CN101063662A - Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP - Google Patents
Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP Download PDFInfo
- Publication number
- CN101063662A CN101063662A CN 200710028028 CN200710028028A CN101063662A CN 101063662 A CN101063662 A CN 101063662A CN 200710028028 CN200710028028 CN 200710028028 CN 200710028028 A CN200710028028 A CN 200710028028A CN 101063662 A CN101063662 A CN 101063662A
- Authority
- CN
- China
- Prior art keywords
- bottle
- image
- dsp
- empty bottle
- bottle bottom
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
This invention relates to one hollow bottle bottom deficiency test method and its device, which comprises the following steps: image pre-processing to adjust image grey even value to limit the image brightness into certain range; b, fringe extracting to exert Sobel formula to get bottle bottom fringe image; c, realizing image cut by use of central point and edge point to divide the image into several areas; d, judging whether there is dirty in the area; e, accordingly determining whether to eliminate bottle.
Description
Technical field
The present invention relates to a kind of detection method of empty bottle bottom defect and, be particularly useful for the imperial crown beer bottle based on the empty bottle bottom defect pick-up unit of DSP.
Background technology
Beer, beverage production enterprise more and more pay attention to the quality of product at present, yet quality, outward appearance and the cleanliness of the bottle of beer, beverage production line also do not reach desired target far away at present, particularly beer industry carries out the returnable bottle that repeated washing utilizes again for beer bottle at present, in different poses and with different expressions especially, multifarious, sort out underproof bottle so before bottle washing machine washing back, can, need to detect, and whether have at the bottom of in test item, all can comprising usually bottle damaged this.
Traditional production line empty bottle check system is manually to finish, and bottle is when being installed in the light test box on carrier chain road next door, and naked eyes are observed, and find that defective bottle carries out craft and takes out.This manual detection standard is fuzzy, is subjected to artificial factor to a great extent, can not keep constant standard, and accuracy of detection is low, and speed is slow.Development along with the Modern High-Speed canning line, the inferior position of human eye in detecting link protruded more, such as: owing to repeat work for a long time, the tired easily and meeting generation error that works long hours of eyes, even if these gaps all evade falling, one is rich in experienced detection employee and also can not surmounts a visual detection equipment that performance is common.
And detect disposal route at the bottom of existing some beer bottle is to take a bottle base map picture by camera, and detection algorithm moves on general industrial computer and image processing software platform to be implemented.General industrial computer makes call processing pragram can not guarantee hard real-time, thereby can occur detecting overtime or the omission phenomenon owing to the time-sharing characteristic of operating system, and then makes rejecting judgement system produce disorderly.
Summary of the invention
The purpose of this invention is to provide a kind of easy realization robotization, identification accurately, the detection method of a kind of empty bottle bottom defect of high efficiency;
Another object of the present invention provides a kind of robotization, discerns a kind of empty bottle bottom defect pick-up unit based on DSP accurate, high efficiency.
For achieving the above object, the technical solution used in the present invention is:
A kind of detection method of empty bottle bottom defect, its special feature is, comprises the steps:
1), image pre-service
Adjust the average gray of image, the brightness stability that makes whole sub-picture is among certain scope;
2), do edge extracting
Image is applied the Sobel operator obtain bottle base map as outline map;
3), realize cutting apart of image
Choose the rational marginal point and the center of circle, obtain bottle base map then and resemble actual central point and radius value, thereby realized visual location, utilize central point and the circle that the marginal point that obtains simulates that image segmentation is several regions again;
4), judge in the zone that is partitioned into whether dirt is arranged;
5), determine according to judged result whether needs are rejected.
Wherein in the step 3) bottle base map resembled be divided into three zone: a, center relatively flat portions be a border circular areas; Between b, center circle territory and the anti-skidding line, what the angle of inclination was bigger is an annular region; C, contain the annular region of anti-skidding line.
A kind of empty bottle bottom defect pick-up unit based on DSP, its special feature is, comprise and to make empty bottle to be detected bottleneck and all unsettled connecting gear of bottle bottom branch in surveyed area, corresponding photoelectric sensor is installed in surveyed area, above the position of bottleneck in surveyed area camera is installed, the polarisation filter is installed between this camera lens and position of bottleneck, below the bottle position, the end in surveyed area light source is installed, between this light source and bottle position, the end, the Polarizer that cooperates with aforementioned polarisation filter is installed; Also comprise a controller, thereby the aforementioned lights electric transducer is electrically connected the location triggered information that transmits empty bottle with the I/O port of this controller, thereby the I/O port of this controller is electrically connected some bright light source with the control end of camera and light source respectively and takes pictures; Thereby aforementioned image of camera output terminal is electrically connected with the input end of an analog to digital converter and converts digital picture to, the output terminal of this analog to digital converter is electrically connected with a CPLD, thereby external two storeies of this CPLD also are electrically connected the image that will receive and are saved in behind a slice storer and it are exported to DSP and carry out defective and judge with a DSP, receive new image by another sheet storer simultaneously and treat to switch once more after DSP disposes; The output terminal of aforementioned DSP is electrically connected with the empty bottle rejecting mechanism.
