CN111080638A - System and method for detecting dirt at bottom of molded bottle - Google Patents
System and method for detecting dirt at bottom of molded bottle Download PDFInfo
- Publication number
- CN111080638A CN111080638A CN201911377562.7A CN201911377562A CN111080638A CN 111080638 A CN111080638 A CN 111080638A CN 201911377562 A CN201911377562 A CN 201911377562A CN 111080638 A CN111080638 A CN 111080638A
- Authority
- CN
- China
- Prior art keywords
- camera
- bottle
- image
- bottle bottom
- light source
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the field of glass bottle appearance defect detection, and discloses a system and a method for detecting molded bottle bottom dirt, which solve the problem that in the traditional technology, when the molded bottle bottom dirt is detected, a mold mark is easily judged to be dirty by mistake, so that the detection accuracy is low. According to the invention, the binocular camera is adopted to shoot the bottle bottom from two different visual angles, the positions of the shadows of the die marks are different under different observation angles, and the position of the stains on the surface of the bottle bottom is not changed, so that the interference and the stains of the die marks are distinguished by processing the images collected at the two observation angles, and the detection accuracy of the stains on the bottom of the molded bottle is improved.
Description
Technical Field
The invention relates to the field of glass bottle appearance defect detection, in particular to a system and a method for detecting molded bottle bottom dirt.
Background
The glass bottle is widely used for packaging food and medicines, and particularly in the pharmaceutical industry, the glass bottle has good sealing property, stability and compatibility, so that the glass bottle becomes almost the only packaging material for precious medicines (liquid medicines), such as various types of vaccines, tumor therapeutic medicines and the like, and is packaged by adopting the glass bottle.
Because the safety demand of liquid medicine self and its value are high, to avoid the liquid medicine pollution to appear the incident and lead to the liquid medicine extravagant because body appearance defect, the pharmaceutical factory all will detect the quality of glass bottle itself before carrying out the filling, the defect kind that detects roughly divide into: stones, bubbles, cracks, dirt, breakage, bruising, etc., which may be distributed at various locations of the glass bottle, such as the mouth, neck, shoulder, body, bottom.
The detection means adopted for the detection of different distribution positions and different defect types are different. At present, the bottle is clamped and suspended by a holding clamp in the air in the aspect of detecting the dirt at the bottom of the bottle, backlight is irradiated downwards from the direction of a bottle opening, and an image of the bottom of the bottle is shot from one side of the bottom of the bottle by adopting an industrial camera, as shown in figure 1. After the image is acquired, the presence or absence of the stain is identified by detecting an area in the image having a lower grayscale than the background.
However, in general, molded bottles (bottles manufactured by injecting molten glass into a molding mold) have raised mold marks at the bottom, and when a clamp clamps a bottle body, a part of light irradiated from above is shielded, so that a directional black shadow appears at the edge of the mold mark at the bottom of the bottle, and when dirt is recognized, the dirt is easily misjudged, as shown in fig. 2; at present, a good solution is not provided for distinguishing the die mark from the bottle bottom dirt, so that the detection accuracy is low.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the system and the method for detecting the dirt at the bottom of the molded bottle are provided, and the problem that the detection accuracy is low due to the fact that the mold mark is easily judged to be dirty when the dirt at the bottom of the molded bottle is detected in the traditional technology is solved.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a system for detecting molded bottle bottom dirt comprises a light source, a clamp, a first camera bracket, a first camera, a second camera bracket and a second camera; the light source is positioned above the holding clamp; the first camera support and the second camera support are arranged on the detection platform below the holding clamp, and the first camera and the second camera are respectively arranged on the first camera support and the second camera support.
As further optimization, the first camera and the second camera are symmetrically distributed along the rotation central axis of the bottle to be detected, and the angle is adjustable. The two cameras are symmetrically distributed so that the shot photos are symmetrical, and therefore matching is performed quickly; the camera angle is adjustable, so that the shooting angle of the camera can be adjusted conveniently according to the actual bottle bottom size, a shot picture at the most appropriate angle can be obtained, and a foundation is provided for accurate detection.
And as further optimization, the light source adopts a white uniform LED circular surface light source, the light source is horizontally placed, the distance from the bottle mouth of the bottle to be detected clamped by the clamping clamp is within 20mm, and the diameter of the light source is at least 3-4 times of the diameter of the bottle bottom. The uniformity of light irradiating to the bottom of the bottle can be ensured through the arrangement, so that a high-quality shot picture is obtained, and a basis is provided for accurate detection.
