propose a kind of online in real time.
Visible sensation method detects carpet and knits the line mass system, it is characterized in that: comprise light source, shooting unit, high speed acquisition transaction card, server; Described light-source system adopts line source, and light source adopts the oblique illumination mode; Described video camera adopts line array video camera, and described shooting unit adopts the mode of breadth splicing; The output line of described line array video camera connects the high-speed image sampling transaction card, FPGA module that described high-speed image sampling transaction card is integrated, and described FPGA module comprises gamma correction unit, gray balance unit, target cutting unit, ROI pickup unit; Described high-speed image sampling transaction card signal connects described server, and described server comprises the defective judge module that the ROI image is analyzed, and described server is knitted the line traffic control machine through signal card and carpet and communicated by letter.
Further, described server is connected with display that can send the defective caution signal and the database that writes down filing.
Further, described server is integrated WEB server can realize that long-range carpet knits the line browsing data.
Knit linear light according to situation according to the scene, the brightness and the frequency information of adjustment light source, the shooting unit adopts horizontally-spliced formation method; Gather carpet in real time and knit line image, carpet is knitted line image and is delivered to the high speed acquisition transaction card in real time, and the high-speed image sampling transaction card adopts the LVDS interface; Satisfy the picking rate of 2GB/s; And inner integrated FPGA module, can realize the low layer Processing Algorithm, as gamma correction, gray balance, target cut apart, ROI (Region of Interest) picks up; If low tomographic image does not have the ROI zone, then directly image is lost, if the ROI zone is arranged, then the ROI zone is sent to the further analyzing and processing of high-speed servers, this ROI disposal route can improve the data-handling efficiency of total system greatly.
Advantage of the present invention is: but online in real time detects carpet broken string, multi-thread defective, and in time knit the line traffic control machine with carpet and communicate by letter.
(4) description of drawings
Fig. 1 is a system synoptic diagram of the present invention.
Fig. 2 is a FPGA Processing Algorithm frame diagram.
(5) embodiment
Below in conjunction with accompanying drawing the present invention is further described.
With reference to accompanying drawing 1,2, code description among the figure: 1 light source; 2 measured objects (carpet); 3 shooting units; 4 high speed acquisition transaction cards; 5 signal cards; 6 high-performance servers; 7 databases; 8 displays.
Visible sensation method detects carpet and knits the line mass system, it is characterized in that: comprise light source, shooting unit, high speed acquisition transaction card, server; Described light-source system adopts line source, and light source adopts the oblique illumination mode; Described video camera adopts line array video camera, and described shooting unit adopts the mode of breadth splicing; The output line of described line array video camera connects the high-speed image sampling transaction card, FPGA module that described high-speed image sampling transaction card is integrated, and described FPGA module comprises gamma correction unit, gray balance unit, target cutting unit, ROI pickup unit; Described high-speed image sampling transaction card signal connects described server, and described server comprises the defective judge module that the ROI image is analyzed, and described server is knitted the line traffic control machine through signal card and carpet and communicated by letter.
Described server is connected with display that can send the defective caution signal and the database that writes down filing.Described server is integrated WEB server can realize that long-range carpet knits the line browsing data.
With reference to Fig. 1, a kind of visible sensation method detects carpet and knits the line mass system, mainly is made up of light source, shooting unit, high speed acquisition transaction card, server.Described light-source system adopts line source, and light source adopts the oblique illumination mode, detects requirement in order to satisfy the wide format carpet; The shooting unit adopts the mode of breadth splicing, and described video camera adopts line array video camera, and its pixel number is 4096; The pixel size is 7 microns; For 1.2 meters wide carpets, detecting defect size is 0.4 millimeter, then needs horizontally-spliced two line array video cameras; The image that line-scan digital camera is gathered is gathered by the high-speed image sampling transaction card; Described high-speed image sampling transaction card adopts the LVDS interface; Acquisition rate can reach 2GB/s; FPGA module that simultaneously described high-speed image sampling transaction card is integrated can Parallel Implementation image low layer Processing Algorithm, as gamma correction, gray balance, target cut apart, ROI (Region of Interest) picks up; Described high-speed image sampling transaction card sends the ROI image to high-performance server, by high-performance server the ROI image is analyzed, and the image processing algorithm framework is shown in accompanying drawing 2; High-performance server is knitted the line traffic control machine through signal card and carpet and is communicated by letter, so that when carpet was knitted line and broken string, multi-thread defective are occurred, vision detection system can be notified carpet to knit the line traffic control machine and shut down, and with the mode notifying operation personnel of sound and light alarm; Described high-performance server is integrated WEB server can realize that long-range carpet knits the line browsing data.
Claims (3)
1. visible sensation method detects carpet and knits the line mass system, it is characterized in that: comprise light source, shooting unit, high speed acquisition transaction card, server; Described light-source system adopts line source, and light source adopts the oblique illumination mode; Described video camera adopts line array video camera, and described shooting unit adopts the mode of breadth splicing; The output line of described line array video camera connects the high-speed image sampling transaction card, FPGA module that described high-speed image sampling transaction card is integrated, and described FPGA module comprises gamma correction unit, gray balance unit, target cutting unit, ROI pickup unit; Described high-speed image sampling transaction card signal connects described server, and described server comprises the defective judge module that the ROI image is analyzed, and described server is knitted the line traffic control machine through signal card and carpet and communicated by letter.
2. the system of claim 1 is characterized in that: described server is connected with the display that can send the defective caution signal and the database of record filing.