Its middle controller is PLC.
Wherein a bottleneck in surveyed area and a bottle bottom are put and other are separately installed with corresponding photoelectric sensor, thereby this photoelectric sensor all is electrically connected with the I/O port of described controller and transmits the bottleneck and the location triggered information at bottle end respectively.
Wherein connecting gear is the travelling belt of clamping empty bottle to be detected both sides.
Wherein light source is the led light source that has the stroboscopic controller, and this stroboscopic controller is electrically connected with the I/O port of described controller.
Wherein Polarizer is coated with waterproof sealing layer and PMMA plastics successively near a side of bottle position, the end, perhaps between Polarizer and bottle position, the end cover glass is installed.
Detection method provided by the invention can be applied in the checkout equipment easily, thereby realizes the robotization of the high speed of empty bottle bottom defect, high discrimination is detected.Owing to adopted combination at the image processing algorithm of the uniqueness of domestic vial characteristic, have the characteristics that adaptability is strong, processing speed is fast, be fit to very much the online detection of the vial on the high-speed production streamline.
Pick-up unit provided by the invention is simple in structure, can robotization, high efficiency to existing defective bottle of defective to carry out correct rejecting.On high-speed production lines, adopt the mode of machine vision to detect automatically, overcome the subjectivity influence that exists in the human eye detection and fatiguability, inefficient defective, improved the accuracy and the production efficiency that detect.
Description of drawings
Accompanying drawing 1 is a structural representation of the present invention;
Accompanying drawing 2 is a structural representation of the present invention;
Accompanying drawing 3 is the system construction drawing of surface-mounted integrated circuit (1) among the present invention;
Accompanying drawing 4 for bottle base map among the present invention as edge extracting figure.
Embodiment
The present invention is further detailed explanation below in conjunction with accompanying drawing:
As shown in Figure 1, 2, the present invention utilizes a pair of polarisation filter 6 and Polarizer 7, the light vibration of employing polarisation of light characteristic and 7 pairs of different directions of Polarizer has the performance of the absorption selected, and by regulating the angle of two polarizing appliances, obtains the transparent foreign matter image of high-contrast.The dazzle on smooth glass surface can also be eliminated or weaken to polarisation filter 6 on camera 2 camera lenses simultaneously, shows the details and the feature of transparent foreign matter better.
Adopt LED as light source 4, led light source is compared with conventional light source, has following long service life, the brightness height, and response speed is fast, advantages such as shape freedom.Employing stroboscopic controller is controlled the flicker of led light source, and synchronous with the exposure time maintenance of camera 2 (specifically can adopt the CCD camera), thereby can obtain the motion video of " solidifying " no smear, for guaranteeing clear being very helpful of transparent foreign matter imaging.And strobe mode illumination can obtain throw light on 20 times the brightness of normal bright mode, has improved the brightness of light source 4, and has increased the serviceable life of light source 4, eliminates the interference of ambient light.
As shown in Figure 2, shape facility and detection content according to bottle, adopt the gimmick of back lighting, the advantage of this lighting system is, the edge contour of measured object can be sketched the contours of clearly, because in image, the place that measured object blocked is a black, unscreened place is a white, forms in white and black image that is easy to image analysis.
Because vial is better than its reflecting properties to the optical transmission performance, so we adopt a side at the bottom of the bottle (be Fig. 2 under the bottle side) to carry out polishing with transmitted light source 4, CCD camera 2 is gathered visual scheme from opposite side (being bottleneck top Fig. 2).This just needs bottle unsettled segment distance in the process of operation, we clamp the bottle operation with four feed belts 3, so both guaranteed that bottle was unsettled, guaranteed that also bottle is in the vertical property perpendicular to the bottle traffic direction, consider the characteristics of bottle shape simultaneously, we place below, bottle bottom with light source 4, and CCD camera 2 places the bottleneck top to resemble from bottleneck collecting bottle base map.Because bottleneck is smaller and the limitation of bottle wall is arranged, adopt this scheme to require bottle when gathering image, must be kept upright, and the trigger pip of camera 2 is wanted accurately.
When empty bottle to be detected moves to CCD camera 2 belows, empty bottle to be detected is taken pictures at the bottom of triggering photoelectric sensor 5 (optoelectronic switch) and then triggering stroboscopic light source 4 and 2 pairs of bottles of CCD camera, specifically adopts two photoelectric sensors 5 (respectively by bottleneck and bottle position, the end) to cooperate connecting gear 3 to realize the solid location of vial.Guarantee the accuracy that CCD camera 2 is gathered so on the one hand, on the other hand according to the combined information of two photoelectric sensor 5 signals, can judge whether run-off the straight on working direction of bottle, if run-off the straight then directly give surface-mounted integrated circuit 1 signal, image is not handled, carry out secondary detection on the endless conveyor but directly bottle is rejected, thereby reduce mistake rejecting rate.
The light of stroboscopic light source 4 in conjunction with polarisation filter 6, makes foreign matter form gloomy zone on bottle base map picture at the bottom of camera 2 receiving bottles of bottleneck top.The requirement (as Fig. 2) of coverage will be satisfied in the height of camera 2, position, and the image of camera 2 sends to surface-mounted integrated circuit 1 and carries out graphical analysis.
Principle of work of the present invention is:
When bottle moves to the detection position, optoelectronic switch detects bottle and reaches, produce trigger pip and give PLC, PLC sends synchronizing signal to camera 2 and stroboscopic controller respectively, so that camera 2 begins exposure when stroboscopic light source 4 brightness are maximum, light source 4 can " solidify the bottle of motion " in image like this, between light source 4 and bottle position, the end, a Polarizer 7 is installed, can be converted to the light that led light source sends polarization light like this, whether have foreign matter at the bottom of the angle that is installed in the polarisation filter 6 on camera 2 camera lenses by adjustment detects bottle then.
Because when bottle does not have foreign matter in an end, light the phenomenon of delustring can occur during by two mutually perpendicular polaroids, does not have light to enter camera 2.But when having transparent foreign matter,, have different refractive indexes, cause light direction to change because the material of foreign matter is different with glass, polarization direction out of plumb then, therefore understand some light by after enter CCD camera 2, in image, form speck.
As shown in Figure 3, a bottle base map picture of exporting from camera 2 converts into digital picture to through an analog to digital converter (ADC), and CPLD (CPLD) is saved in image among a slice SRAM (static RAM).After whole sub-picture was preserved and finished, CPLD switched the bus of two SRAM (being SRAM0 and SRAM1), and originally the preservation SRAM that newly collects image is connected with DSP (digital signal processor) now, and confession DSP carries out Flame Image Process; Originally the SRAM that is connected with DSP is connected with analog to digital converter now, preserves the image that next width of cloth collects.After DSP processing image finishes, provide testing result to the empty bottle rejecting mechanism by serial ports and general input/output port.
Relate to Flame Image Process below: in order to realize the extraction of bottle detection of base map picture and information, the location in the bottle center of circle, the end vital.In order to realize the accurate location in the center of circle, Processing Algorithm has been used edge extracting, iterative approach scheduling algorithm.
(1), image pre-service
For pick-up unit, the raw image that the CCD camera obtains is because be subjected to the interference and the influence of various noise sources in the process that generates and transmit, all there is certain noise, and because bottle has slight rocking in transport process, illumination is not very even, causes all even continually varying gray scale increase suddenly originally or minimizing, forms some false object edge or profiles, cause image blurringly, bring difficulty to graphical analysis.Therefore must carry out image pre-processing methods such as noise filtering, gray correction, morphology processing, remove noise, proofread and correct uneven illumination, interested feature in the image is outstanding.We carried out pre-service to image before split image, pass through verification experimental verification: the average gray value in bottle base map inconocenter zone relatively helps subsequent treatment between being stabilized in 190 to 220, utilize the average a and the required comparatively appropriate gray shade value b (value of general b is between 190 to 220) of image processing of the raw image central area gray scale of gathering, calculate a yield value gain and an off-set value offset, gain=b/a wherein, the offset value is then floated between 20 to 30 according to the depth of bottle color.Then each the pixel value x in the pending zone is made following processing: y=x*gain+offset, wherein y is new pixel value, thereby adjusts the average gray value of whole subpicture, and the brightness stability that makes whole subpicture is among certain scope.
Utilize the average and the required optimum gradation value of Flame Image Process of gradation of image to calculate a yield value and an off-set value, be designated as parameter gain and offset, then each the pixel value x in the pending zone is made following processing: y=x*gain+offset, wherein y is new pixel value, thereby adjust the average gray of image, the brightness stability that makes whole sub-picture is among certain scope.
(2), do edge extracting
The edge extracting operator has multiple effective edge extracting operators such as Sobel operator, Prewitt operator, Laplace operator, Kirsch operator.Because the Sobel operator has difference and smooth effect concurrently and is subjected to the less advantage of disturbing effect, so adopt the Sobel operator to do edge extracting.The Sobel rim detection is a kind of nonlinear edge detection algorithm, and efficient is very high.
The basic skills of Sobel rim detection is to use two different convolution kernels on x, y direction respectively, and is as follows:
If use x, the convolution pixel value of a certain pixel that y direction convolution kernel draws is respectively Sx, Sy, and then the boundary intensity S of this pixel and direction γ can calculate with following formula:
After with the Sobel algorithm each pixel in the image being handled, the gray scale of output image is done the sectioning valve value handle.In limited time, the output pixel is put white, puts black during less than lower threshold on point image element in center is worth greater than threshold values.The image that obtains behind the edge extracting as shown in Figure 4.
Because the Sobel operator has difference and smooth effect concurrently and is subjected to the less advantage of disturbing effect, so adopt the Sobel operator to do edge extracting.The basic skills of Sobel rim detection is to use two different convolution kernels on x, y direction respectively, and is as follows:
Image is applied the Sobel operator obtain bottle base map as outline map.
(3), realize cutting apart of image
Because we have adopted many photoelectricity orientation triggering system when image acquisition, the bottle base map resembles the variation of position in our acceptable process range.We from the center of this known range to around carry out radial scan along 36 straight lines, find the gray-value variation maximum point, because before we utilized the edge at the bottom of the Sobel operator has been handled bottle outlet, so the point that our radial scan obtains is exactly a marginal point.According to the combination of certain interval, per three points are one group and determine a circle to these, utilizes following formula calculate its center of circle and radius (for example three point coordinate be (X1, Y1) (X2, Y2) (X3, Y3) its center of circle is (X0, Y0) radius is R):
X0=((Y3-Y1)*(Y2*Y2-Y1*Y1+X2*X2-X1*X1)+(Y2-Y1)*(Y1*Y1-Y3*Y3+X1*X1-X3*X3))/(2*(X2-X1)*(Y3-Y1)-2*(X3-X1)*(Y2-Y1))
Y0=((X3-X1)*(X2*X2-X1*X1+Y2*Y2-Y1*Y1)+(X2-X1)*(X1*X1-X3*X3+Y1*Y1-Y3*Y3))/(2*(Y2-Y1)*(X3-X1)-2*(Y3-Y1)*(X2-X1))
R=sqr((X1-X0)*(X1-X0)+(Y1-Y0)*(Y1-Y0))
In these points that obtain above, we utilize known radius to choose the rational marginal point and the center of circle, then the centre point selected and radius value are got average and are obtained bottle base map and resemble actual central point and radius value, thereby realized visual location.The circle that the marginal point that utilizes central point again and obtain simulates is realized cutting apart of image.
In technical scheme of the present invention, can utilize different radiuses with the bottle base map resemble be divided into three area-of-interest: a, center relatively flat portions be a border circular areas; Between b, center circle territory and the anti-skidding line, what the angle of inclination was bigger is an annular region; C, contain the annular region of anti-skidding line.We can adopt different algorithms according to different requirements at different area-of-interests, thereby reach different accuracy of detection.
(4), detect the annular domain (being the c zone) that contains anti-skidding line whether dirt is arranged
Whether utilizing the coordinate of the center of circle and anti-skidding line circle ring center radius calculation circumference each point, be kept in the array, is index then with the horizontal ordinate, have to surpass white circumference and the black circumference that limits length on decorative pattern is gone in ring in search on the circumference.If the black circumference of the length that transfinites is arranged, representing has spot on the anti-skidding line; If the white decorative pattern of the length that transfinites is arranged, represent that anti-skidding line is imperfect, damaged decorative pattern is arranged.Whether this algorithm can detect annular decorative pattern simultaneously complete, and whether dirt is arranged between decorative pattern, and whether annular decorative pattern is eccentric.
(5), detect bottle central area, the end (being a and b zone) whether dirt is arranged
The gray-scale value of background is than higher in the circle ring area between central circular zone and center circle territory and anti-skidding line, and the gray-scale value of dirt is low than background, so we choose an appropriate threshold image is carried out binary conversion treatment.We are as long as find a gray-scale value between dirt and background gray levels as threshold value exactly, and gray-scale value in the image is made as white greater than the pixel of threshold value, and gray-scale value is made as black less than the pixel of threshold value, so just dirt and background can be made a distinction.
Brightness and instability at glass bottle base map elephant, we adopt the automatic threshold that histogram analysis combines with iteration threshold to seek method in native system: determine the tonal range that image is overall and the number of gray level earlier, then with the intermediate value of this scope as initial threshold T
0, the number of gray level is made as L.Carry out iteration according to formula once then:
H wherein
kBe that gray scale is the number of the pixel of k value, iteration is performed until T
I+1=T
iFinish, get the T when finishing
iFor we carry out the threshold value that binaryzation is cut apart.
We know that the operand of process of iteration is bigger by the knowwhy of above iteration threshold method, and the present invention will apply to automatic detection production line at a high speed, it requires the time of our Flame Image Process to lack, so we at first will utilize the grey level histogram information of area-of-interest to simplify its operand in the present invention, concrete method is: (contain then comparatively concentrating in two tonal ranges of dirt) because the gray-scale value of bottle base map picture in these two zones concentrates in certain scope, we pass through histogrammic calculating, calculate the boundary value of these one or two tonal ranges, remove the gray shade scale at histogram two ends, thereby shortened the scope of gray shade scale, reduced the number of the pixel value that will calculate, shorten the processing time greatly, reached the requirement of high speed detection.
We utilize the algorithm that corrosion is earlier expanded again to remove scattered noise spot after the binaryzation, pixel to the black region of area-of-interest carries out connectivity analysis then, what we adopted is the method that pixel eight is communicated with, promptly in eight adjacent pixels of black picture element, there is one to be pixel on the spot of just thinking to be communicated with of black, just can detect the spot of different sizes and shape by the shape and the big or small parameter that are communicated with the district are set, thereby reach different accuracy of detection.
The judgement in comprehensive (4) step and (5) step provides comprehensive judged result, and whether decision needs to reject this empty bottle.
Claims (8)
1, a kind of detection method of empty bottle bottom defect is characterized in that, comprises the steps:
1), image pre-service
Adjust the average gray of image, the brightness stability that makes whole sub-picture is among certain scope;
2), do edge extracting
Image is applied the Sobel operator obtain bottle base map as outline map;
3), realize cutting apart of image
Choose the rational marginal point and the center of circle, obtain bottle base map then and resemble actual central point and radius value, thereby realized visual location, utilize central point and the circle that the marginal point that obtains simulates that image segmentation is several regions again;
4), judge in the zone that is partitioned into whether dirt is arranged;
5), determine according to judged result whether needs are rejected.
2, the detection method of a kind of empty bottle bottom defect as claimed in claim 1 is characterized in that: wherein in the step 3) bottle base map resembled be divided into three zone: a, center relatively flat portions be a border circular areas; Between b, center circle territory and the anti-skidding line, what the angle of inclination was bigger is an annular region; C, contain the annular region of anti-skidding line.
3, a kind of empty bottle bottom defect pick-up unit based on DSP, it is characterized in that: comprise to make empty bottle to be detected bottleneck and all unsettled connecting gear (3) of bottle bottom branch in surveyed area, corresponding photoelectric sensor (5) is installed in surveyed area, camera (2) is installed above the position of bottleneck in surveyed area, polarisation filter (6) is installed between this camera (2) camera lens and position of bottleneck, below the bottle position, the end in surveyed area light source (4) is installed, between this light source (4) and bottle position, the end, the Polarizer (7) that cooperates with aforementioned polarisation filter (6) is installed;
Also comprise a controller, aforementioned lights electric transducer (5) thus be electrically connected the location triggered information that transmits empty bottle with the I/O port of this controller, the I/O port of this controller respectively with camera (2) and light source (4) thus control end be electrically connected some bright light source (4) and take pictures;
Aforementioned camera (2) thus output end of image be electrically connected with the input end of an analog to digital converter and convert digital picture to, the output terminal of this analog to digital converter is electrically connected with a CPLD, thereby external two storeies of this CPLD also are electrically connected the image that will receive and are saved in behind a slice storer and it are exported to DSP and carry out defective and judge with a DSP, receive new image by another sheet storer simultaneously and treat to switch once more after DSP disposes;
The output terminal of aforementioned DSP is electrically connected with the empty bottle rejecting mechanism.
4, a kind of empty bottle bottom defect pick-up unit based on DSP as claimed in claim 3, it is characterized in that: its middle controller is PLC.
5, a kind of empty bottle bottom defect pick-up unit as claimed in claim 3 based on DSP, it is characterized in that: wherein the other corresponding photoelectric sensor (5) that is separately installed with is put in a bottleneck in surveyed area and a bottle bottom, this photoelectric sensor (5) thus all be electrically connected and transmit the bottleneck and the location triggered information at bottle end respectively with the I/O port of described controller.
6, a kind of empty bottle bottom defect pick-up unit based on DSP as claimed in claim 3, it is characterized in that: wherein connecting gear (3) is the travelling belt of clamping empty bottle to be detected both sides.
7, a kind of empty bottle bottom defect pick-up unit as claimed in claim 3 based on DSP, it is characterized in that: wherein light source (4) is the led light source that has the stroboscopic controller, this stroboscopic controller is electrically connected with the I/O port of described controller.
8, as any described a kind of empty bottle bottom defect pick-up unit in the claim 3 to 7 based on DSP; it is characterized in that: wherein Polarizer (7) is coated with waterproof sealing layer and PMMA plastics successively near a side of bottle position, the end, perhaps between Polarizer (7) and bottle position, the end cover glass (8) is installed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200710028028 CN101063662A (en) | 2007-05-15 | 2007-05-15 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200710028028 CN101063662A (en) | 2007-05-15 | 2007-05-15 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101063662A true CN101063662A (en) | 2007-10-31 |
Family
ID=38964822
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 200710028028 Pending CN101063662A (en) | 2007-05-15 | 2007-05-15 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101063662A (en) |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102213681A (en) * | 2011-04-01 | 2011-10-12 | 哈尔滨工业大学(威海) | Novel method for detecting sewage in anti-skidding region at bottom of glass bottle |
CN102274829A (en) * | 2011-04-30 | 2011-12-14 | 佛山市海天调味食品股份有限公司 | Bottle testing and rejecting apparatus |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN102341810A (en) * | 2009-01-06 | 2012-02-01 | 西门子医疗保健诊断公司 | Methods and apparatus for automated detection of the presence and types of caps on vials and containers |
CN102809569A (en) * | 2011-05-30 | 2012-12-05 | 上海福耀客车玻璃有限公司 | Automatic testing system for vehicle glass trademark in mold, and application thereof |
CN103163156A (en) * | 2013-03-21 | 2013-06-19 | 万新光学集团有限公司 | Automatic grading method of lens defects based on machine vision technology |
CN103472069A (en) * | 2012-06-07 | 2013-12-25 | 上海利控机械电子有限公司 | Foam detection machine and control method thereof |
CN103529053A (en) * | 2013-09-27 | 2014-01-22 | 清华大学 | Bottle mouth defect detection method |
CN103718026A (en) * | 2011-06-10 | 2014-04-09 | Khs有限责任公司 | Empty bottle inspection |
CN103792235A (en) * | 2014-01-10 | 2014-05-14 | 内蒙古农业大学 | Diffuse transmission spectrum and image information fusion method for detecting internal quality of honeydew melons on line and device |
CN103929585A (en) * | 2013-01-15 | 2014-07-16 | 联想(北京)有限公司 | Control method, electronic device and system for polaroid |
CN104251837A (en) * | 2014-10-17 | 2014-12-31 | 北京农业智能装备技术研究中心 | Near-infrared transmittance spectroscopy on-line detecting system and method for fruit internal quality |
CN104390914A (en) * | 2014-12-12 | 2015-03-04 | 天津普达软件技术有限公司 | Light source system for visual inspection of green vial machine |
CN104535006A (en) * | 2015-01-21 | 2015-04-22 | 杭州电子科技大学 | Bottle cap gap width estimation method by using transmission type illuminating and imaging system |
CN105046697A (en) * | 2015-07-06 | 2015-11-11 | 湖南大学 | Beer bottle opening positioning method based on multi-time random circle detection and fitting degree assessment |
CN105223209A (en) * | 2015-09-23 | 2016-01-06 | 广东暨通信息发展有限公司 | Defect detecting device at the bottom of a kind of glass bottle |
CN105699387A (en) * | 2016-03-15 | 2016-06-22 | 广州市慧眼电气产品有限公司 | Electronic product appearance defect detection system |
CN106124528A (en) * | 2016-08-31 | 2016-11-16 | 山东省药用玻璃股份有限公司 | Verifier at the bottom of vial bottleneck bottle |
CN106872480A (en) * | 2017-03-16 | 2017-06-20 | 亿信标准认证集团有限公司 | A kind of drug bottle packaging standard authentication checks platform |
CN106981060A (en) * | 2017-02-27 | 2017-07-25 | 湖南大学 | A kind of Empty Bottle Inspector bottom of bottle localization method |
CN107377398A (en) * | 2017-07-21 | 2017-11-24 | 北京巴龙机电科技有限公司 | A kind of transmission identification sorting mechanism for Bottle & Can recovery |
CN107909579A (en) * | 2017-10-31 | 2018-04-13 | 征图新视(江苏)科技有限公司 | Product profile extraction method in vision-based detection |
CN108387590A (en) * | 2018-03-15 | 2018-08-10 | 福州大学 | A kind of low module stem gear appearance defect detection device |
CN108787489A (en) * | 2018-07-06 | 2018-11-13 | 东阿阿胶股份有限公司 | A kind of recognition detection system of full automatic lamp detecting machine |
CN109115803A (en) * | 2017-06-22 | 2019-01-01 | 山东明佳科技有限公司 | A kind of mold number coding is in ray imaging device, system and detection method |
CN109118476A (en) * | 2018-07-11 | 2019-01-01 | 华南理工大学广州学院 | A kind of components edge contour integrality detection method and device |
CN109191439A (en) * | 2018-08-20 | 2019-01-11 | 宁波市智能制造产业研究院 | A kind of target workpiece surface knife mark defect inspection method |
CN109406534A (en) * | 2018-11-28 | 2019-03-01 | 广州番禺职业技术学院 | A kind of medicine bottle bottom pull ring defect detecting device and method |
CN109444157A (en) * | 2018-12-25 | 2019-03-08 | 苏州凡目视觉科技有限公司 | A kind of scratch detection apparatus and method |
CN109967379A (en) * | 2019-03-06 | 2019-07-05 | 东莞中科蓝海智能视觉科技有限公司 | A kind of detection device detecting column surface blemish |
CN110070523A (en) * | 2019-04-02 | 2019-07-30 | 广州大学 | A kind of foreign matter detecting method for bottom of bottle |
CN110440853A (en) * | 2019-07-24 | 2019-11-12 | 沈阳工程学院 | A kind of monitoring dust pelletizing system |
CN110458223A (en) * | 2019-08-06 | 2019-11-15 | 湖南省华芯医疗器械有限公司 | Tumor of bronchus automatic testing method and detection system under a kind of scope |
CN111330874A (en) * | 2020-04-17 | 2020-06-26 | 广州番禺职业技术学院 | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle |
CN112129783A (en) * | 2020-09-22 | 2020-12-25 | 广州番禺职业技术学院 | Transparent medicine bottle bottom defect detection device and detection method based on deep learning |
CN112203779A (en) * | 2018-06-07 | 2021-01-08 | 威尔科股份公司 | Inspection process |
CN113748328A (en) * | 2019-03-05 | 2021-12-03 | 伊莫拉Sacmi机械合作公司 | Apparatus and method for inspecting an object |
CN116152248A (en) * | 2023-04-20 | 2023-05-23 | 中科慧远视觉技术(北京)有限公司 | Appearance defect detection method and device, storage medium and computer equipment |
-
2007
- 2007-05-15 CN CN 200710028028 patent/CN101063662A/en active Pending
Cited By (53)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9092650B2 (en) | 2009-01-06 | 2015-07-28 | Siemens Healthcare Diagnostics Inc. | Methods and apparatus for automated detection of the presence and type of caps on vials and containers |
CN102341810A (en) * | 2009-01-06 | 2012-02-01 | 西门子医疗保健诊断公司 | Methods and apparatus for automated detection of the presence and types of caps on vials and containers |
CN102213681A (en) * | 2011-04-01 | 2011-10-12 | 哈尔滨工业大学(威海) | Novel method for detecting sewage in anti-skidding region at bottom of glass bottle |
CN102213681B (en) * | 2011-04-01 | 2013-01-02 | 哈尔滨工业大学(威海) | Novel method for detecting sewage in anti-skidding region at bottom of glass bottle |
CN102274829A (en) * | 2011-04-30 | 2011-12-14 | 佛山市海天调味食品股份有限公司 | Bottle testing and rejecting apparatus |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN102809569A (en) * | 2011-05-30 | 2012-12-05 | 上海福耀客车玻璃有限公司 | Automatic testing system for vehicle glass trademark in mold, and application thereof |
CN103718026A (en) * | 2011-06-10 | 2014-04-09 | Khs有限责任公司 | Empty bottle inspection |
CN103718026B (en) * | 2011-06-10 | 2017-10-10 | Khs有限责任公司 | Empty bottle is checked |
CN103472069A (en) * | 2012-06-07 | 2013-12-25 | 上海利控机械电子有限公司 | Foam detection machine and control method thereof |
CN103929585A (en) * | 2013-01-15 | 2014-07-16 | 联想(北京)有限公司 | Control method, electronic device and system for polaroid |
CN103929585B (en) * | 2013-01-15 | 2018-02-27 | 联想(北京)有限公司 | A kind of control method of polaroid, electronic equipment and system |
CN103163156A (en) * | 2013-03-21 | 2013-06-19 | 万新光学集团有限公司 | Automatic grading method of lens defects based on machine vision technology |
CN103529053A (en) * | 2013-09-27 | 2014-01-22 | 清华大学 | Bottle mouth defect detection method |
CN103529053B (en) * | 2013-09-27 | 2015-12-02 | 清华大学 | Bottle mouth defect detection method |
CN103792235A (en) * | 2014-01-10 | 2014-05-14 | 内蒙古农业大学 | Diffuse transmission spectrum and image information fusion method for detecting internal quality of honeydew melons on line and device |
CN104251837A (en) * | 2014-10-17 | 2014-12-31 | 北京农业智能装备技术研究中心 | Near-infrared transmittance spectroscopy on-line detecting system and method for fruit internal quality |
CN104251837B (en) * | 2014-10-17 | 2016-08-31 | 北京农业智能装备技术研究中心 | Fruit internal quality NIR transmittance spectroscopy on-line detecting system and method |
CN104390914A (en) * | 2014-12-12 | 2015-03-04 | 天津普达软件技术有限公司 | Light source system for visual inspection of green vial machine |
CN104535006B (en) * | 2015-01-21 | 2017-10-27 | 杭州电子科技大学 | A kind of bottle cap gap width evaluation method of utilization transmission-type illumination imaging systems |
CN104535006A (en) * | 2015-01-21 | 2015-04-22 | 杭州电子科技大学 | Bottle cap gap width estimation method by using transmission type illuminating and imaging system |
CN105046697B (en) * | 2015-07-06 | 2017-07-28 | 湖南大学 | A kind of beer bottleneck localization method assessed based on multiple random loop truss and degree of fitting |
CN105046697A (en) * | 2015-07-06 | 2015-11-11 | 湖南大学 | Beer bottle opening positioning method based on multi-time random circle detection and fitting degree assessment |
CN105223209A (en) * | 2015-09-23 | 2016-01-06 | 广东暨通信息发展有限公司 | Defect detecting device at the bottom of a kind of glass bottle |
CN105699387A (en) * | 2016-03-15 | 2016-06-22 | 广州市慧眼电气产品有限公司 | Electronic product appearance defect detection system |
CN106124528A (en) * | 2016-08-31 | 2016-11-16 | 山东省药用玻璃股份有限公司 | Verifier at the bottom of vial bottleneck bottle |
CN106981060A (en) * | 2017-02-27 | 2017-07-25 | 湖南大学 | A kind of Empty Bottle Inspector bottom of bottle localization method |
CN106872480A (en) * | 2017-03-16 | 2017-06-20 | 亿信标准认证集团有限公司 | A kind of drug bottle packaging standard authentication checks platform |
CN109115803A (en) * | 2017-06-22 | 2019-01-01 | 山东明佳科技有限公司 | A kind of mold number coding is in ray imaging device, system and detection method |
CN107377398A (en) * | 2017-07-21 | 2017-11-24 | 北京巴龙机电科技有限公司 | A kind of transmission identification sorting mechanism for Bottle & Can recovery |
CN107909579A (en) * | 2017-10-31 | 2018-04-13 | 征图新视(江苏)科技有限公司 | Product profile extraction method in vision-based detection |
CN107909579B (en) * | 2017-10-31 | 2019-12-03 | 征图新视(江苏)科技股份有限公司 | Product profile extraction method in vision-based detection |
CN108387590A (en) * | 2018-03-15 | 2018-08-10 | 福州大学 | A kind of low module stem gear appearance defect detection device |
CN112203779B (en) * | 2018-06-07 | 2023-08-18 | 威尔科股份公司 | Inspection process |
CN112203779A (en) * | 2018-06-07 | 2021-01-08 | 威尔科股份公司 | Inspection process |
CN108787489A (en) * | 2018-07-06 | 2018-11-13 | 东阿阿胶股份有限公司 | A kind of recognition detection system of full automatic lamp detecting machine |
CN109118476A (en) * | 2018-07-11 | 2019-01-01 | 华南理工大学广州学院 | A kind of components edge contour integrality detection method and device |
CN109118476B (en) * | 2018-07-11 | 2020-11-24 | 华南理工大学广州学院 | Method and device for detecting integrity of edge profile of part |
CN109191439A (en) * | 2018-08-20 | 2019-01-11 | 宁波市智能制造产业研究院 | A kind of target workpiece surface knife mark defect inspection method |
CN109406534A (en) * | 2018-11-28 | 2019-03-01 | 广州番禺职业技术学院 | A kind of medicine bottle bottom pull ring defect detecting device and method |
CN109444157A (en) * | 2018-12-25 | 2019-03-08 | 苏州凡目视觉科技有限公司 | A kind of scratch detection apparatus and method |
CN113748328A (en) * | 2019-03-05 | 2021-12-03 | 伊莫拉Sacmi机械合作公司 | Apparatus and method for inspecting an object |
CN109967379A (en) * | 2019-03-06 | 2019-07-05 | 东莞中科蓝海智能视觉科技有限公司 | A kind of detection device detecting column surface blemish |
CN110070523A (en) * | 2019-04-02 | 2019-07-30 | 广州大学 | A kind of foreign matter detecting method for bottom of bottle |
CN110070523B (en) * | 2019-04-02 | 2021-06-22 | 广州大学 | Foreign matter detection method for bottle bottom |
CN110440853A (en) * | 2019-07-24 | 2019-11-12 | 沈阳工程学院 | A kind of monitoring dust pelletizing system |
CN110440853B (en) * | 2019-07-24 | 2024-05-17 | 沈阳工程学院 | Monitoring dust removing system |
CN110458223A (en) * | 2019-08-06 | 2019-11-15 | 湖南省华芯医疗器械有限公司 | Tumor of bronchus automatic testing method and detection system under a kind of scope |
CN110458223B (en) * | 2019-08-06 | 2023-03-17 | 湖南省华芯医疗器械有限公司 | Automatic detection method and detection system for bronchial tumor under endoscope |
CN111330874A (en) * | 2020-04-17 | 2020-06-26 | 广州番禺职业技术学院 | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle |
CN112129783A (en) * | 2020-09-22 | 2020-12-25 | 广州番禺职业技术学院 | Transparent medicine bottle bottom defect detection device and detection method based on deep learning |
CN112129783B (en) * | 2020-09-22 | 2024-03-29 | 广州番禺职业技术学院 | Transparent medicine bottle bottom defect detection method based on deep learning |
CN116152248A (en) * | 2023-04-20 | 2023-05-23 | 中科慧远视觉技术(北京)有限公司 | Appearance defect detection method and device, storage medium and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101063662A (en) | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP | |
CN111006608B (en) | Transparent plate through hole visual detection system and method | |
CN102495069B (en) | Method for detecting defects of chain belts of zipper on basis of digital image processing | |
CN1237327C (en) | System and method for discriminating road gap | |
US7414716B2 (en) | Machine for inspecting glass containers | |
US7626158B2 (en) | Machine for inspecting glass containers | |
CN101819162A (en) | Empty bottle wall defect detection method and device | |
CN101556208B (en) | Intelligent lighting automatic detection and analysis system and detection method thereof | |
CN205538740U (en) | Intelligence timber surface defect detection system | |
CN100547394C (en) | Fruit quality detection system based on image information fusion technology | |
CN201689063U (en) | Empty bottle wall defect inspection device | |
CN101315338A (en) | Defect detecting system and method for glass product | |
CN104634791A (en) | Omnidirectional and visual on-line detection system of surface defects of strip-shaped workpiece | |
CN101825582A (en) | Method and device for detecting wall of cylindrical transparent bottle | |
CN103480586A (en) | Dual infrared online plastic material sorting device | |
CN113000413B (en) | System, method and terminal for detecting surface defects of synchronizer gear sleeve based on machine vision | |
CN105954301A (en) | Bottleneck quality detection method based on machine vision | |
CN103698337A (en) | Method for automatically detecting adhesion defect of label of flat wine bottle | |
CN101937505B (en) | Target detection method and equipment and used image acquisition device thereof | |
CN110567968A (en) | part defect detection method and device | |
CN111474179A (en) | Lens surface cleanliness detection device and method | |
CN109827974B (en) | Resin optical filter film crack detection device and detection method | |
EP1558919B1 (en) | Method and device for the detection of surface defects on the finish of a transparent or translucent rotating container | |
US7541572B2 (en) | Machine for inspecting rotating glass containers with light source triggered multiple times during camera exposure time | |
CN108229447B (en) | High beam light detection method based on video stream |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20071031 |