As further optimization, the holding clamp adopts a double-finger holding clamp with a hollow middle part. Through the arrangement, more surface light on the bottle can be ensured to be emitted to the bottom of the bottle, and a more uniform bright background is formed.
In addition, based on the detection system, the invention also provides a method for detecting the molded bottle bottom smudginess, which comprises the following steps:
a. calibrating camera parameters and attitude parameters of a first camera and a second camera respectively, and correspondingly obtaining an internal parameter matrix and attitude parameters of the first camera and an internal parameter matrix and attitude parameters of the second camera;
b. during detection, the first camera and the second camera simultaneously acquire images of the bottle bottom to respectively obtain an image 1 and an image 2,
c. extracting black areas Br1 and Br2 possibly existing at the bottle bottoms in the image 1 and the image 2 respectively by a threshold method;
d. projecting a black area Br1 extracted from the image 1 to a world coordinate system through an internal reference matrix and attitude parameters of a first camera to obtain an area Br1 w;
e. projecting the region Br1w under the world coordinate system into an image coordinate system of the second camera through the internal reference matrix of the second camera and the inverse matrix of the attitude parameters to obtain a region Br1w 2;
f. and calculating the overlapping rate Fp and the area similarity ratio Ap of the region Br1w2 and the black region Br2 in the image 2, if Fp is less than the Fp threshold value and Ap is less than the Ap threshold value, judging that the black region is dirty, otherwise, judging that the black region is stamp-disturbed.
The invention has the beneficial effects that:
adopt two mesh cameras to shoot at the bottom of the bottle from two different visual angles, under the observation angle of difference, the position that the shadow of stamp appears will be different, and the dirty position that then can not change of bottle bottom surface to distinguish stamp interference and dirty through the processing to two observation angle collection images, improve the dirty detection accuracy in mould bottle bottom from this.
Drawings
FIG. 1 is a diagram illustrating a system for detecting contamination on a bottle bottom using a single camera according to a conventional technique;
FIG. 2 is a schematic diagram of a single camera detecting the presence of die-mark interference at the bottom of a bottle;
FIG. 3 is a block diagram of a system for detecting mold bottle bottom smudging in accordance with the present invention;
FIGS. 4(a) and 4(b) are schematic diagrams illustrating the change of the interference position under different viewing angles of the dual cameras according to the present invention;
FIG. 5 is a flow chart of an algorithm for detecting soil on the bottom of a bottle using a dual phase machine according to the present invention.
Detailed Description
The invention aims to provide a system and a method for detecting molded bottle bottom dirt, and solves the problem that in the prior art, when the molded bottle bottom dirt is detected, a stamping mark is easily mistakenly judged as dirt, so that the detection accuracy is low. The core idea is as follows: the binocular camera is adopted to shoot the bottle bottom from two different visual angles, the positions of the shadows of the die print will be different under different observation angles, and the position of the stains on the surface of the bottle bottom will not be changed, so that the interference and the stains of the die print can be distinguished by processing the collected images at the two observation angles; specifically, if a black area is detected in the image 1 captured by the camera 1 and the pixel coordinates are (u1, v1), the coordinates of the black area in the real world coordinate system are (x, y) according to the transformation relationship between the camera 1 coordinate system and the world coordinate system, and then the theoretical pixel coordinates (u2, v2) of the real target point in the image 2 captured by the camera 2 can be calculated through the transformation relationship between the world coordinate system and the camera 2 coordinate system; therefore, it is only necessary to determine the degree of overlapping and area similarity between the theoretical pixel coordinates (u2, v2) and the black regions (u2 ', v 2') in the image 2 actually captured by the camera 2 to determine whether the detection target is shifted in different viewing angles, and if the shift occurs, it is determined as the impression interference, as shown in fig. 4(a) and (b), and if the shift does not occur, it is determined as the smudging.
As shown in fig. 3, the system for detecting mold-based bottle bottom smudginess in the present invention comprises a light source, a clamp, a first camera bracket, a first camera, a second camera bracket and a second camera; the light source is positioned above the holding clamp; the first camera support and the second camera support are arranged on the detection platform below the holding clamp, and the first camera and the second camera are respectively arranged on the first camera support and the second camera support.
When the system is arranged, the quality of the shot image can be improved by the following means:
the position and the angle of the camera are adjusted, the camera is symmetrically distributed along the bottle rotation central axis, the included angle between the camera and the vertical line is within the range of 5-20 degrees, and the camera is determined according to the size of the bottle bottom. The inclination angle is preferably 10 degrees for a 50ml glass bottle having a bottom diameter of about 40 mm.
The light source above the bottle mouth is preferably a white uniform LED circular surface light source and is horizontally placed within 20mm of the bottle mouth, and the diameter of the light source is at least 3-4 times of the diameter of the bottle bottom.
The holding clamp of the bottle body is preferably a double-finger holding clamp with a hollow middle part, so that more surface light can be emitted to the bottom of the bottle to form a more uniform bright background.
After the camera position and the lens aperture and the focal circle are adjusted and fixed, in order to establish the correspondence and the conversion relation of each pixel point in the images collected by the two cameras so as to realize the detection of the target point, a calibration plate is needed to calibrate the relative spatial postures and some optical parameters of the two cameras, and the method is divided into two steps:
(1) calibrating camera lens intrinsic parameters: the calibration method adopts a Zhang calibration method which is an industry practice, and the specific process is not described herein again. And obtaining internal reference matrixes CamH1 and CamH2 of the two cameras through calibration.
(2) Calibrating the relative poses of the two cameras: firstly, clamping any glass bottle to be detected on a holding clamp according to the correct height, then fixing a calibration plate at the bottom of the bottle, and respectively collecting an image of the calibration plate by two cameras. The pose Pos1 of the camera 1 optical coordinate system relative to the physical world coordinate system of the calibration plate is calculated, and similarly another camera Pos2 is calculated.
After obtaining four parameters, CamH1, CamH2, Pos1, and Pos2, storing the parameters in a configuration file, reading the whole four parameters at the beginning of each detection, and performing detection calculation, wherein the process is shown in fig. 5 and includes the following steps:
(1) the first camera and the second camera simultaneously acquire images of the bottom of the bottle to respectively acquire an image 1 and an image 2,
(2) extracting black areas Br1 and Br2 possibly existing at the bottle bottoms in the image 1 and the image 2 respectively by a threshold method;
(3) projecting a black area Br1 extracted from the image 1 to a world coordinate system through an internal reference matrix CamH1 and attitude parameters Pos1 of the first camera to obtain an area Br1 w;
(4) projecting the region Br1w under the world coordinate system into an image coordinate system of the second camera through an internal reference matrix CamH2 of the second camera and an inverse matrix of the attitude parameter Pos2 to obtain a region Br1w 2;
(5) and calculating the overlapping rate Fp and the area similarity ratio Ap of the region Br1w2 and the black region Br2 in the image 2, if Fp is less than the Fp threshold value and Ap is less than the Ap threshold value, judging that the black region is dirty, otherwise, judging that the black region is stamp-disturbed.
Through the means, the method can distinguish the die mark interference and the dirt, so that the detection accuracy of the dirt on the bottom of the molded bottle is improved.
Claims (5)
1. A system for detecting the bottom dirt of a molded bottle is characterized in that,
the device comprises a light source, a holding clamp, a first camera bracket, a first camera, a second camera bracket and a second camera; the light source is positioned above the holding clamp; the first camera support and the second camera support are arranged on the detection platform below the holding clamp, and the first camera and the second camera are respectively arranged on the first camera support and the second camera support.
2. A system for detecting mold-based bottle bottom smudging according to claim 1,
the first camera and the second camera are symmetrically distributed along the rotation central axis of the bottle to be detected, and the angle is adjustable.
3. A system for detecting mold-based bottle bottom smudging according to claim 1,
the light source adopts white uniform LED circular surface light source, and the level is placed, and the distance from the bottleneck of the to-be-detected bottle clamped by the clamp is within 20mm, and the diameter of the light source is at least 3-4 times of the diameter of the bottle bottom.
4. A system for detecting mold-based bottle bottom smudging according to claim 1,
the holding clamp adopts a double-finger holding clamp with a hollow middle part.
5. A method of detecting mold bottle bottom smudging for use in a system according to any one of claims 1-4, the method comprising the steps of:
a. calibrating camera parameters and attitude parameters of a first camera and a second camera respectively, and correspondingly obtaining an internal parameter matrix and attitude parameters of the first camera and an internal parameter matrix and attitude parameters of the second camera;
b. during detection, the first camera and the second camera simultaneously acquire images of the bottle bottom to respectively obtain an image 1 and an image 2,
c. extracting black areas Br1 and Br2 possibly existing at the bottle bottoms in the image 1 and the image 2 respectively by a threshold method;
d. projecting a black area Br1 extracted from the image 1 to a world coordinate system through an internal reference matrix and attitude parameters of a first camera to obtain an area Br1 w;
e. projecting the region Br1w under the world coordinate system into an image coordinate system of the second camera through the internal reference matrix of the second camera and the inverse matrix of the attitude parameters to obtain a region Br1w 2;
f. and calculating the overlapping rate Fp and the area similarity ratio Ap of the region Br1w2 and the black region Br2 in the image 2, if Fp is less than the Fp threshold value and Ap is less than the Ap threshold value, judging that the black region is dirty, otherwise, judging that the black region is stamp-disturbed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911377562.7A CN111080638B (en) | 2019-12-27 | 2019-12-27 | Method for detecting dirt at bottom of molded bottle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911377562.7A CN111080638B (en) | 2019-12-27 | 2019-12-27 | Method for detecting dirt at bottom of molded bottle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111080638A true CN111080638A (en) | 2020-04-28 |
CN111080638B CN111080638B (en) | 2023-04-07 |
Family
ID=70318602
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911377562.7A Active CN111080638B (en) | 2019-12-27 | 2019-12-27 | Method for detecting dirt at bottom of molded bottle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111080638B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111948214A (en) * | 2020-07-17 | 2020-11-17 | 同济大学 | Device and method for classifying image pollution levels |
CN112750113A (en) * | 2021-01-14 | 2021-05-04 | 深圳信息职业技术学院 | Glass bottle defect detection method and device based on deep learning and linear detection |
CN112881432A (en) * | 2021-01-12 | 2021-06-01 | 成都泓睿科技有限责任公司 | Method for detecting bottle mouth cracks of liquid glass bottle |
CN113538427A (en) * | 2021-09-16 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Product defect identification method, device, equipment and readable storage medium |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05113411A (en) * | 1991-10-21 | 1993-05-07 | Asahi Chem Ind Co Ltd | Bottle inspecting apparatus |
JPH0634575A (en) * | 1992-07-21 | 1994-02-08 | Asahi Chem Ind Co Ltd | Bottle inspection method |
JPH09318338A (en) * | 1996-05-31 | 1997-12-12 | Nissan Motor Co Ltd | Surface defect inspection device |
CN1324277A (en) * | 1998-08-26 | 2001-11-28 | 光谱科学公司 | Methods and apparatus employing multi-spectral imaging for the remote identification and sorting of objects |
JP2005091243A (en) * | 2003-09-19 | 2005-04-07 | Sukiyan Technol:Kk | Empty bottle inspection system |
WO2011117539A1 (en) * | 2010-03-23 | 2011-09-29 | Msc & Sgcc | Method and equipment for detecting the presence and extent of defects in an optical component |
JP2012242148A (en) * | 2011-05-17 | 2012-12-10 | Kurabo Ind Ltd | Appearance inspection apparatus and appearance inspection method of transparent bottle |
US20130044209A1 (en) * | 2011-08-18 | 2013-02-21 | Samsung Corning Precision Materials Co., Ltd. | Apparatus and method for detecting the surface defect of the glass substrate |
JP2013088342A (en) * | 2011-10-20 | 2013-05-13 | Toppan Printing Co Ltd | Defect inspection method for color filter substrate |
JP2013092430A (en) * | 2011-10-25 | 2013-05-16 | Kojima Press Industry Co Ltd | Surface inspection method |
JP2014157121A (en) * | 2013-02-18 | 2014-08-28 | N Tech:Kk | Container inspection apparatus |
CN104990512A (en) * | 2015-07-20 | 2015-10-21 | 清华大学 | Transparent container bottle opening thread defect detection system and method |
JP2016005263A (en) * | 2014-06-19 | 2016-01-12 | Kddi株式会社 | Image generation system, terminal, program, and method that generate panoramic image from plurality of photographed images |
CN105675619A (en) * | 2016-01-15 | 2016-06-15 | 佛山市晶华检测设备有限公司 | Rotary type bottle body photographing and detecting method as well as apparatus for realizing method |
CN105699395A (en) * | 2016-02-04 | 2016-06-22 | 成都泓睿科技有限责任公司 | Method for detecting liquid surface foreign matter of transparent glass bottles |
CN205538732U (en) * | 2016-02-04 | 2016-08-31 | 成都泓睿科技有限责任公司 | Detection apparatus for foreign matter among transparent glass bottle |
JP2016194847A (en) * | 2015-04-01 | 2016-11-17 | キヤノン株式会社 | Image detection device, image detection method, and program |
JP2017156343A (en) * | 2016-02-26 | 2017-09-07 | 東レ株式会社 | Defect inspection device |
WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
CN107768269A (en) * | 2017-10-30 | 2018-03-06 | 河北工业大学 | A kind of method of the dirty defects detection of polysilicon solar battery slice outward appearance |
CN108181319A (en) * | 2017-12-12 | 2018-06-19 | 陕西三星洁净工程有限公司 | A kind of laying dust detecting device and method based on stereoscopic vision |
CN108288264A (en) * | 2017-12-26 | 2018-07-17 | 横店集团东磁有限公司 | A kind of dirty test method of wide-angle camera module |
US20180211373A1 (en) * | 2017-01-20 | 2018-07-26 | Aquifi, Inc. | Systems and methods for defect detection |
CN110095478A (en) * | 2019-05-22 | 2019-08-06 | 山东鲁玻包装有限公司 | A kind of tubetype glass bottle detecting and controlling system |
-
2019
- 2019-12-27 CN CN201911377562.7A patent/CN111080638B/en active Active
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05113411A (en) * | 1991-10-21 | 1993-05-07 | Asahi Chem Ind Co Ltd | Bottle inspecting apparatus |
JPH0634575A (en) * | 1992-07-21 | 1994-02-08 | Asahi Chem Ind Co Ltd | Bottle inspection method |
JPH09318338A (en) * | 1996-05-31 | 1997-12-12 | Nissan Motor Co Ltd | Surface defect inspection device |
CN1324277A (en) * | 1998-08-26 | 2001-11-28 | 光谱科学公司 | Methods and apparatus employing multi-spectral imaging for the remote identification and sorting of objects |
JP2005091243A (en) * | 2003-09-19 | 2005-04-07 | Sukiyan Technol:Kk | Empty bottle inspection system |
WO2011117539A1 (en) * | 2010-03-23 | 2011-09-29 | Msc & Sgcc | Method and equipment for detecting the presence and extent of defects in an optical component |
JP2012242148A (en) * | 2011-05-17 | 2012-12-10 | Kurabo Ind Ltd | Appearance inspection apparatus and appearance inspection method of transparent bottle |
US20130044209A1 (en) * | 2011-08-18 | 2013-02-21 | Samsung Corning Precision Materials Co., Ltd. | Apparatus and method for detecting the surface defect of the glass substrate |
JP2013088342A (en) * | 2011-10-20 | 2013-05-13 | Toppan Printing Co Ltd | Defect inspection method for color filter substrate |
JP2013092430A (en) * | 2011-10-25 | 2013-05-16 | Kojima Press Industry Co Ltd | Surface inspection method |
JP2014157121A (en) * | 2013-02-18 | 2014-08-28 | N Tech:Kk | Container inspection apparatus |
JP2016005263A (en) * | 2014-06-19 | 2016-01-12 | Kddi株式会社 | Image generation system, terminal, program, and method that generate panoramic image from plurality of photographed images |
JP2016194847A (en) * | 2015-04-01 | 2016-11-17 | キヤノン株式会社 | Image detection device, image detection method, and program |
CN104990512A (en) * | 2015-07-20 | 2015-10-21 | 清华大学 | Transparent container bottle opening thread defect detection system and method |
CN105675619A (en) * | 2016-01-15 | 2016-06-15 | 佛山市晶华检测设备有限公司 | Rotary type bottle body photographing and detecting method as well as apparatus for realizing method |
CN105699395A (en) * | 2016-02-04 | 2016-06-22 | 成都泓睿科技有限责任公司 | Method for detecting liquid surface foreign matter of transparent glass bottles |
CN205538732U (en) * | 2016-02-04 | 2016-08-31 | 成都泓睿科技有限责任公司 | Detection apparatus for foreign matter among transparent glass bottle |
JP2017156343A (en) * | 2016-02-26 | 2017-09-07 | 東レ株式会社 | Defect inspection device |
WO2018000731A1 (en) * | 2016-06-28 | 2018-01-04 | 华南理工大学 | Method for automatically detecting curved surface defect and device thereof |
US20180211373A1 (en) * | 2017-01-20 | 2018-07-26 | Aquifi, Inc. | Systems and methods for defect detection |
CN107768269A (en) * | 2017-10-30 | 2018-03-06 | 河北工业大学 | A kind of method of the dirty defects detection of polysilicon solar battery slice outward appearance |
CN108181319A (en) * | 2017-12-12 | 2018-06-19 | 陕西三星洁净工程有限公司 | A kind of laying dust detecting device and method based on stereoscopic vision |
CN108288264A (en) * | 2017-12-26 | 2018-07-17 | 横店集团东磁有限公司 | A kind of dirty test method of wide-angle camera module |
CN110095478A (en) * | 2019-05-22 | 2019-08-06 | 山东鲁玻包装有限公司 | A kind of tubetype glass bottle detecting and controlling system |
Non-Patent Citations (3)
Title |
---|
柴曼等: "计算机视觉测量中相机标定方法的应用研究", 《内江科技》 * |
赵阳等: "平行照明多目视觉检测技术", 《红外与激光工程》 * |
高绍嵩等: "基于机器视觉的玻璃瓶检测系统", 《海军航空工程学院学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111948214A (en) * | 2020-07-17 | 2020-11-17 | 同济大学 | Device and method for classifying image pollution levels |
CN112881432A (en) * | 2021-01-12 | 2021-06-01 | 成都泓睿科技有限责任公司 | Method for detecting bottle mouth cracks of liquid glass bottle |
CN112881432B (en) * | 2021-01-12 | 2022-11-29 | 成都泓睿科技有限责任公司 | Method for detecting bottle mouth cracks of liquid glass bottle |
CN112750113A (en) * | 2021-01-14 | 2021-05-04 | 深圳信息职业技术学院 | Glass bottle defect detection method and device based on deep learning and linear detection |
CN113538427A (en) * | 2021-09-16 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Product defect identification method, device, equipment and readable storage medium |
CN113538427B (en) * | 2021-09-16 | 2022-01-07 | 深圳市信润富联数字科技有限公司 | Product defect identification method, device, equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111080638B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111080638B (en) | Method for detecting dirt at bottom of molded bottle | |
CN103063137B (en) | A kind of medicine bottle measuring system based on machine vision and measuring method thereof | |
CN104217441B (en) | Mechanical arm positioning fetching method based on machine vision | |
CN101566582B (en) | Medicine bottle label information online detection system in powder injection production based on mechanical vision | |
CN103743761B (en) | A kind of eyeglass watermark defect image detection device | |
CN110261410A (en) | A kind of detection device and method of glass lens defect | |
CN110108711A (en) | The vision detection system of annulus side wall defect | |
CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
CN110766748B (en) | Non-contact whole vehicle attitude measurement method | |
CN102539443A (en) | Bottle body defect automatic detection device based on machine vision and method thereof | |
CN103954458B (en) | Non-contacting type four-wheel aligner and detecting method thereof | |
CN106052793A (en) | Machine vision based liquid level sub-quality product marking method | |
JP6134383B2 (en) | Optical method for inspecting transparent or translucent containers with visible patterns | |
CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
CN104535006B (en) | A kind of bottle cap gap width evaluation method of utilization transmission-type illumination imaging systems | |
CN107202555A (en) | A kind of Machining of Connecting Rod rotating disc fixture vision inspection apparatus and detection method | |
CN115760782B (en) | Machine vision-based in-mold labeling offset defect identification method | |
CN114565848B (en) | Liquid medicine level detection method and system in complex scene | |
CN108520260A (en) | The recognition methods of visible foreign matters in bottled oral solution | |
CN109540084B (en) | Method and device for measuring three-dimensional attitude of part in floating liquid | |
CN111330874A (en) | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle | |
CN109406539B (en) | Transparent medicine bottle bottom accumulated material defect detection system and method | |
CN109945842B (en) | Method for detecting label missing and analyzing labeling error of end face of bundled round steel |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |