CN104512579A - Defect detecting method for bracing wire on transparent packing material - Google Patents
Defect detecting method for bracing wire on transparent packing material Download PDFInfo
- Publication number
- CN104512579A CN104512579A CN201410571540.5A CN201410571540A CN104512579A CN 104512579 A CN104512579 A CN 104512579A CN 201410571540 A CN201410571540 A CN 201410571540A CN 104512579 A CN104512579 A CN 104512579A
- Authority
- CN
- China
- Prior art keywords
- bracing wire
- template
- image
- detected
- curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B57/00—Automatic control, checking, warning, or safety devices
- B65B57/02—Automatic control, checking, warning, or safety devices responsive to absence, presence, abnormal feed, or misplacement of binding or wrapping material, containers, or packages
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a defect detecting method for a bracing wire on a transparent packing material. The method comprises the steps of using an industrial camera to acquire a bracing wire image to be detected and then transmitting the same to a computer; selecting a bracing wire template in a confirming product image according to a template selecting principal; carrying out graying, vertical projection and filter processing to the template and an interest area in the bracing wire image to be detected through the computer, so as to respectively obtain projection curves of the template and the interest area, and determining the position of the bracing wire on the projection curves according to the positions of peaks of wave; carrying out sliding comparison on the projection curve of the image to be detected by the projection curve of the template, calculating a matching factor array according to a matching factor formula matched with the template, finding out a curve section which is most similar to the projection curve of the template on the projection curve of the image to be detected, and judging whether the bracing wire in an existing interest area is missing, deflected and the like according to the coefficient and position of the most similar curve section, so as to realize an aim of detecting the bracing wire on the transparent packing material. The defect detecting method provided by the invention is very high in detection accuracy and has an extensive application space.
Description
Technical field
The present invention relates to bracing wire method of inspection field, specifically a kind of transparent packaging material pull-up line defect method of inspection.
Background technology
At present, on market, the packing box outer wrapping layer of transparent packing of a lot of commodity, can play certain sealing, moisture-proof role, take packaging apart for the ease of user, be pasted with the wide bracing wire of a treaty 2-3mm at the inside face of transparent packaging material.This with the transparent material packaging process of bracing wire in need quality of wire drawing detecting device is installed, bracing wire disappearance, bracing wire skew are detected.Existing detecting device is mainly used in the quality testing of opaque bracing wire, undertaken lacking and offseting judgement by the transceiver being arranged on bracing wire both sides opto-electronic pickup, when bracing wire is qualified, opaque bracing wire shelters from the light that projector is launched, the photodiode of receptor is in not on-state, exports as low level; When there is bracing wire disappearance or bracing wire skew, the light-emitting diode of receptor is in conducting state, exports as high level, judges that whether bracing wire is qualified like this by the outgoing level of receptor.
On market, a lot of transparent packaging material have employed new process and has the water white transparency bracing wire of environmental-protecting performance, the detecting device of opto-electronic pickup is adopted cannot effectively reliably to detect bracing wire defect, often there is flase drop, detection leakage phenomenon, cause off-grade to come into the market, also reduce the work efficiency of packaging facilities simultaneously.Therefore, one actv. method of inspection is more badly in need of, for accurately detecting bracing wire various on market.
Summary of the invention
The object of this invention is to provide a kind of transparent packaging material pull-up line defect method of inspection, to detect the defect such as bracing wire disappearance, skew that the bracing wire on transparent packaging material may occur in packaging process more exactly.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of transparent packaging material pull-up line defect method of inspection, it is characterized in that: adopt industrial camera, LED light source, wherein industrial camera camera lens perpendicular alignmnet bracing wire to be detected, namely industrial camera camera lens becomes 90 degree with bracing wire to be detected, LED light source is installed on industrial camera side, and has the setting angle of 45 degree between LED light source emitting light path and industrial camera;
Utilize industrial camera to gather the image of bracing wire to be detected, the image collected is sent to computing machine by industrial camera after first treatment; Then from certified products image, choose wire drawing template (namely template is the model that the bracing wire in qualified image to be detected generates); Computing machine carries out gray processing, vertical projection, filtering process to the region-of-interest in template and bracing wire image to be detected, the drop shadow curve obtaining both respectively also, according to the position of crest location determination bracing wire from drop shadow curve; With template drop shadow curve in the enterprising line slip contrast of image projection curve to be detected, matching factor formulae discovery according to template matches obtains matching factor array, the segment of curve maximum with template drop shadow curve similarity is found from image projection curve to be detected, according to the coefficient of maximum resemblance and position to judge in current interest region bracing wire whether exist lack, the situation such as skew, and then realize the object detecting bracing wire on transparent packaging material.