3. according to claim 1 or claim 2 system is characterized in that: described server is integrated WEB server, can realize that long-range carpet knits the line browsing data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101288106A CN102680479A (en) | 2012-04-27 | 2012-04-27 | System for detecting quality of carpet threads based on visual method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101288106A CN102680479A (en) | 2012-04-27 | 2012-04-27 | System for detecting quality of carpet threads based on visual method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102680479A true CN102680479A (en) | 2012-09-19 |
Family
ID=46812739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101288106A Pending CN102680479A (en) | 2012-04-27 | 2012-04-27 | System for detecting quality of carpet threads based on visual method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102680479A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102864559A (en) * | 2012-09-26 | 2013-01-09 | 长沙理工大学 | Broken yarn detection method based on video signal processing |
| CN103196873A (en) * | 2013-03-06 | 2013-07-10 | 东南大学 | Detection imaging system based on laser scanning |
| CN103913467A (en) * | 2014-04-04 | 2014-07-09 | 常州市宏大电气有限公司 | Quilting line breakage detection method based on machine vision |
| CN110738606A (en) * | 2019-09-06 | 2020-01-31 | 深圳新视智科技术有限公司 | Image correction method, device, terminal and storage medium for multi-light source system |
| CN113885397A (en) * | 2021-10-25 | 2022-01-04 | 中国人民解放军陆军装备部驻北京地区军事代表局驻北京地区第一军事代表室 | Embedded-based intelligent manufacturing operation layer information acquisition device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923059A (en) * | 2010-04-15 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Automatic cloth inspection method and system |
| CN202013324U (en) * | 2011-03-15 | 2011-10-19 | 顾金华 | Toweling characteristic detection device based on machine vision |
| CN202599857U (en) * | 2012-04-27 | 2012-12-12 | 浙江工业大学 | System for detecting carpet weaving thread quality by vision method |
-
2012
- 2012-04-27 CN CN2012101288106A patent/CN102680479A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923059A (en) * | 2010-04-15 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Automatic cloth inspection method and system |
| CN202013324U (en) * | 2011-03-15 | 2011-10-19 | 顾金华 | Toweling characteristic detection device based on machine vision |
| CN202599857U (en) * | 2012-04-27 | 2012-12-12 | 浙江工业大学 | System for detecting carpet weaving thread quality by vision method |
Non-Patent Citations (2)
| Title |
|---|
| 张洪涛: "钢板表面缺陷在线视觉检测***关键技术研究", 《中国博士学位论文全文数据库》 * |
| 纪惠军等: "基于机器视觉的织物疵点检测技术探讨", 《现代纺织技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102864559A (en) * | 2012-09-26 | 2013-01-09 | 长沙理工大学 | Broken yarn detection method based on video signal processing |
| CN103196873A (en) * | 2013-03-06 | 2013-07-10 | 东南大学 | Detection imaging system based on laser scanning |
| CN103913467A (en) * | 2014-04-04 | 2014-07-09 | 常州市宏大电气有限公司 | Quilting line breakage detection method based on machine vision |
| CN103913467B (en) * | 2014-04-04 | 2017-01-25 | 常州市宏大电气有限公司 | Quilting line breakage detection method based on machine vision |
| CN110738606A (en) * | 2019-09-06 | 2020-01-31 | 深圳新视智科技术有限公司 | Image correction method, device, terminal and storage medium for multi-light source system |
| CN113885397A (en) * | 2021-10-25 | 2022-01-04 | 中国人民解放军陆军装备部驻北京地区军事代表局驻北京地区第一军事代表室 | Embedded-based intelligent manufacturing operation layer information acquisition device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN202175829U (en) | On-line real-time detection system for gray fabric flaw based on machine vision | |
| CN102680479A (en) | System for detecting quality of carpet threads based on visual method | |
| CN105181714B (en) | A kind of bottling liquid Impurity Detection System and its detection method based on image procossing | |
| CN105044126A (en) | Visual detection system for large-width continuous surface defects | |
| CN105044121B (en) | A kind of online defect detection device of circular knitting machine and detection method | |
| CN201828525U (en) | Automatic detection system for disposable syringe needles | |
| CN101834989B (en) | Real-time data acquisition and storage system of helicopter in electric inspection process | |
| CN101923059A (en) | Automatic cloth inspection method and system | |
| CN103543161A (en) | On-line detection method of continuous casting billet surface quality | |
| CN202599857U (en) | System for detecting carpet weaving thread quality by vision method | |
| CN107944342A (en) | A kind of scrapper conveyor abnormal state detection system based on machine vision | |
| CN201570231U (en) | Detection device of electro luminescence display screen | |
| CN105891228A (en) | Optical fiber appearance defect detecting and outer diameter measuring device based on machine vision | |
| CN203337567U (en) | Fabric detection device based on machine vision | |
| CN104766310B (en) | light source detection system and detection method | |
| CN102879404B (en) | System for automatically detecting medical capsule defects in industrial structure scene | |
| CN103010258A (en) | System and method for detecting cracks of fasteners of high-speed rails and subways | |
| CN105974616A (en) | Method and system for detecting defect of LCD screen | |
| CN203572776U (en) | Detection device for lower-surface defects of continuous casting billet | |
| CN206862915U (en) | A kind of plastic bottle quality visual detecting system | |
| CN102854000B (en) | The detection method of a kind of high-brightness LED optical axis pick-up unit and light shaft offset | |
| CN113592852A (en) | Carbon fiber carbon wire quality online detection system and method | |
| CN112485263A (en) | PE fiber yarn quality online detection device and method based on machine vision | |
| CN111562540A (en) | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
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: 20120919 |