CN104535586B - Strip steel edge defect detection identification method - Google Patents
Strip steel edge defect detection identification method Download PDFInfo
- Publication number
- CN104535586B CN104535586B CN201410656403.1A CN201410656403A CN104535586B CN 104535586 B CN104535586 B CN 104535586B CN 201410656403 A CN201410656403 A CN 201410656403A CN 104535586 B CN104535586 B CN 104535586B
- Authority
- CN
- China
- Prior art keywords
- defect
- strip steel
- gray
- image
- data
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 76
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 71
- 239000010959 steel Substances 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000005097 cold rolling Methods 0.000 abstract description 4
- 238000003708 edge detection Methods 0.000 abstract 1
- 230000000877 morphologic effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000005096 rolling process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229910000976 Electrical steel Inorganic materials 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000007747 plating Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000005028 tinplate Substances 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of the cold rolling manufacturing industry, and discloses a strip steel edge defect detection identification method. The method includes the following steps: 1, generating morphologic data; 2, generating the rectangular morphology grey-scale image of the strip steel edge; 3, converting the rectangular morphology grey-scale image to form an annular morphology gray image; 4, carrying out binaryzation processing on the annular morphology grey-scale image to obtain a binary image; 5, carrying out contour detection on the binary image to obtain a defect area; 6, extracting the coordinates, the area and the grey average of the defect area; and 7, corresponding the defect area to the actually detected strip steel edge to obtain the defect position coordinates, the defect area, the defect length and width size and the defect depth of the actual strip steel edge. The method can be used to quickly and accurately detect the edge defects of strip steel coils, improves the detection precision and accuracy, and finally provides an edge detection report of the detected steel coils.
Description
Technical field
The present invention relates to cold rolling manufacturing industry technical field, more particularly to a kind of side defects of strip steel detection recognition method.
Background technology
Recently as the progress of cold rolling manufacturing technology, flat cold-rolled sheet is obtained in fields such as automobile, chemical industry, the energy, buildings
Increasing application.Compared with SPHC, flat cold-rolled sheet has the advantages that plate shape is good, molding is fast, surface accuracy is high, more accords with
Close the technological requirement of advanced manufacture equipment.But in cold rolling of strip steel manufacture process, usually because the original edge of hot rolled plate lacks
Fall into, the abrasion of the metallurgical hole of material itself, circle shear, edge tension force is uneven etc. reason causes roll rear band steel edge it is all kinds of not
Split and fold etc. edge fault in regular side.This kind of defect not only affects the end product quality of steel, causes the effective usable floor area of coil of strip
Reduce, can also increase extra trimming process step, even result in generation of the following process process interrupt with accident.
The existing steel edge portion quality testing major part of China still relies on the naked eyes identification of technical staff, wastes time and energy,
And it is susceptible to missing inspection.Ji Tao automatizatioies strip quality defect detecting technique few in number is also more from external introduction.With Baosteel
As a example by the tin plating unit in sheet-steel rolling mill, introduce based on the defect recognition system of High-speed Photography Technology from Japan within 2004, but this is
The surface quality united mainly for tin plate, lacks the discriminating power to edge fault.And silicon steel welds unit from Germany's introduction
Complete QCDS systems then weldquality can only be passed judgment on, the non-joint edge of strip steel is split also helpless.Baosteel is opened
The side defects of strip steel Detection Techniques sent out are based on flash ranging principle, can effectively recognize the middle part rolling hole of strip steel, although to edge
Defect also has certain identification ability, but is only confined to side and splits defect more than 5 centimetres, for less than 5 centimetres or non-penetrative
Edge fault is then without an effectively identification.It is various due to rolling rear side defects of strip steel form complexity, therefore existing domestic and international defect
Technology of identification, all cannot form complete effectively sign to edge fault, and the automatic identification technology of edge fault is still steel so far
The difficult point in ferrum rolling field is located.
High-precision laser measuring surface form technology obtained in recent years fast development, nowadays the other line laser skill of civil
Art certainty of measurement and rate of scanning have respectively reached 0.01mm and 30Hz, have substantially met the industrial requirements of routine.Based on laser
The side defects of strip steel technology of identification of surface row topography exploitation is to improving the high-performance cold rolled thin plate quality of China, opening
Send out and formed high accuracy defect detecting technique and all there is important learning value and engineering significance.
The content of the invention
In order to solve above-mentioned technical problem, the present invention provides a kind of side defects of strip steel detection recognition method, realizes to quiet
Only the coiled strip steel coil of strip of state carries out the detection and identification of edge fault.
The present invention is adopted the technical scheme that：
A kind of side defects of strip steel detection recognition method, is characterized in that, comprise the steps：
The first step：Annular trace scanning is carried out to strip steel steel roll rim by laser range sensor, topographic data is generated,
The form of the topographic data is：
x1, h1；x2, h2；x3, h3；……
Wherein x1, x2, x3... ... for the continuous position information that one laser beam passes through, h1, h2,
H3 ... ... is the range data between measured point and laser range sensor, and range data is valid data, needs the number for retaining
According to；
Second step：By formula：gi=hi/ A, by the range data gray value is converted into, and by xiAnd giChange into band
Steel edge rectangle pattern gray-scale maps, wherein i=1,2,3 ... ..., A is integer；
3rd step：The conversion of rectangle pattern gray-scale maps is circularized into pattern gray-scale maps；
4th step：The annular pattern gray-scale maps are carried out into binary conversion treatment, bianry image is obtained；
5th step：Contour detecting is carried out to the bianry image, obtains wherein that gray-value variation is substantially and and peripheral region
The big defect area of gray scale difference value；
6th step：Coordinate, area, the gray average of the defect area are extracted, and the region corresponds to the square
Length and width information in shape pattern gray-scale maps；
7th step：By defect area correspondence to the actually detected steel edge portion, actual steel edge portion is obtained
Defective locations coordinate, defect area, defect length and width size and depth of defect.
Further, the scanning step of the annular trace scanning in the first step is 7mm/s, and scanning accuracy is 3mm/s.
Further, before the 4th step, also include that the annular pattern gray-scale maps using medium filtering to obtaining are carried out
Denoising.
Further, A=100.
Further, the binary conversion treatment of the 4th step comprises the steps：
（1）Image segmentation；
（2）The segmentation threshold of optimal binaryzation is determined to the topography after segmentation by maximum kind differences method；
（3）Binaryzation is carried out to the image after segmentation；
（4）Obtain bianry image.
The invention has the beneficial effects as follows：
The edge fault of strip steel coil of strip can quickly and accurately be detected, be improved accuracy of detection and accuracy, finally
The edge examining report for being detected coil of strip is provided, including the quantity of defect, location and shape size, and defect rank are commented
Fixed, the performance rating for strip steel coil of strip provides data refer and ready for next production process.
Description of the drawings
Accompanying drawing 1 is method of the present invention flow chart；
Accompanying drawing 2 is sensor scan steel edge portion schematic diagram；
Accompanying drawing 3 is that steel edge portion feature image rebuilds schematic diagram；
Accompanying drawing 4 is the gray-scale maps obtained in embodiment detection；
Accompanying drawing 5 is that defect circular contour is fitted to rectangular profile.
Specific embodiment
The specific embodiment of side defects of strip steel detection recognition method of the present invention is elaborated below in conjunction with the accompanying drawings.
High-precision laser measuring surface form technology obtained in recent years fast development, nowadays the other line laser skill of civil
Art certainty of measurement and rate of scanning have respectively reached 0.01mm and 30Hz, have substantially met the industrial requirements of routine.Based on laser
The side defects of strip steel technology of identification of surface row topography exploitation is to improving the high-performance cold rolled thin plate quality of China, opening
Send out and formed high accuracy defect detecting technique and all there is important learning value and engineering significance.
Referring to accompanying drawing 1, the side defects of strip steel detection recognition method of the present invention, comprise the steps：
The first step：Annular trace scanning is carried out to strip steel steel roll rim by laser range sensor, topographic data is generated,
The form of the topographic data is：
x1, h1；x2, h2；x3, h3；……
Wherein x1, x2, x3... ... for the continuous position information that one laser beam passes through, h1, h2,
H3 ... ... is the range data between measured point and laser range sensor, and range data is valid data, needs the number for retaining
According to.The scanning step of annular trace scanning is 7mm/s, and scanning accuracy is 3mm/s.
Second step：By formula：gi=hi/ A, by the range data gray value is converted into, and by xiAnd giChange into band
Steel edge rectangle pattern gray-scale maps, wherein i=1,2,3 ... ..., A is integer, can use 100.
3rd step：The conversion of rectangle pattern gray-scale maps is circularized into pattern gray-scale maps；
4th step：The annular pattern gray-scale maps are carried out into binary conversion treatment, bianry image is obtained.Before binary conversion treatment,
Denoising is carried out to the annular pattern gray-scale maps for obtaining using medium filtering.
Binary conversion treatment comprises the steps：
（1）Image segmentation；
（2）The segmentation threshold of optimal binaryzation is determined to the topography after segmentation by maximum kind differences method；
（3）Binaryzation is carried out to the image after segmentation；
（4）Obtain bianry image.
5th step：Contour detecting is carried out to the bianry image, obtains wherein that gray-value variation is substantially and and peripheral region
The big defect area of gray scale difference value；
6th step：Coordinate, area, the gray average of the defect area are extracted, and the region corresponds to the square
Length and width information in shape pattern gray-scale maps；
7th step：By defect area correspondence to the actually detected steel edge portion, actual steel edge portion is obtained
Defective locations coordinate, defect area, defect length and width size and depth of defect.
Referring to accompanying drawing 2, in being embodied as, assistant analysis can be carried out using software, first with laser range sensor,
Runs software realizes the connection and control with sensor on computer, sets up communication to collect the steel edge portion number that its scanning is obtained
According to, data are processed and is achieved, when detection module is run, the data to collecting are analyzed process, according to scanning
Data after process carry out image reconstruction, generate strip steel steel roll rim pattern gray level image, then the image to generating is filtered
Process and binary conversion treatment, carry out image segmentation and contour detecting to the bianry image after process, extract the profile that obtains
The information such as coordinate, area, the length and width of fitted rectangle and gray average in gray-scale maps, reconvert is believed into the defect of steel edge portion
Breath, including the information such as defective locations coordinate, size, length and width size and mean depth, and defect etc. is carried out according to defect information
The evaluation of level, obtains the grade of defect, and final output is detected the defect information of strip steel and collects and total quality evaluation, and will knot
Fruit achieves, output, and implementation step includes：
（1）The connection of programming realization software and laser range sensor equipment and control；
（2）Software is set up after communicating with sensor, the topographic data of sensor scan strip steel steel roll rim is received, to receiving
To data be analyzed extraction range data achieve；
（3）According to the data for achieving, range data is converted into into gray value, software in drawing area real-time dynamic display just
In detected steel edge portion pattern gray-scale maps；
（4）According to the scan pattern founding mathematical models for achieving data and laser range sensor, steel edge portion shape is realized
The reconstruction of looks gray level image；
（5）Image denoising and binaryzation are carried out successively to rebuilding the steel edge portion pattern gray level image for obtaining, and obtain two-value
Image；
（6）To process obtain bianry image carry out image segmentation and contour detecting, then extract the profile for obtaining in ash
The information such as coordinate, area, the length and width of fitted rectangle and the gray average in degree figure, reconvert into steel edge portion defect information,
Including information such as defective locations coordinate, size, length and width size and mean depths, testing result is exported, achieved.
Step（2）Middle distance measuring sensor scans the topographic data form of the strip steel steel roll rim of transmission：
x1, h1；x2, h2；x3, h3；……
Wherein x1, x2, x3... ... for the continuous position information that one laser beam passes through, h1, h2, h3……
For the range data between measured point and laser range sensor, range data is valid data, needs the number for retaining
According to.
Step（3）It is middle according to formula：
gi=hi/ 100,（G is gray value, and h is distance, i=1,2,3 ...）
Gray value range data being converted in gray level image（Referring to accompanying drawing 4）.
Step（4）In, because actual scanning track is annular, but the data for obtaining are rectangle, are needed according to scanning
The scan pattern of data and laser range sensor carries out the reconstruction of steel edge portion feature image, and the mathematical model of reconstruction model is such as
Under：
Referring to accompanying drawing 3, it is assumed that scanning obtain rectangle total length be b, width is a（That is beam width）, then actually sweep
The radius R of the annulus inner circle retouched1With exradius R2Respectively：
R2=b/(2π)
R1=R2-a
n=R2-R1
Obtain the inside and outside radius of circle R of actual scanning annulus1、R2Afterwards, then whole annulus is made up of n circle, from annulus outmost turns
Count, the n that is followed successively by 0,1,2,3 ... ..., then radius of each circle is：
R=R2-i (i=0、1、2、3……)
Each corresponding data of circle is the rectangle data that from top to bottom (i+1) goes, and total length of data is b, with circle
Radius successively decreases, and girth reduces, and packing density accordingly increases, but because the data that actual scanning is obtained there is in itself repetition
Situation, so not affecting the result of last reconstruction image when annulus is fitted to.
Rebuild steel edge portion pattern gray level image during, each point position coordinateses according to round polar equation come
It is determined that, i.e.,：
x=x0+R*cosθ
y=y0+R*sinθ
(x0,y0) be central coordinate of circle, θ ∈ [0,2 π]
The gray value of each point is by step（3）Obtain, point-by-point mapping is obtained preliminary steel edge portion pattern gray-scale maps
As figure.
To tentatively obtaining obtaining leak source phenomenon that may be present in image, that is, there is certain pixel (xj,yj) gray value is
Sky, adopts and takes the upper left corner (xj-1,yj- 1) and the lower right corner (xj+1,yj+ 1) pixel gray level average enters row interpolation filling, final to obtain
To complete steel edge portion pattern gray level image.
Step（5）In, using medium filtering to obtain steel edge portion pattern gray level image carries out denoising, reduction is made an uproar
Impact of the acoustical signal to testing result.
Step（5）In, then binary conversion treatment is respectively adopted using image segmentation is first carried out to the topography after segmentation
OTSU algorithms（Maximum kind differences method）, it is determined that the segmentation threshold of optimal binaryzation, carries out the binaryzation of image, obtain binary map
Picture.Wherein OTSU algorithm principles are：
Hypothesis segmentation threshold is t, then point of the gray value more than t is foreground point, is background dot less than t.Foreground point accounts for figure
As ratio is w0, gray average is u0, it is w that background dot accounts for image scaled1, gray average is u1, then the gray average of whole image
For：
u=w0*u0+w1*u1
Set up function：
g(t)=w0*(u0-u)2+w1*(u1-u)2
G (t) is the inter-class variance expression formula of segmentation threshold t, t ∈ (0,255) in the range of so that g (t) obtains maximum
The t values of value are optimal binarization segmentation threshold value.
Step（6）On the basis of the middle contour detecting algorithm using in image procossing source code library OpenCV of increasing income, changed
Enter the contour detecting and information extraction algorithm for obtaining, to step（5）In the bianry image that obtains carry out contour detecting, obtain wherein
Substantially and the region big with peripheral region gray scale difference value, i.e., actual steel edge portion there may be the region of defect to gray-value variation,
Extract image in profile coordinate, area, gray average, and by contour fitting for rectangle length and width information（Referring to accompanying drawing 5）,
Obtain these information converted by image and actually detected steel edge portion ratio, you can obtain actual steel edge portion and lack
The defect informations such as sunken position coordinateses, defect area, defect length and width size and depth of defect, most at last these defect informations are defeated
Go out to achieve.
Step（6）The depth of defect value that middle basis is detected is compared with the defect rank of setting, you can obtain defect
Ranking results.Defect rank is set according to different production requirements by user sets itself.
The example of a defect rank evaluation result is given below：
Detection time：2014-7-18 9：36：20
Detection parameter：
Scanning step：7.00mm/s
Scanning accuracy：3.00mm/s (defect minimum permissible value)
Defect rank：3.00 ~ 5.00mm is I levels, and 5.00 ~ 7.00mm is II levels, and more than 7.00mm is III level
10 ~ 18 21.30 ~ 22.35 length：19mm width：1.20mm depth：6.83mm II levels
24 ~ 9 17.20 ~ 19.00 length：6mm width：1.80mm depth：3.54mm I levels
3 21 ~ 29 2.30 ~ 6.35 length：9mm width：4.05mm depth：5.28mm II levels
I levels defect 1
II levels defect 2
III level defect 0
Defect sum 1.
The above is only the preferred embodiment of the present invention, it is noted that for those skilled in the art,
Without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should be regarded as this
Bright protection domain.
Claims (5)
1. a kind of side defects of strip steel detection recognition method, it is characterised in that：Comprise the steps：
The first step：Annular trace scanning is carried out to strip steel steel roll rim by laser range sensor, topographic data is generated, it is described
The form of topographic data is：
x1, h1；x2, h2；x3, h3；……
Wherein x1, x2, x3... ... for the continuous position information that one laser beam passes through, h1, h2, h3 ... ... are
Range data between measured point and laser range sensor, range data is valid data, needs the data for retaining；
Second step：By formula：gi=hi/ A, by the range data gray value is converted into, and by xiAnd giChange into steel edge portion
Rectangle pattern gray-scale maps, wherein i=1,2,3 ... ..., A is integer；
3rd step：The conversion of rectangle pattern gray-scale maps is circularized into pattern gray-scale maps；
4th step：The annular pattern gray-scale maps are carried out into binary conversion treatment, bianry image is obtained；
5th step：Contour detecting is carried out to the bianry image, obtains that wherein gray value and peripheral region gray scale difference value are big to be lacked
Sunken region；
6th step：Coordinate, area, the gray average of the defect area are extracted, and the region corresponds to the rectangle shape
Length and width information in looks gray-scale maps；
7th step：By defect area correspondence to actually detected steel edge portion, the defective locations of actual steel edge portion are obtained
Coordinate, defect area, defect length and width size and depth of defect.
2. side defects of strip steel detection recognition method according to claim 1, it is characterised in that：Ring in the first step
The scanning step of shape track scanning is 7mm/s, and scanning accuracy is 3mm/s.
3. side defects of strip steel detection recognition method according to claim 1, it is characterised in that：The 4th step it
Before, also include that the annular pattern gray-scale maps using medium filtering to obtaining carry out denoising.
4. side defects of strip steel detection recognition method according to any one of claim 1 to 3, it is characterised in that：A=
100。
5. side defects of strip steel detection recognition method according to any one of claim 1 to 3, it is characterised in that：It is described
The binary conversion treatment of the 4th step comprises the steps：
（1）Image segmentation；
（2）The segmentation threshold of optimal binaryzation is determined to the topography after segmentation by maximum kind differences method；
（3）Binaryzation is carried out to the image after segmentation；
（4）Obtain bianry image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410656403.1A CN104535586B (en) | 2014-11-18 | 2014-11-18 | Strip steel edge defect detection identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410656403.1A CN104535586B (en) | 2014-11-18 | 2014-11-18 | Strip steel edge defect detection identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104535586A CN104535586A (en) | 2015-04-22 |
| CN104535586B true CN104535586B (en) | 2017-05-17 |
Family
ID=52851158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410656403.1A Expired - Fee Related CN104535586B (en) | 2014-11-18 | 2014-11-18 | Strip steel edge defect detection identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104535586B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105259252B (en) * | 2015-10-15 | 2018-09-21 | 浙江大学 | Ultrasonic phase array detects polyethylene electric-melting connector defect type automatic identifying method |
| CN105405142B (en) * | 2015-11-12 | 2019-04-05 | 冯平 | A kind of the side defect inspection method and system of glass panel |
| CN107025653A (en) * | 2017-06-17 | 2017-08-08 | 丹凤县荣毅电子有限公司 | A kind of magnet ring detection method based on machine vision |
| CN107764837B (en) * | 2017-09-25 | 2020-12-15 | 北京首钢股份有限公司 | Method and system for judging surface quality of non-oriented electrical steel |
| CN107703150B (en) * | 2017-11-01 | 2020-04-14 | 南昌航空大学 | Detection method and detection system for defects of valve head |
| CN109175763B (en) * | 2018-07-17 | 2021-01-29 | 中国石油天然气集团有限公司 | Detector for welding seam deviation parameter of submerged-arc welding steel pipe |
| CN111363878A (en) * | 2018-12-26 | 2020-07-03 | 山西建龙实业有限公司 | Production control method for edge crack defect of hot rolled steel strip |
| CN109816645B (en) * | 2019-01-18 | 2020-11-17 | 创新奇智(广州)科技有限公司 | Automatic detection method for steel coil loosening |
| CN109623151B (en) * | 2019-02-20 | 2021-06-22 | 中铝瑞闽股份有限公司 | Aluminum coil end face welding system based on point-line laser |
| CN109872292A (en) * | 2019-02-22 | 2019-06-11 | 东华理工大学 | Method for quickly being handled graph image |
| CN110082365B (en) * | 2019-04-08 | 2020-07-03 | 燕山大学 | Robot for detecting quality of edge of steel coil based on machine vision |
| CN110211120B (en) * | 2019-06-04 | 2021-11-02 | 北京航天宏图信息技术股份有限公司 | Method and device for determining corrosion degree of cultural relic and electronic equipment |
| CN110732558B (en) * | 2019-10-29 | 2020-09-08 | 燕山大学 | Online three-dimensional monitoring method for cold-rolled strip shape |
| CN111242894B (en) * | 2019-12-30 | 2022-12-16 | 芜湖哈特机器人产业技术研究院有限公司 | Visual identification method for water pump impeller blades |
| CN111340027A (en) * | 2020-03-05 | 2020-06-26 | 中冶赛迪重庆信息技术有限公司 | Steel pile identification method and system, electronic equipment and medium |
| CN111609795B (en) * | 2020-04-27 | 2021-08-20 | 杭州电子科技大学 | Quality parameter detection method and system for cutting hot rolled steel plate |
| CN112129258B (en) * | 2020-08-24 | 2022-07-26 | 中车唐山机车车辆有限公司 | Scratch depth measuring method |
| CN114333141A (en) * | 2020-09-25 | 2022-04-12 | 深圳富桂精密工业有限公司 | Carton recycling method, electronic device and storage medium |
| CN112275807B (en) * | 2020-09-30 | 2022-11-18 | 首钢集团有限公司 | Method and device for detecting edge platform of hot-rolled strip steel profile |
| CN112733841B (en) * | 2020-12-30 | 2022-12-16 | 中冶赛迪信息技术(重庆)有限公司 | Method, system, equipment and medium for judging internal disorder of steel coil |
| CN113469921B (en) * | 2021-09-06 | 2022-02-08 | 深圳市创世易明科技有限公司 | Image defect repairing method, system, computer device and storage medium |
| CN113962997B (en) * | 2021-12-22 | 2022-03-18 | 武汉同顺源钢构钢模有限公司 | Strip steel edge crack defect detection method and system based on image processing |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005003682A1 (en) * | 2003-07-08 | 2005-01-13 | Heon Jeong | Apparatus for detecting adhered portion or edge of sheet |
| CN101644684A (en) * | 2009-09-11 | 2010-02-10 | 北京科技大学 | On-line detection method for continuous plate blank surface crack |
| CN201653321U (en) * | 2010-03-24 | 2010-11-24 | 宝山钢铁股份有限公司 | Detecting device for edge crack of steel coil |
| JP5561178B2 (en) * | 2010-04-09 | 2014-07-30 | 新日鐵住金株式会社 | Surface defect inspection apparatus, surface defect inspection method, and program |
| CN101871895B (en) * | 2010-05-10 | 2012-05-23 | 重庆大学 | Laser scanning imaging nondestructive inspection method for hot continuous casting blank surface defects |
-
2014
- 2014-11-18 CN CN201410656403.1A patent/CN104535586B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN104535586A (en) | 2015-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104535586B (en) | Strip steel edge defect detection identification method | |
| CN103499585B (en) | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision | |
| CN107808378B (en) | Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features | |
| CN105588845B (en) | A kind of weld defect characteristic parameter extraction method | |
| CN115239704B (en) | Accurate detection and repair method for wood surface defects | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| CN103345632B (en) | A kind of battery tail end surface scratch defect inspection method | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| CN105447512A (en) | Coarse-fine optical surface defect detection method and coarse-fine optical surface defect detection device | |
| CN106682629A (en) | Identification number identification algorithm in complicated background | |
| CN112651968A (en) | Wood board deformation and pit detection method based on depth information | |
| CN106371148A (en) | Millimeter wave image-based human body foreign substance detection method and system | |
| CN104951799A (en) | SAR remote-sensing image oil spilling detection and identification method | |
| CN103914827A (en) | Method for visual inspection of shortages of automobile sealing strip profile | |
| CN110322428B (en) | Method and device for detecting tunnel diseases and electronic equipment | |
| CN109993154A (en) | The lithium sulfur type instrument intelligent identification Method of substation's simple pointer formula | |
| CN116735612B (en) | Welding defect detection method for precise electronic components | |
| CN112857252B (en) | Tunnel image boundary line detection method based on reflectivity intensity | |
| CN104700423A (en) | Method and device for detecting bottle cap | |
| CN101739549A (en) | Face detection method and system | |
| CN110009633A (en) | A kind of detection method of surface flaw of steel rail based on reversed difference of Gaussian | |
| CN100492396C (en) | Method for identifying fabric grain image facing camara weft straightener | |
| CN107240086A (en) | A kind of fabric defects detection method based on integration nomography | |
| CN106709952A (en) | Automatic calibration method of display screen | |
| CN116703847A (en) | Identification method, system, equipment and storage medium for turnout steel rail light band |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170517 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |