CN101424514B - Band tape graduation on-line automatic detection system and method based on image processing - Google Patents

Band tape graduation on-line automatic detection system and method based on image processing Download PDF

Info

Publication number
CN101424514B
CN101424514B CN2008102040008A CN200810204000A CN101424514B CN 101424514 B CN101424514 B CN 101424514B CN 2008102040008 A CN2008102040008 A CN 2008102040008A CN 200810204000 A CN200810204000 A CN 200810204000A CN 101424514 B CN101424514 B CN 101424514B
Authority
CN
China
Prior art keywords
tape measure
image
video camera
ccd video
computing machine
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.)
Active
Application number
CN2008102040008A
Other languages
Chinese (zh)
Other versions
CN101424514A (en
Inventor
张之江
赵庆祥
曾丹
庄克成
陶江良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
HAIAN SUZHOU UNIVERSITY ADVANCED ROBOT RESEARCH INSTITUTE
Original Assignee
University of Shanghai for Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Shanghai for Science and Technology filed Critical University of Shanghai for Science and Technology
Priority to CN2008102040008A priority Critical patent/CN101424514B/en
Publication of CN101424514A publication Critical patent/CN101424514A/en
Application granted granted Critical
Publication of CN101424514B publication Critical patent/CN101424514B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention relates to a tape measure scale on-line automatic detecting system based on image processing and a method thereof; the system forms a main framework by a CCD video camera, two light source devices (including a direct annular epi-illuminating light source and a side LED light source), a computer equipped with an image capture card, an operating platform provided with a neck and a shielding device, and an alarm bell. The method acquires production line moving tape measure surface images by using the CCD video camera, judges whether the scale, marks and figures on the surface of the tape measure are completely accurate by the computer processing, and further monitors by using the alarm bell. The utility system can automatically check the printing quality of the surface of the tape measure in real time, and has high detecting precision and good accuracy.

Description

Band tape graduation on-line automatic monitoring system and method based on Flame Image Process
Technical field
The present invention relates to a kind of tape measure figure on-line automatic monitoring system and method, the special employing obtained the tape measure surface image and carried out Digital Image Processing and detect the tape measure quality, and be efficient, accurately, and the automaticity height.
Background technology
China is steel tape big producing country, produce per year above more than 1,000,000,000 meter, the production of steel tape is to be imprinted on the strain line of specified accuracy on the steel band continuously with the rolling template, because how odjective causes such as printing equipment are carried out quality testing to the steel tape printing accurately and are become important link in the tape measure production run.The quality testing means that present China is taked are also more original, and quality detection apparatus is simpler and cruder, mainly are to detect by artificial sampling, and labour intensity is big, the loss height, and accuracy of detection is low, and poor reliability can't write down testing result automatically.Along with development of science and technology, Computer Processing speed is fast, and the advantage that automaticity is high more and more is applied in the checkout equipment, and wherein computer digital image is treated as an important means of quality testing.
At first adopt CCD to obtain the surface image of product in the industrial processes, utilize computing machine that image is discerned then, conversion, cutting after the various Treatment Analysis such as separation, transports out the result at last, automatically product quality is detected according to the result.Utilize the product surface image to carry out quality detection technology at present and begun to be applied to during other products detect, for example utilize 6 ccd video cameras that the packaging quality of each face of cigarette case is detected automatically and based on the cotton knot and the magazine on-line detecting system of video.In the production run of tape measure, part technology has also begun to adopt Digital Image Processing to simplify workflow, utilizes two ccd video cameras that tape measure length is carried out robotization and detects.With mechanical arm or manually tape measure is aligned zero point, 2 cameras align respectively and require the length mark district, automatically detect mark lengths whether in error range with methods such as Flame Image Process, pattern-recognitions after the images acquired, improved detection speed and precision greatly.Yet because the complicacy on tape measure surface, tight tinyization of band tape graduation, and tape measure detects the high precision that requires rests on the primitive stage to the detection of tape measure surface printing quality always.
Summary of the invention
The object of the present invention is to provide a kind of automatically, accurately, band tape graduation on-line automatic monitoring system and method at a high speed based on Flame Image Process.The present invention utilizes the regularity of tape measure figure, adopts ccd video camera to obtain surface image and handles, and judges, thereby realizes onlinely, in real time tape measure surface printing quality is detected.
For achieving the above object, the utility model adopts following technical proposals:
A kind of band tape graduation on-line automatic monitoring system based on Flame Image Process, comprise a ccd video camera, a computing machine and a stream line operation platform that is equipped with image pick-up card, it is characterized in that: two tape measure draw-in grooves and a shield assembly that the guiding tape measure is housed on the described stream line operation platform table top, described ccd video camera is fixed on the shield assembly directly over the tape measure, the tape measure surface is aimed in the visual field, a direct ring-type falls to penetrating light source around being fixed on the described ccd video camera, a side led light source is fixed on the shield assembly of ccd video camera below side, and tape measure can pass from two draw-in grooves on the operating platform; Described computing machine is connected with described ccd video camera and is connected with the warning alarm bell by outlet terminal by its image pick-up card, is provided with the surface printing trace routine of a cover according to the compiling of tape measure surface characteristics in the computing machine; With different tape measure surface abstract be a group system parameter, obtain the tape measure surface image by ccd video camera, utilize computing machine the tape measure surface image to be carried out analyzing and processing by program compiler.
The effect of system's critical piece:
Directly ring-type falls to penetrating light source: ring-type falls to penetrating light source can be provided evenly, the illumination of low reflection.Light source is provided on the one hand the sealing photographed scene, can prevents that on the other hand uneven illumination from influencing picture quality.
The side led light source: because bubble may appear in the tape measure surface, thus utilize the side light source reflective by bubble, and then obtain bubble diagram by CCD and look like to analyze.
Tape measure draw-in groove: prevent because the tape measure material flexibility is strong, elongated, and the outside is involute and cause the deformation of tape measure amplitude, thereby influence photographs the effect on tape measure surface, and increase difficulty and the error that detects.
Shield assembly: because ccd video camera is for illumination sensitivity very, shielding can prevent the illuminated the way instability of image pixel of ambient light.
A kind of band tape graduation on-line automatic monitoring system and method based on Flame Image Process, adopt above-mentioned system to detect, it is characterized in that: earlier under the drive of thread band tape at travelling belt with specific uniform rate by the draw-in groove in the platform, entering in the ccd video camera visual field slowly then, the computing machine of process assembling image pick-up card is to the collection of image, treatment of picture, Feature Extraction, and the judgement of view data and control, final result is sent in the warning alarm bell by output device, thereby realize robotization, objective, contactless, high-precision on-line detecting system.
Computing machine is as follows to tape measure surface image handling procedure step:
1) pre-service:
(1) read in a two field picture,
(2) figure image intensifying,
(3) image binaryzation, color conversion,
(4) image filtering
2) the meter ruler scale detects,
3) meter ruler Digital Detecting,
4) foot detects.
Repeating step 1)~4), being implemented in the linear flow waterline detects.
System and method of the present invention is compared with existing tape measure surface inspecting method, has following conspicuous outstanding substantive distinguishing features and remarkable advantage:
1. use video camera as sensor, obtain the tape measure surface, really realized the robotization detection thereby replace naked eyes.
2. because CCD can be apart from shooting, thus can realize non-contact detection, thus prevent swiping tape measure surface.
3. use various image processing algorithms, the single-frame images in the image sequence is carried out scale and Digital Detecting.
4. has stronger adaptability.Abstract to different tape measures is one group of tape measure parameter, can adapt to different tape measures by simple modification environmental parameter and detect, and makes the range of application of system become wide.
5. accuracy of detection height, speed is fast, and real-time is good.Native system utilizes ccd video camera to obtain image, by Computer Analysis, handles and judgement, and all operations all is an automation process, thereby can realize in real time, fast, accurately detects judgement.
Description of drawings
Fig. 1 is the one-piece construction synoptic diagram of this practicality invention system.
Fig. 2 is the process flow diagram of the tape measure surface analysis determining program of Fig. 1 example.
Embodiment
Details are as follows in conjunction with the accompanying drawings for a preferred embodiment of the present invention:
Referring to Fig. 1, this is based on the band tape graduation on-line automatic monitoring system of Flame Image Process, comprise a ccd video camera 1, a computing machine 8 and a stream line operation platform 6 that is equipped with image pick-up card, two tape measure draw-in grooves 7 and a shield assembly 4 of guiding tape measure 5 are housed on described stream line operation platform 6 table tops, described ccd video camera 1 is fixed on the shield assembly 4 directly over the tape measure, the tape measure surface is aimed in the visual field, a direct ring-type falls to penetrating light source 2 around being fixed on the described ccd video camera 1, a side led light source 3 is fixed on the shield assembly 4 of ccd video camera below side, and tape measure 5 can pass from two draw-in grooves 7 on the operating platform 6; Described computing machine 8 is connected with described ccd video camera 1 and is connected with warning alarm bell 9 by outlet terminal by its image pick-up card, is provided with the surface printing trace routine of a cover according to the compiling of tape measure surface characteristics in the computing machine 8; With different tape measure surface abstract be a group system parameter, obtain the tape measure surface image by ccd video camera 1, utilize computing machine 8 the tape measure surface image to be carried out analyzing and processing by program compiler.
Referring to Fig. 2, the band tape graduation online automatic detection method based on Flame Image Process of present embodiment adopts said system to detect.Computer Image Processing is analyzed: in the Vision Builder for Automated Inspection, the treatment technology of visual information mainly depends on image processing method, comprises the image graph image intensifying,, level and smooth, edge sharpening is cut apart, feature extraction, contents such as image recognition and understanding.After these processing, the quality of output image improves, and is convenient to computing machine image is further analyzed, and handles and identification, judges.Computing machine is to tape measure surface image handling procedure step (as Fig. 2):
1) pre-service.
(1) system's ccd video camera is to gather in the mode of frame/field, in view of the requirement of product of production line quality (within 1/4 millimeter of the error, speed per second 5-6 rice), with video camera CCD hardware (resolution pixel 768*576, frame per second 100/ second) length that basis, system's ccd video camera single frames obtain tape measure is 10cm.
(2) figure image intensifying because the tape measure figure is intensive, must strengthen the pixel of needs.What native system adopted is the spatial domain enhancement techniques, utilizes the linear smoothing technology will need the scale that detects, and numeral strengthens.
(3) image binaryzation, the image that obtains from the colored CCD camera all is the RGB image, has blue (B) three compositions of red (R) green (G) to determine the color value of a point in the space.But these aberration are different from the sensation of human eye, even very little noise, perhaps the influence of illumination all can change the rgb value of position in the space.For these reasons, native system is converted into more stable HIS color space pattern, wherein H (tone), S (color saturation) and brightness (I) relatively with the rgb space pixel value.Conversion formula (suc as formula 1) is used H then, and S, I and given three threshold ratios are converted into black (needing to detect color) and (background color) two kinds of colors in vain with colour.Binaryzation has improved the contrast of image, thereby is convenient to next step detection and processing.
I = ( R + G + B ) / 3 ; H = { 90 - arctan ( F / 3 ) + ( 0 , G > B ; 180 , G < B ) } / 360 ; S = 1 - min ( R , G , B ) / I ; Formula 1
(4) image filtering, because the scale on tape measure surface is a vertical direction, pixel is based on vertical line, so native system has adopted the mean filter operator, wherein template (suc as formula R) has improved the effect of filtering.
R = 1 3 1 1 3 1 1 3 1 f ( 2,2 ) = &Sigma; i = 1 i = 3 &Sigma; j = 1 j = 3 f ( i , j ) * k ( i , j ) &Sigma; i = 1 i = 3 &Sigma; j = 1 j = 3 k ( i , j ) Wherein (i j) is the template weights to k.
2) scale detects.
The pattern on tape measure surface mainly contains by scale and numeral to be formed.The first half on tape measure surface is a foot standard, and the latter half is the meter ruler standard.It is that benchmark comes single frames to detect that native system detects with the 10cm meter ruler, thereby realizes continuous detecting fast.
Determine the single frames detection reference, in ccd image, find out former frame and detect end point (promptly long calibration points) behind the 10cm, according to the distribution characteristics of scale, detect scale one by one then.Because after CCD obtains image, scale distortions that can become, interruption is so CCD must allow such error, so native system adopts search pattern as shown below to search for.
With pixel reference point (being black) is starting point, order according to a->h begins to search for scale pixel (black) then, in a single day when searching scale pixel (for example f), stop search, basic point moves to new scale pixel (f), again search when search highly surpasses scale mark, illustrates that scale mark is complete.Same principle, and then can judge the integrality of 10cm scale mark.
3) Digital Detecting
When 1cm judges in search in system, determine the reference point of 1cm, search for then with the digital rectangular area of reference point as relative position, with the respective digital data of having deposited in the numerical data base carry out right, calculate matching degree at last, size according to matching degree and threshold value compares, the final integrality of judging numeral.
4) foot
The foot of the first half of standard tape measure detects according to the meter ruler relative position of the latter half determines sensing range, and scale is identical with the digital detection and the detection principle of meter ruler.
System obtains continuous single-frame images by ccd video camera, and through the single frames collection, single frames is handled, and single frames judges, thus realize to the tape measure surface in real time, efficient fast, robotization accurately detects.

Claims (2)

1. band tape graduation on-line automatic monitoring system based on Flame Image Process, comprise a ccd video camera (1), a computing machine (8) and a stream line operation platform (6) that is equipped with image pick-up card, it is characterized in that: two tape measure draw-in grooves (7) and a shield assembly (4) that guiding tape measure (5) is housed on described stream line operation platform (6) table top, described ccd video camera (1) is fixed on the shield assembly (4) directly over the tape measure, the tape measure surface is aimed in the visual field, a direct ring-type falls to penetrating light source (2) around being fixed on the described ccd video camera (1), a side led light source (3) is fixed on the shield assembly (4) of ccd video camera below side, and tape measure (5) can pass from last two draw-in grooves of operating platform (6) (7); Described computing machine (8) is connected with described ccd video camera (1) and is connected with warning alarm bell (9) by outlet terminal by its image pick-up card, is provided with the surface printing trace routine of a cover according to the compiling of tape measure surface characteristics in the computing machine (8); With different tape measure surface abstract be a group system parameter, obtain the tape measure surface image by ccd video camera (1), utilize computing machine (8) the tape measure surface image to be carried out analyzing and processing by program compiler.
2. band tape graduation online automatic detection method based on Flame Image Process, adopt the band tape graduation automatic checkout system based on Flame Image Process according to claim 1 to detect, it is characterized in that at first under the drive of thread band tape (5) at travelling belt with uniform rate by the tape measure draw-in groove (7) on the operating platform (6), entering in ccd video camera (1) visual field slowly then, the image of picked-up is imported computing machine (8) through image pick-up card, subsequently by the collection of computing machine (8) to image, treatment of picture, Feature Extraction, and the judgement of view data and control, net result is sent to warning alarm bell (9) by output device; Computing machine (8) is as follows to tape measure surface image handling procedure step:
A. pre-service:
I. read in a two field picture,
Ii. figure image intensifying,
Iii. image binaryzation, color conversion,
Iv. image filtering
B. the meter ruler scale detects,
C. meter ruler Digital Detecting,
D. foot detects;
Repeating step a~d is implemented in the linear flow waterline and detects.
CN2008102040008A 2008-12-04 2008-12-04 Band tape graduation on-line automatic detection system and method based on image processing Active CN101424514B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2008102040008A CN101424514B (en) 2008-12-04 2008-12-04 Band tape graduation on-line automatic detection system and method based on image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2008102040008A CN101424514B (en) 2008-12-04 2008-12-04 Band tape graduation on-line automatic detection system and method based on image processing

Publications (2)

Publication Number Publication Date
CN101424514A CN101424514A (en) 2009-05-06
CN101424514B true CN101424514B (en) 2010-11-17

Family

ID=40615278

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2008102040008A Active CN101424514B (en) 2008-12-04 2008-12-04 Band tape graduation on-line automatic detection system and method based on image processing

Country Status (1)

Country Link
CN (1) CN101424514B (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5267891B2 (en) * 2010-09-30 2013-08-21 横河電機株式会社 Device for measuring position and shape of pattern formed on sheet and coating pattern measuring device
CN102288611A (en) * 2011-04-27 2011-12-21 苏州工业园区天势科技有限公司 Printing quality detecting equipment
CN102303019B (en) * 2011-04-29 2013-01-02 无锡众望四维科技有限公司 Method for automatically detecting scales of injector needle cylinders by using machine vision system
CN102506625A (en) * 2011-10-25 2012-06-20 北华航天工业学院 Automatic calibration system for error of steel tape
CN102607361B (en) * 2012-03-29 2014-06-11 重庆大学 Automatic detection device for double-row-graduated-line measuring instrument
CN103234407B (en) * 2013-04-10 2015-08-26 北华航天工业学院 A kind of Steel Ruler calibrating installation
CN104165591A (en) * 2014-09-12 2014-11-26 东莞市三姆森光电科技有限公司 Fully-automatic optical size detection method and system for metal shell
CN104315936A (en) * 2014-10-29 2015-01-28 四川金码科技有限公司 Video measuring tool based on camera
CN104677221B (en) * 2015-03-16 2017-08-29 河海大学常州校区 A kind of Intelligent measuring tape and its measuring method based on cmos image sensor
CN106839918A (en) * 2017-03-24 2017-06-13 盐城工学院 A kind of tape data logger and tape
CN107623814A (en) * 2017-08-09 2018-01-23 广东欧珀移动通信有限公司 The sensitive information screen method and device of shooting image
CN107478654A (en) * 2017-09-21 2017-12-15 桐城市闲产网络服务有限公司 A kind of computer system motherboard intelligent checking system
CN112170254B (en) * 2020-08-29 2022-05-06 宁波巨丰工具实业有限公司 On-line detection device for defects of tape measure
CN113624091B (en) * 2021-08-18 2024-01-02 深圳市菁菁教育网络技术有限公司 Detection device capable of testing quality of graduated scale
CN114707904A (en) * 2022-05-05 2022-07-05 江苏文友软件有限公司 Quality detection method and system based on big data

Also Published As

Publication number Publication date
CN101424514A (en) 2009-05-06

Similar Documents

Publication Publication Date Title
CN101424514B (en) Band tape graduation on-line automatic detection system and method based on image processing
CN102176228B (en) Machine vision method for identifying dial plate information of multi-pointer instrument
CN109454006A (en) Chemical fiber wire ingot is stumbled the device and its detection stage division of a defect on-line checking and classification
CN108109137A (en) The Machine Vision Inspecting System and method of vehicle part
CN104256882B (en) Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision
CN106824806A (en) The detecting system and detection method of the low module plastic gear based on machine vision
CN109507192A (en) A kind of magnetic core detection method of surface flaw based on machine vision
CN104132897B (en) A kind of nitrogenous measuring method of plant leaf blade based on handheld device and device
CN104198325B (en) Stem ratio measuring method in pipe tobacco based on computer vision
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN110018172B (en) Product detection system and method
CN103454285A (en) Transmission chain quality detection system based on machine vision
CN104729426A (en) Automatic angle iron online detecting system and method based on machine vision
CN102988052B (en) Method and system for measuring foot length
CN107891012B (en) Pearl size and circularity sorting device based on equivalent algorithm
CN110567976A (en) mobile phone cover plate silk-screen defect detection device and detection method based on machine vision
CN107734329A (en) A kind of detecting system and detection method of baseband digital video frame per second
CN105004722A (en) Method for rapidly detecting maturity of tobacco leaves
CN109003271A (en) A kind of Wiring harness connector winding displacement quality determining method based on deep learning YOLO algorithm
CN102663340A (en) Device and method for classifying plates
CN104132945A (en) On-line surface quality visual inspection device for bar based on optical fiber conduction
CN110223276A (en) A kind of bottle cap detection method and device based on image procossing
CN114280075A (en) Online visual inspection system and method for surface defects of pipe parts
CN108195847A (en) A kind of relief pattern Online Video detection device and its detection method
CN206951597U (en) A kind of Blueberry hierarchical detection system based on machine vision

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
ASS Succession or assignment of patent right

Owner name: HAIAN SUSHI TECHNOLOGY TRANSFORMATION CENTER CO.,

Free format text: FORMER OWNER: SHANGHAI UNIVERSITY

Effective date: 20140516

C41 Transfer of patent application or patent right or utility model
COR Change of bibliographic data

Free format text: CORRECT: ADDRESS; FROM: 200444 BAOSHAN, SHANGHAI TO: 226600 NANTONG, JIANGSU PROVINCE

TR01 Transfer of patent right

Effective date of registration: 20140516

Address after: 226600 Yingbin Road 8, Haian Town Development Zone, Jiangsu, Nantong

Patentee after: Haian Su Fu Technology Transfer Center Co., Ltd.

Address before: 200444 Baoshan District Road, Shanghai, No. 99

Patentee before: Shanghai University

ASS Succession or assignment of patent right

Owner name: HAIAN SUZHOU UNIVERSITY ADVANCED ROBOT RESEARCH IN

Free format text: FORMER OWNER: HAIAN SUSHI TECHNOLOGY TRANSFORMATION CENTER CO., LTD.

Effective date: 20141202

C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20141202

Address after: No. 8 Haian County in Jiangsu province was 226600 Avenue in Nantong City

Patentee after: HAIAN SUZHOU UNIVERSITY ADVANCED ROBOT RESEARCH INSTITUTE

Address before: 226600 Yingbin Road 8, Haian Town Development Zone, Jiangsu, Nantong

Patentee before: Haian Su Fu Technology Transfer Center Co., Ltd.