CN201795993U - Image treatment system for coiled material surface detection - Google Patents
Image treatment system for coiled material surface detection Download PDFInfo
- Publication number
- CN201795993U CN201795993U CN2010205353420U CN201020535342U CN201795993U CN 201795993 U CN201795993 U CN 201795993U CN 2010205353420 U CN2010205353420 U CN 2010205353420U CN 201020535342 U CN201020535342 U CN 201020535342U CN 201795993 U CN201795993 U CN 201795993U
- Authority
- CN
- China
- Prior art keywords
- image
- coiled material
- early stage
- image processing
- light source
- 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
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses an image treatment system for coiled material surface detection. The system comprises a light source, a linear array camera set and a control cabinet, wherein the light source is used for providing illumination for the linear array camera set; the linear array camera set is used for acquiring the initial image information of a coiled material surface and performing image pretreatment on the initial image information to obtain an image pretreatment result; and the control cabinet is used for performing image post treatment according to the image pretreatment result to obtain an image post treatment result. The image treatment system for the coiled material surface detection can overcome the defects of high workload, high cost and high omission factor, low detection precision and the like in the prior art and consequently achieve the advantages of low workload, low cost, low omission factor and high precision.
Description
Technical field
The utility model relates to the coiled material surface detection technique, particularly, relates to the image processing system that usefulness is detected on a kind of coiled material surface.
Background technology
As everyone knows, coiled material is meant the material that film, paper, tinfoil paper and steel plate etc. are thin, and these materials have individual common characteristic, i.e. high speed in process of production, line speed basically all more than per minute hundreds of rice, have in addition can reach km.In addition, the coiled material series products is because processing technology, often product meeting generation defective itself or flaw in the process of producing; May have oil mark, cavity and fine wrinkle etc. such as, film paper etc., and steel plate this may have flaws such as printing.
In the prior art, the detection of such flaw all is to finish by on-the-spot operator's naked eyes basically.But because the factor of aspects such as operator's fatigue, technology water product, problems such as omission take place often, have made irretrievable loss to producer; While can realize that along with labour cost is surging the demand that detects automatically is also more and more higher.
At present, on the coil production line of developed country such as American-European-Japanese, the automatic flaw checkout equipment that all is to use basically is such as the AYAHA of Japan; This kind equipment adopts field programmable gate array hardware such as (Field-Programmable Gate Array are called for short FPGA) to finish when image is handled in earlier stage basically, and man-machine interface is to utilize PC to make.
Our country had also engendered the checkout equipment manufacturer that some are professional in the last few years, and domestic product, such as double base science and technology, the detection of equipment all is to finish by software with calculating, such mode basically can be corresponding about at slow production line (such as 100 meters/minute), if and the speed of production line has been when having reached more than 300 meters, computed in software will produce problems such as frame losing, influences accuracy of detection.
In sum, in realizing process of the present utility model, the inventor finds to exist at least in the prior art following defective:
(1) the hand labor amount is big: because the speed of coil production line is very high, finish the detection of flaw by execute-in-place workman's naked eyes, operator's labour intensity is bigger;
(2) cost height: omission has been made irretrievable loss to producer; While can realize that along with labour cost is surging the demand that detects automatically is also more and more higher;
(3) loss height: because the factor of aspects such as operator's fatigue, technology water product, problems such as omission take place often;
(4) accuracy of detection is low: adopt detection techniques such as double base science and technology, when the speed of production line had reached more than 300 meters, computed in software will produce problems such as frame losing, influenced accuracy of detection.
Summary of the invention
The purpose of this utility model is, at the problems referred to above, proposes the image processing system that usefulness is detected on a kind of coiled material surface, to realize that the hand labor amount is little, cost is low, loss is low and the high advantage of accuracy of detection.
For achieving the above object, the technical solution adopted in the utility model is: the image processing system of usefulness is detected on a kind of coiled material surface, comprises light source, line-scan digital camera group and switch board, wherein: described light source: be used to described line-scan digital camera group that illumination is provided; Described line-scan digital camera group: be used to gather the original image information on coiled material surface, and described original image information is carried out the Flame Image Process in early stage, obtain image result in early stage; Described switch board: be used for carrying out later image and handling, obtain image post-processed result according to image result in early stage.
Further, also comprise auxiliary output device, described auxiliary output device comprises the alarm that is equipped with switch board, and is arranged on the lip-deep mark machine of coiled material; Wherein: described alarm: be used for the image post-processed result that obtains according to switch board, when described image post-processed result shows that there is flaw on the coiled material surface, carry out alarm; Described mark machine: be used for the image post-processed result that obtains according to switch board, carry out marking.
Further, described light source comprises at least a in light-focusing type light source, astigmatic type light source, high frequency fluorescent tube and the LED linear light sorurce.
Further, described line-scan digital camera group comprises a plurality of cameras of series connection, and is equipped with respectively at video processing board-card in each in magazine early stage.
Further, described early stage, video processing board-card comprised image processing unit FPGA in early stage, high speed image processing unit in early stage and PCL-e controller, described high speed image processing unit in early stage is connected between FPGA and the PCL-e controller, described FPGA and a plurality of camera are equipped with, and described PCL-e controller is connected with switch board.
Further, described switch board comprises Industrial Control Computer or PC, and the image post-processed unit and the PC main memory that are plugged on described Industrial Control Computer or PC inside, described PC main memory is connected with image post-processed unit, and described PC main memory is connected with the PCL-e controller.
The image processing system of usefulness is detected on the coiled material surface of each embodiment of the utility model, owing to comprise light source, line-scan digital camera group and switch board, wherein: light source is used to the line-scan digital camera group that illumination is provided; The line-scan digital camera group is used to gather the original image information on coiled material surface, and original image information is carried out the Flame Image Process in early stage, obtains image result in early stage; Switch board is used for carrying out later image and handling according to image result in early stage, obtains image post-processed result; By early stage Flame Image Process handle with later image and combine, help improving detection speed and precision; The hand labor amount is big in the prior art, cost is high, loss is high and the low defective of accuracy of detection thereby can overcome, to realize that the hand labor amount is little, cost is low, loss is low and the high advantage of accuracy of detection.
Other features and advantages of the utility model will be set forth in the following description, and, partly from instructions, become apparent, perhaps understand by implementing the utility model.The purpose of this utility model and other advantages can realize and obtain by specifically noted structure in the instructions of being write, claims and accompanying drawing.
Below by drawings and Examples, the technical solution of the utility model is described in further detail.
Description of drawings
Accompanying drawing is used to provide further understanding of the present utility model, and constitutes the part of instructions, is used from explanation the utility model with embodiment one of the present utility model, does not constitute restriction of the present utility model.In the accompanying drawings:
Fig. 1 is the structural representation that detects the image processing system of usefulness according to the utility model coiled material surface;
Fig. 2 is the principle of work synoptic diagram that detects the image processing system of usefulness according to the utility model coiled material surface;
Fig. 3 is the work-based logic synoptic diagram that detects the image processing system of usefulness according to the utility model coiled material surface;
Fig. 4 is the image processing system mid-early stage image processing process synoptic diagram that detects usefulness according to the utility model coiled material surface;
Fig. 5 is the image processing system middle and later periods image processing process synoptic diagram that detects usefulness according to the utility model coiled material surface;
Fig. 6 realizes the process synoptic diagram that image is handled in earlier stage for FPGA in the image processing system that detects usefulness according to the utility model coiled material surface.
In conjunction with the accompanying drawings, Reference numeral is as follows among the utility model embodiment:
1-line-scan digital camera group; The 2-flaw; The 3-light source; 4-mark machine; The 5-coiled material; The 6-switch board; The 7-alarm.
Embodiment
Below in conjunction with accompanying drawing preferred embodiment of the present utility model is described, should be appreciated that preferred embodiment described herein only is used for description and interpretation the utility model, and be not used in qualification the utility model.
According to the utility model embodiment, provide a kind of coiled material surface to detect the image processing system of usefulness.As Fig. 1-shown in Figure 6, present embodiment comprises light source 3, line-scan digital camera group 1 and switch board 6, and wherein: light source 3 is used to line-scan digital camera group 1 that illumination is provided; Line-scan digital camera group 1 is used to gather the original image information on coiled material surface, and original image information is carried out the Flame Image Process in early stage, obtains image result in early stage; Switch board 6 is used for carrying out later image and handling according to image result in early stage, obtains image post-processed result.
Wherein, light source 3 comprises at least a in light-focusing type light source, astigmatic type light source, high frequency fluorescent tube and the LED linear light sorurce.
Here, light source 3 can use high frequency fluorescent tube or LED linear light sorurce; According to the difference of detected object, light source 3 can be selected light-focusing type light source and astigmatic type light source, and the color of light source 3 is also decided on concrete object.
Particularly, the use-pattern of light source 3 is as follows: the light-focusing type light source mainly is at the relatively poor object of surface reflection, such as plastic sheeting, monochromatic non-reflective paper etc.; Astigmatism type light source mainly is applicable to the material that surperficial color development is stronger, such as gold stamping surface, shinny aluminium foil plate etc.The color of light source 3 mainly is to decide according to the color of target object, the detection that will have more contrasty light source relatively to be fit to this type objects basically with the surface color of target object is thrown light on, such as the cyan light source is used in the suggestion of the detection lighting source of red object.
Line-scan digital camera group 1 comprises a plurality of cameras of series connection, and is equipped with respectively at video processing board-card in each in magazine early stage; Early stage, video processing board-card comprised image processing unit FPGA in early stage, high speed image processing unit in early stage and PCL-e controller, high speed image processing unit in early stage is connected between FPGA and the PCL-e controller, FPGA and a plurality of camera are equipped with, and the PCL-e controller is connected with switch board.
Here, line-scan digital camera group 1 has been formed a camera set by crossing a camera by connecting, and this camera set is determined the parameter of each camera in the camera set according to the width of the speed of production line and product.
Wherein, the logical diagram of video processing board-card as shown in Figure 3 in earlier stage: the information that early stage, video processing board-card was gathered the CCD camera by Camera Link (FULL) interface sends image-capture and transmits order from FPGA; Subsequently, image processing unit in early stage (FPGA) is gathered the information of CCD camera and is carried out early stage and handle.
This image comprises in the processing unit early stage: comprise the convolution filter algorithm of the multinuclear of 3x3,5x5,7x7, these algorithms can be realized parallel computing and PIPLINE; Specifically comprise: middle finger filtering, average filter, gaussian filtering etc.; Three values of image are handled; The histogram of image is set up; The axial projection of the XY of image; Parallel computing circuit of taking advantage of etc. adds up.Simultaneously, early stage, video processing board-card can also utilize the function of MLT to realize the effect of the allocation process of camera, realized real-time processing truly.Aforementioned algorithm utilizes modes such as multinuclear parallel computing and PIPLINE to realize the effect that high speed image is handled.
Particularly, in histogrammic foundation with utilize in the calculating of the dynamic thresholding that histogram carries out, the information of utilizing the mode of MLT (camera link repeater module) to disperse the high speed linear array camera, handle a large amount of image information of high speed by the multi-processing board multiple operation, as shown in Figure 6, the image processing step of distinctive coiled material detection comprises: medium filtering, the projection of Y-axis, the projection of X-axis, three values are handled Fourier transform, inversefouriertransform, maximum filtering (3 times), minimum filtering (5 times), maximum filtering (twice), triple-expansion, three contractions, LABELING handles, area, the calculating of features such as size.
Subsequently, handle, can be divided into following several steps as shown in Figure 5 by the later stage software image that the software in the industrial computer carries out:
(1) image that connects each bar line forms an image of finishing; (2) extraction may be the pattern of flaw from image; (3) pattern is carried out LABELING and handle, calculate the geometric properties of each little pattern, comprise length and width, area or the like; (4) judge whether it is flaw according to these features, if such as coiled material itself has fixing pattern greatly, can calculate the area of these fixed patterns, wide height, circularity, girth or the like geometric properties in advance, whether utilize these geometric properties to come to compare with the same set feature of flaw, be flaw thereby differentiate; If flaw comes the notifying operation personnel by alarm 7, utilize mark machine 4 to mark simultaneously in the position that flaw 2 is arranged.
Switch board 6 comprises Industrial Control Computer or PC, and the image post-processed unit and the PC main memory that are plugged on Industrial Control Computer or PC inside, and the PC main memory is connected with image post-processed unit, and the PC main memory is connected with the PCL-e controller.
Here, comprise Industrial Control Computer and be inserted in video processing board-card in early stage in the industrial computer in the switch board.
In the above-described embodiments, the concrete working method of Flame Image Process is as shown in Figure 2: gathered by the line-scan digital camera group through the coiled material image after the light source irradiation, image after the collection is sent in the video processing board-card in early stage by Camera Linker (FULL), and early stage, video processing board-card carried out the Flame Image Process in early stage.
Wherein, the Flame Image Process in early stage is divided following several steps as shown in Figure 4: (1) is taken into and is had the light and shade striped on the picture sometimes owing to the variation of light, by the special processing of shading, can remove the light and shade striped in the image; (2) at the impurity that utilizes various filtrators to cause owing to electric signal in to picture, such as isolated point etc.; (3) utilize three values to handle the background color that to remove in the picture, thereby stay the flaw point of light and shade; (4) utilize the electronic circuit of the aforementioned calculation that FPGA realizes to shorten the computing velocity of Flame Image Process greatly by modes such as parallel processing and PIPLINE.
Further, in the above-described embodiments, also comprise auxiliary output device, auxiliary output device comprises the alarm 7 that is equipped with switch board 6, and is arranged on the lip-deep mark machine 4 of coiled material; Wherein: alarm 7 is used for the image post-processed result that obtains according to switch board 6, when image post-processed result shows that there is flaw 2 on the coiled material surface, carries out alarm; Mark machine 4 is used for the image post-processed result that obtains according to switch board 6, carries out marking.
In the above-described embodiments, by the improvement of resource optimization (distribution of software and hardware computational resource) and algorithm, in order to reach the purpose that high speed image is handled, the video processing board-card in early stage that utilization can high speed processing realizes that by FPGA handle the early stage of Flame Image Process; Wherein:
(1) compares with domestic existing scheme, the foregoing description has improved the speed and the precision of coiled material Defect Detection greatly by the pre-treatment of FPGA, not as accuracy of detection is controlled at 0.5mm with under the interior prerequisite, the detection speed of the foregoing description can be given full play to the high-speed capture effect of the NED camera of 160Mhz, when the speed of production line is 250 to 300 meters per minutes, can realize real-time Flame Image Process.As frame losing can take place when realizing with precision with the detection of speed or calculate problems such as hysteresis in the scheme of using existing software;
(2) compare with external existing scheme, the foregoing description adopts the mode of camera link repeater module to come dispersion treatment high resolving power camera at a high speed by series connection polylith video processing board-card in early stage, and limit processing speed can reach the nearly 2000 meters coiled material of per minute and detect; Distinctive image processing algorithm has also improved accuracy of detection greatly, makes in the past to be difficult to the tiny cut that detects etc. and can clearly to obtain detecting.
In sum, the image processing system of usefulness is detected on the coiled material of each embodiment of the utility model surface, owing to comprise light source, line-scan digital camera group and switch board, wherein: light source is used to the line-scan digital camera group that illumination is provided; The line-scan digital camera group is used to gather the original image information on coiled material surface, and original image information is carried out the Flame Image Process in early stage, obtains image result in early stage; Switch board is used for carrying out later image and handling according to image result in early stage, obtains image post-processed result; By early stage Flame Image Process handle with later image and combine, help improving detection speed and precision; The hand labor amount is big in the prior art, cost is high, loss is high and the low defective of accuracy of detection thereby can overcome, to realize that the hand labor amount is little, cost is low, loss is low and the high advantage of accuracy of detection.
It should be noted that at last: the above only is preferred embodiment of the present utility model, be not limited to the utility model, although the utility model is had been described in detail with reference to previous embodiment, for a person skilled in the art, it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement.All within spirit of the present utility model and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within the protection domain of the present utility model.
Claims (6)
1. the image processing system of a coiled material surface detection usefulness is characterized in that, comprises light source, line-scan digital camera group and switch board, wherein:
Described light source: be used to described line-scan digital camera group that illumination is provided;
Described line-scan digital camera group: be used to gather the original image information on coiled material surface, and described original image information is carried out the Flame Image Process in early stage, obtain image result in early stage;
Described switch board: be used for carrying out later image and handling, obtain image post-processed result according to image result in early stage.
2. the image processing system of usefulness is detected on coiled material according to claim 1 surface, it is characterized in that also comprise auxiliary output device, described auxiliary output device comprises the alarm that is equipped with switch board, and is arranged on the lip-deep mark machine of coiled material; Wherein:
Described alarm: be used for the image post-processed result that obtains according to switch board, when described image post-processed result shows that there is flaw on the coiled material surface, carry out alarm;
Described mark machine: be used for the image post-processed result that obtains according to switch board, carry out marking.
3. the image processing system of usefulness is detected on coiled material according to claim 1 and 2 surface, it is characterized in that, described light source comprises at least a in light-focusing type light source, astigmatic type light source, high frequency fluorescent tube and the LED linear light sorurce.
4. the image processing system of usefulness is detected on coiled material according to claim 1 and 2 surface, it is characterized in that described line-scan digital camera group comprises a plurality of cameras of series connection, and is equipped with respectively at video processing board-card in each in magazine early stage.
5. the image processing system of usefulness is detected on coiled material according to claim 4 surface, it is characterized in that, described early stage, video processing board-card comprised image processing unit FPGA in early stage, high speed image processing unit in early stage and PCL-e controller, described high speed image processing unit in early stage is connected between FPGA and the PCL-e controller, described FPGA and a plurality of camera are equipped with, and described PCL-e controller is connected with switch board.
6. the image processing system of usefulness is detected on coiled material according to claim 5 surface, it is characterized in that, described switch board comprises Industrial Control Computer or PC, and the image post-processed unit and the PC main memory that are plugged on described Industrial Control Computer or PC inside, described PC main memory is connected with image post-processed unit, and described PC main memory is connected with the PCL-e controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010205353420U CN201795993U (en) | 2010-09-16 | 2010-09-16 | Image treatment system for coiled material surface detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010205353420U CN201795993U (en) | 2010-09-16 | 2010-09-16 | Image treatment system for coiled material surface detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201795993U true CN201795993U (en) | 2011-04-13 |
Family
ID=43850899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010205353420U Expired - Fee Related CN201795993U (en) | 2010-09-16 | 2010-09-16 | Image treatment system for coiled material surface detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201795993U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383124A (en) * | 2016-08-30 | 2017-02-08 | 四川石棉华瑞电子有限公司 | Capacitor aluminum foil surface defect visual on-line inspection system and method |
| CN106932006A (en) * | 2017-04-12 | 2017-07-07 | 浙江硕和机器人科技有限公司 | A kind of product quality testing equipment based on machine vision |
-
2010
- 2010-09-16 CN CN2010205353420U patent/CN201795993U/en not_active Expired - Fee Related
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383124A (en) * | 2016-08-30 | 2017-02-08 | 四川石棉华瑞电子有限公司 | Capacitor aluminum foil surface defect visual on-line inspection system and method |
| CN106932006A (en) * | 2017-04-12 | 2017-07-07 | 浙江硕和机器人科技有限公司 | A kind of product quality testing equipment based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101988907A (en) | Image processing system for surface detection of coiled material | |
| CN202916213U (en) | Gear defect detecting system based on computer vision | |
| CN109709102A (en) | Die-cutting machine lithium battery pole slice physical imperfection detection system, method and device | |
| CN201935873U (en) | Online image detection system for bottle cap | |
| CN102374993A (en) | Unit and method for detecting appearance of three dimensional pin of integrated circuit package chip | |
| CN110441316B (en) | Battery surface defect detection method and detection system | |
| Zhang et al. | A review of fabric identification based on image analysis technology | |
| CN105044126A (en) | Visual detection system for large-width continuous surface defects | |
| CN104990511A (en) | Threaded hole structure quality detection method | |
| CN105139397A (en) | PCB board detection method and device | |
| CN201795993U (en) | Image treatment system for coiled material surface detection | |
| CN103175850A (en) | Detection method and system for material surface detects of wide-range high-speed production line | |
| CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
| CN203298726U (en) | Component dimension detection system | |
| CN101510295A (en) | Design method for machine vision system based on PCIe and Vision Assistan | |
| CN100582932C (en) | Apparatus and method for detecting camera module group dark angle | |
| CN109881356B (en) | Hosiery machine knitting needle online detection device and method based on SVM image classification | |
| CN100462672C (en) | Image measuring system and method | |
| CN106872477A (en) | Car engine seal open defect fault detection system | |
| CN103175840B (en) | Based on offset plate surface detection method and the system of machine vision | |
| CN111982787A (en) | System characterization parameter self-adaptive extraction method of lens-free imaging cell detection device | |
| CN102854193A (en) | Detection method and detection system used for image defect detection | |
| CN211786014U (en) | Detection apparatus for OLED tail lamp developments flowing water effect | |
| CN201697615U (en) | Three-dimensional laser scanning on-line detection profile meter | |
| CN204486317U (en) | One main laver automatic sorting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110413 Termination date: 20150916 |
|
| EXPY | Termination of patent right or utility model |