The invention has the beneficial effects as follows:
1, have employed industrial camera and the LED light source of special mounting angle, when making the bracing wire on transparent packaging material in disappearance or offset, produce notable difference with normal bracing wire, greatly can reduce the difficulty of image procossing, be applicable to various types of bracing wire and detect.
2, adopt ripe image processing techniques, the image processing algorithm used in the present invention is all ripe algorithms most in use, and all contain these algorithms in various commercialization or the machine vision function library of increasing income, developer can directly call.
3, on the transparent packaging material that proposes of the present invention, bracing wire disappearance, bias detecting method have very high accuracy in detection, can the product of bracing wire existing defects on transparent packaging material be avoided to come into the market by actv., have a wide range of applications space.
Accompanying drawing explanation
Fig. 1 is industrial camera of the present invention and LED light source scheme of installation.
Fig. 2 is the qualified bracing wire image in surveyed area of the present invention.
Fig. 3 is the gray-scale map of qualified bracing wire (template) in region-of-interest of the present invention and correspondence thereof.
Fig. 4 is that in region-of-interest of the present invention, wire drawing template and the surveyed area drop shadow curve that vertical projection obtains separately schemes.
Fig. 5 is drop shadow curve filter effect figure of the present invention.
Fig. 6 is the drop shadow curve figure that crack conditions appears in bracing wire of the present invention.
Fig. 7 is the drop shadow curve that bracing wire of the present invention deviates from surveyed area.
Detailed description of the invention
Shown in Figure 1, a kind of transparent packaging material pull-up line defect method of inspection, adopt industrial camera, LED light source, wherein industrial camera camera lens perpendicular alignmnet bracing wire to be detected, namely industrial camera camera lens becomes 90 degree with bracing wire to be detected, LED light source is installed on industrial camera side, and has the setting angle of 45 degree between LED light source emitting light path and industrial camera;
Utilize industrial camera to gather the image of bracing wire to be detected, the image collected is sent to computing machine by industrial camera after first treatment; Then from certified products image, choose wire drawing template (namely template is the model that the bracing wire in qualified image to be detected generates); Computing machine carries out gray processing, vertical projection, filtering process to the region-of-interest in template and bracing wire image to be detected, the drop shadow curve obtaining both respectively also, according to the position of crest location determination bracing wire from drop shadow curve; With template drop shadow curve in the enterprising line slip contrast of image projection curve to be detected, matching factor formulae discovery according to template matches obtains matching factor array, the segment of curve maximum with template drop shadow curve similarity is found from image projection curve to be detected, according to the coefficient of maximum resemblance and position to judge in current interest region bracing wire whether exist lack, the situation such as skew, and then realize the object detecting bracing wire on transparent packaging material.
As shown in Figure 1, industrial camera becomes 90 degree to install with bracing wire to be detected for industrial camera and LED light source scheme of installation, and adopt LED light source, light source is installed on industrial camera side, and the setting angle of LED light source and industrial camera is about 47 degree.Because industrial camera and LED light source have employed special mounting angle, make bracing wire on transparent packaging material when bracing wire disappearance, skew, produce notable difference with normal bracing wire.During actual installation, can LED light source and industrial camera be sealed in housing, before camera lens and LED light source, all install case hardened glass sheet additional, avoid the outside environmental elements such as natural daylight to affect bracing wire image quality to be detected.
Fig. 2 is the intact transparent wire stay collected.This method adopts the template matches based on projection, converted by image gray projection, form One Dimensional Projection data (characteristics of image), and carry out Rapid matching with one-dimensional data, intact or the appearance disappearance regardless of bracing wire, skew, in region-of-interest all can there is a best matching factor in characteristics of image and template characteristic, according to the matching factor that Treatment Analysis draws, computing machine judges whether current interest region exists defect, namely when optimum matching coefficient is less than a reference value of default, then think that this region-of-interest exists defect, and then realize detecting bracing wire disappearance, the object of skew.
Computing machine carries out the process such as gray processing, vertical projection, filtering by image processing techniques successively to the bracing wire image that industrial camera photographs, then carry out template matches with the data for projection of the data for projection after process and template, calculate a best match position and matching factor.Gray processing is that the bracing wire RGB image in order to be photographed by industrial camera is converted to single pass GRAY image, improves follow-up processing speed; Vertical projection is in order to two dimensional image is done projective transformation, is the data characteristics of the one-dimensional space by the Feature Conversion of bracing wire in image, is beneficial to follow-up fast Template Matching; Filtering is some interfering datas in order to eliminate in data for projection, ensures the accuracy of follow-up template matches; Whether the best match position and the matching factor that calculate detected image data for projection and template data for projection damage with bracing wire to judge whether bracing wire offsets.
Fig. 3 is the former figure of wire drawing template and gray-scale map in region-of-interest, and template image should be intact bracing wire part, size and the bracing wire sizableness chosen in surveyed area.All carries out template matches with template image with a certain eigenwert in surveyed area, and then judge the whether qualified of bracing wire in surveyed area.
Fig. 4 is that the intact surveyed area of wire drawing template image and bracing wire carries out gray scale vertical projection and converts the one-dimensional curve formed, and the columns of abscissa representative image, ordinate represents average gray value.Can draw from figure the feature of template drop shadow curve be two side datas steadily and value is lower, middle bracing wire part presents four crest shapes and left side crest is maximum, and also can find from the drop shadow curve of surveyed area one section of curve and template drop shadow curve similar, just can find a best match position and optimum matching coefficient so template drop shadow curve mated in surveyed area drop shadow curve.
Fig. 5 is the effect of the drop shadow curve in Fig. 4 being carried out to filtering process, after filtering after process, the influence power of some interfering datas on original projection curve can be weakened, is presented as that in drop shadow curve, burr is less in Figure 5, can improve the accuracy of follow-up template matches like this.
Fig. 6 is the vertical projection curve of surveyed area under wire drawing template image and bracing wire breakage, when bracing wire occurs damaged, the position average gray value that in drop shadow curve, bracing wire is corresponding is lower, namely 4 crest values all compared with normal time much lower, just comparatively a reference value is low for the matching factor of such template matches, thus judges that this bracing wire is damaged bracing wire.
Fig. 7 is the vertical projection curve of surveyed area under wire drawing template image and bracing wire drift condition, when bracing wire offsets away, drop shadow curve does not just have normal 4 crests, the matching factor of such template matches is lower, thus can judge that this region does not have bracing wire.
Normal to bracing wire, bracing wire is damaged and bracing wire offsets out the situations such as surveyed area and adopts the method to detect, and obtains optimum matching coefficient results as shown in table 1.Can see that from the table of optimum matching coefficient to(for) the qualified bracing wire of transparent wire stay is between 0.3 ~ 0.4, and when rupturing a part, 0.1 ~ 0.15 directly, deviate from the situation of surveyed area completely in bracing wire, its matching factor is close to 0 for its matching factor.So just can set the matching factor of qualified bracing wire respectively according to secondary test result: 0.25 is proper.
Table 1 transparent wire stay is in varied situations according to the optimum matching coefficient table that matching factor computing formula calculates
The present invention is based on the problem such as bracing wire disappearance, bracing wire skew that the bracing wire on machine vision technique detection transparent packaging material may occur in packaging process.There is very high accuracy in detection, can bracing wire faulty goods be avoided to come into the market by actv., have a wide range of applications space.
Claims (1)
1. a transparent packaging material pull-up line defect method of inspection, it is characterized in that: adopt industrial camera, LED light source, wherein industrial camera camera lens perpendicular alignmnet bracing wire to be detected, namely industrial camera camera lens becomes 90 degree with bracing wire to be detected, LED light source is installed on industrial camera side, and has the setting angle of 45 degree between LED light source emitting light path and industrial camera;
Utilize industrial camera to gather the image of bracing wire to be detected, the image collected is sent to computing machine by industrial camera after first treatment; Then from certified products image, choose wire drawing template (namely template is the model that the bracing wire in qualified image to be detected generates); Computing machine carries out gray processing, vertical projection, filtering process to the region-of-interest in template and bracing wire image to be detected, the drop shadow curve obtaining both respectively also, according to the position of crest location determination bracing wire from drop shadow curve; With template drop shadow curve in the enterprising line slip contrast of image projection curve to be detected, matching factor formulae discovery according to template matches obtains matching factor array, the segment of curve maximum with template drop shadow curve similarity is found from image projection curve to be detected, according to the coefficient of maximum resemblance and position to judge in current interest region bracing wire whether exist lack, the situation such as skew, and then realize the object detecting bracing wire on transparent packaging material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410571540.5A CN104512579A (en) | 2014-10-22 | 2014-10-22 | Defect detecting method for bracing wire on transparent packing material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410571540.5A CN104512579A (en) | 2014-10-22 | 2014-10-22 | Defect detecting method for bracing wire on transparent packing material |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104512579A true CN104512579A (en) | 2015-04-15 |
Family
ID=52788533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410571540.5A Pending CN104512579A (en) | 2014-10-22 | 2014-10-22 | Defect detecting method for bracing wire on transparent packing material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104512579A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106091936A (en) * | 2016-06-01 | 2016-11-09 | 中国电子科技集团公司第四十研究所 | A kind of cellophane offset detecting device based on machine vision technique and method |
| CN106442543A (en) * | 2016-10-14 | 2017-02-22 | 龚新林 | Detection method for identifying surface quality of continuous laser seam of metal workpiece online |
| CN107392216A (en) * | 2017-07-27 | 2017-11-24 | 上海同岩土木工程科技股份有限公司 | A kind of duct pieces of shield tunnel circumferential weld method for quickly identifying based on gradation data |
| CN110111312A (en) * | 2019-04-20 | 2019-08-09 | 东莞中科蓝海智能视觉科技有限公司 | The MARK point visible detection method and device of transparent flexible glue paper |
| CN110211113A (en) * | 2019-06-03 | 2019-09-06 | 湖南瑞智健科技有限公司 | A kind of detection algorithm and calculating equipment of groove exception |
| CN110944913A (en) * | 2017-08-04 | 2020-03-31 | 利乐拉瓦尔集团及财务有限公司 | Method and device for applying a sealing strip to a web of packaging material |
| CN113814292A (en) * | 2021-08-10 | 2021-12-21 | 天津恒兴机械设备有限公司 | Stamping cracking defect detection device for automobile stamping parts |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0902275A1 (en) * | 1997-09-12 | 1999-03-17 | Philip Morris Products Inc. | Fold inspection device for transparent overwrap film |
| CN101893580A (en) * | 2010-06-10 | 2010-11-24 | 北京交通大学 | Digital image based detection method of surface flaw of steel rail |
| CN201662538U (en) * | 2010-04-22 | 2010-12-01 | 深圳市润之创科技有限公司 | Digital bracing wire detector |
| CN202089280U (en) * | 2011-01-30 | 2011-12-28 | 沈阳中科朗运科技有限公司 | Visual detection apparatus of small cigarette package and strip package transparent paper drawing line |
| CN102609699A (en) * | 2012-02-17 | 2012-07-25 | 重庆大学 | Device and method for recognizing number of cast workpiece scanned by laser |
-
2014
- 2014-10-22 CN CN201410571540.5A patent/CN104512579A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0902275A1 (en) * | 1997-09-12 | 1999-03-17 | Philip Morris Products Inc. | Fold inspection device for transparent overwrap film |
| CN201662538U (en) * | 2010-04-22 | 2010-12-01 | 深圳市润之创科技有限公司 | Digital bracing wire detector |
| CN101893580A (en) * | 2010-06-10 | 2010-11-24 | 北京交通大学 | Digital image based detection method of surface flaw of steel rail |
| CN202089280U (en) * | 2011-01-30 | 2011-12-28 | 沈阳中科朗运科技有限公司 | Visual detection apparatus of small cigarette package and strip package transparent paper drawing line |
| CN102609699A (en) * | 2012-02-17 | 2012-07-25 | 重庆大学 | Device and method for recognizing number of cast workpiece scanned by laser |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106091936A (en) * | 2016-06-01 | 2016-11-09 | 中国电子科技集团公司第四十研究所 | A kind of cellophane offset detecting device based on machine vision technique and method |
| CN106442543A (en) * | 2016-10-14 | 2017-02-22 | 龚新林 | Detection method for identifying surface quality of continuous laser seam of metal workpiece online |
| CN106442543B (en) * | 2016-10-14 | 2019-10-15 | 龚新林 | A kind of detection method of online recognition metal works continuous laser face of weld quality |
| CN107392216A (en) * | 2017-07-27 | 2017-11-24 | 上海同岩土木工程科技股份有限公司 | A kind of duct pieces of shield tunnel circumferential weld method for quickly identifying based on gradation data |
| CN107392216B (en) * | 2017-07-27 | 2020-06-23 | 上海同岩土木工程科技股份有限公司 | Method for quickly identifying circumferential seams of shield tunnel segments based on gray data |
| CN110944913A (en) * | 2017-08-04 | 2020-03-31 | 利乐拉瓦尔集团及财务有限公司 | Method and device for applying a sealing strip to a web of packaging material |
| CN110111312A (en) * | 2019-04-20 | 2019-08-09 | 东莞中科蓝海智能视觉科技有限公司 | The MARK point visible detection method and device of transparent flexible glue paper |
| CN110211113A (en) * | 2019-06-03 | 2019-09-06 | 湖南瑞智健科技有限公司 | A kind of detection algorithm and calculating equipment of groove exception |
| CN110211113B (en) * | 2019-06-03 | 2021-09-07 | 湖南瑞智健科技有限公司 | Detection algorithm and calculation equipment for groove abnormity |
| CN113814292A (en) * | 2021-08-10 | 2021-12-21 | 天津恒兴机械设备有限公司 | Stamping cracking defect detection device for automobile stamping parts |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104512579A (en) | Defect detecting method for bracing wire on transparent packing material | |
| US8121400B2 (en) | Method of comparing similarity of 3D visual objects | |
| CN103698337B (en) | A kind of adhesion defect of label of flat wine bottle automatic testing method | |
| CN102023168B (en) | Method and system for detecting chips on semiconductor wafer surface | |
| TWI263942B (en) | Method and sensing device for motion detection in an optical pointing device, such as an optical mouse | |
| CN103760170A (en) | Tobacco bale lining defect detection method based on machine vision technology | |
| CN101804907A (en) | Machine vision belt tearing detecting and protecting device | |
| CN109788281B (en) | Light leakage detection method and device of camera module | |
| CN204330609U (en) | Six axis robot AOI detection system | |
| CN104101611A (en) | Mirror-like object surface optical imaging device and imaging method thereof | |
| CN109596631B (en) | Cigarette packet seal wrong-brand detection device and method based on machine vision technology | |
| CN108732507A (en) | A kind of lithium battery defect detecting device based on battery temperature field and visible images | |
| CN109191516B (en) | Rotation correction method and device of structured light module and readable storage medium | |
| CN103712568B (en) | The reflective feature detection system of a kind of plastic pallet based on machine vision | |
| TW201702584A (en) | Method for searching region of interest of electronic component, defect inspection method and device of electronic component using the searching method conducting image binarization on inspection items | |
| CN101676712B (en) | Optical detecting system and method thereof | |
| CN109696240A (en) | Detection method, device and the readable storage medium storing program for executing of the semiconductor laser overall situation uniformity | |
| CN104297250A (en) | Yarn hairiness detection device | |
| CN107782354B (en) | Motion sensor detection system and method | |
| CN107833223B (en) | Fruit hyperspectral image segmentation method based on spectral information | |
| CN210720185U (en) | Small cigarette packet end face detection device based on machine vision technology | |
| CN109040724B (en) | Light spot distortion detection method and device of structured light projector and readable storage medium | |
| US20220216081A1 (en) | Method and device for detecting placement of wafers in wafer cassette | |
| CN109612408B (en) | Method and device for testing emission angle of semiconductor laser and readable storage medium | |
| CN208476813U (en) | Industrial part defect detecting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150415 |
|
| RJ01 | Rejection of invention patent application after publication |