CN112858312B - Pen cap silicon bead installation visual detection device and method - Google Patents
Pen cap silicon bead installation visual detection device and method Download PDFInfo
- Publication number
- CN112858312B CN112858312B CN202110076671.6A CN202110076671A CN112858312B CN 112858312 B CN112858312 B CN 112858312B CN 202110076671 A CN202110076671 A CN 202110076671A CN 112858312 B CN112858312 B CN 112858312B
- Authority
- CN
- China
- Prior art keywords
- pen cap
- image
- camera
- installation
- silica
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8841—Illumination and detection on two sides of object
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/50—Manufacturing or production processes characterised by the final manufactured product
Abstract
The invention relates to a pen cap silica bead installation visual detection device and a method, wherein the device comprises a camera, an upper computer, a fixed support used for installing the camera, and a workbench used for installing and fixing a pen cap to be detected, wherein an annular light source is arranged on the workbench and is positioned at a pen cap installation position on the workbench, the camera is connected with the upper computer through a transmission line, and the upper computer is configured to execute the following steps: when the annular light source is lightened, receiving an axial image of the pen cap to be detected, which is acquired by the camera; carrying out gray scale and binary processing on the collected image in sequence; and calculating the area of the silica bead area of the pen cap, and outputting an abnormal value if the area is smaller than a threshold value. Compared with the prior art, the invention illuminates the pen cap from the end part of the pen cap through the annular light source, then collects the axial image of the pen cap from the opening of the pen cap, and realizes the visual detection whether the silica bead installation angle is correct or not through the area of the silica bead part after gray scale and binary processing in sequence, thereby greatly improving the detection efficiency of the silica bead.
Description
Technical Field
The invention relates to the field of stationery manufacturing and detection, in particular to a pen cap silicon bead installation visual detection device and method.
Background
In the production of gel ink pens, the installation of pen cap silica beads is one of the necessary procedures, and the pen cap silica beads are important parts for protecting pen points. The silica beads on the pen cap are installed obliquely, and the silica beads are easy to fall off in the subsequent use, so that the fragile pen point is not protected, and the silica beads can be damaged by impact, and the writing life of the gel pen is seriously influenced.
At present, in the installation process of the silica beads on the pen cap of the gel ink pen, the silica beads on the pen cap are generally installed and detected in a manual detection mode, so that defective products are screened out. However, the manual screening mode has large workload, low working efficiency and low accuracy, and the detection speed cannot meet the production requirement. In addition, the existing detection mode has the problems of fuzzy judgment qualified standards, inaccurate detection caused by observation angle and definition, low accuracy and efficiency caused by human uncontrollable factors and the like.
Disclosure of Invention
The invention aims to provide a pen cap silica bead installation visual detection device and a pen cap silica bead installation visual detection method.
The purpose of the invention can be realized by the following technical scheme:
the utility model provides a pen cap silica bead installation visual detection device, includes camera, host computer, is used for installing the fixed bolster of camera to and the fixed workstation of the pen cap that awaits measuring of installation, be equipped with annular light source on the workstation, this annular light source is located the pen cap installation position department on the workstation, the camera passes through transmission line connection with the host computer, the host computer is configured to carry out following step:
when the annular light source is lightened, receiving an axial image of the pen cap to be detected, which is acquired by a camera, wherein the image is shot from the opening direction of the pen cap;
carrying out gray level processing and binarization processing on the acquired image in sequence;
and calculating the area of the pen cap silica bead region based on the image after the binarization processing, and outputting an abnormal value if the area is smaller than a threshold value.
The threshold specifically comprises:
wherein: ST is a threshold value and is a threshold value,
the average value of the areas of the pen cap silica bead areas under the condition that all silica beads are normally installed is shown, alpha is a proportionality coefficient, and the proportionality coefficient is 0.9-1.
The alpha is 0.95.
The axial image contains all areas of the pen cap silica beads.
The workbench is an annular rotatable workbench, a plurality of pen cap mounting positions are arranged on the annular rotatable workbench, and annular light sources are arranged at the pen cap mounting positions.
The upper computer is a PC.
An automatic detection method for pen cap silicon bead installation comprises the following steps:
when the annular light source is lightened and the pen cap to be detected is axially irradiated from the closed end part of the pen cap to be detected, receiving an axial image of the pen cap to be detected, which is acquired by a camera, wherein the image is shot from the opening direction of the pen cap;
carrying out gray level processing and binarization processing on the acquired image in sequence;
and calculating the area of the pen cap silica bead region based on the image after the binarization processing, and outputting an abnormal value if the area is smaller than a threshold value.
Compared with the prior art, the invention has the following beneficial effects:
1) the pen cap is illuminated from the end part of the pen cap through the annular light source, then the axial image of the pen cap is collected from the opening of the pen cap, gray level and binary processing are sequentially carried out, whether the silica bead installation angle is correct or not is visually detected through the area of the silica bead part, and the detection efficiency of the silica beads is greatly improved.
2) The threshold value is dynamically generated, self-learning can be realized, and the detection precision is improved.
3) Cutting a part of area to calculate area, reducing calculated amount and lowering performance requirement
4) And the annular rotatable workbench is adopted, so that the detection efficiency is improved.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of the present invention;
FIG. 2 is a diagram illustrating the effect of gray scale processing on an image in an embodiment;
FIG. 3 is a diagram illustrating the effect of image binarization processing in the embodiment;
FIG. 4 is a diagram of actual acquisition in the example;
wherein: 1. the device comprises a fixed support, 2, a pen cap to be tested, 3, an annular light source, 4, an annular rotatable workbench, 5, a camera, 6 and an upper computer.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The utility model provides a pen cap silica bead installation visual detection device, as shown in figure 1, including camera 5, host computer 6, the fixed bolster 1 that is used for installing camera 5 to and the fixed workstation of the pen cap that awaits measuring of installation, be equipped with annular light source 3 on the workstation, this annular light source 3 is located the pen cap installation position department on the workstation, and camera 5 passes through transmission line connection with host computer 6, as shown in figure 2 ~ 4, the host computer is configured to carry out following step:
when the annular light source 3 is lightened, receiving an axial image of the pen cap 2 to be detected, which is acquired by the camera 5, wherein the image is shot from the opening direction of the pen cap;
carrying out gray level processing and binarization processing on the collected image in sequence, wherein after binarization, the silicon bead part is black, and the rest part is white;
and calculating the area of the pen cap silica bead region based on the image after the binarization processing, and outputting an abnormal value if the area is smaller than a threshold value.
When the silica ball installation slope, its projection area on the axial cross section can reduce, consequently, this application illuminates the pen cap from pen cap tip through annular light source, then follows the axial image of pen cap collection from pen cap opening part, passes through grey level and binary processing in proper order, and whether the area through silica ball part realizes silica ball installation angle correct visual detection, has improved the detection efficiency of silica ball greatly.
In some embodiments, the threshold is dynamically generated, so that self-learning can be realized, and the detection accuracy is improved, where the specific threshold is:
wherein: ST is a threshold value and is a threshold value,
the average value of the areas of the pen cap silica bead areas under the condition that all silica beads are normally installed is shown, alpha is a proportionality coefficient, and the proportionality coefficient is 0.9-1.
For example, in a certain embodiment, α is determined to be 0.95 based on the variance and standard deviation.
The annular light source 3 can uniformly generate light with stronger brightness to radiate outwards, the light intensity is uniform within a certain horizontal range, in some embodiments, the focal length of the lens of the camera 5 is 16mm, and in other embodiments, the focal length can be larger than 16 mm; an image processing part in the upper computer is mainly written by an open source algorithm OpenCV; the transmission line has conventional data interface and trigger device interface, and data interface links to each other with host computer 6, and trigger device links to each other with outside trigger signal, and fixed bolster 1 is similar with general camera support.
After the image is subjected to graying processing, the gray value of a pixel point on the image is between 0 and 255. Such images typically exhibit a distinct black and white effect, with 0 representing the lowest brightness and the tail black being displayed and 255 representing the brightest brightness and the white being displayed. By changing the height and the angle of the light source, any pixel point with the pixel value within the range can be displayed theoretically to form images with different gray levels. After binarization processing is adopted, the installation inclination angles of the pen cap silica beads are different, the area of a formed image is different, the installation of the pen cap silica beads is qualified, and the area of the formed image is larger than the area of the image formed by the installation inclination of the silica beads. The image is grayed, the collected image is converted into a gray image, due to the irradiation of the uniform radiation annular light source, the silicon bead part and the non-silicon bead part have obvious brightness difference, and after the silicon bead part is converted into the gray image, the brightness of the silicon bead part is lower.
In some embodiments, the interested region comprises all regions of the silica beads of the pen cap, one pen cap is selected to frame the whole silica bead part according to the brightness difference between the silica bead part and the non-silica bead part, the frame also comprises a few non-silica bead parts, the size of the frame is adjusted to ensure that the silica bead image is completely acquired, the calculated amount can be reduced, and the performance requirement is lowered
In some embodiments, the workbench is an annular rotatable workbench 4, a plurality of cap mounting positions are arranged on the annular rotatable workbench 4, and an annular light source 3 is arranged at each cap mounting position.
In some embodiments, the upper computer 6 is a PC, which is easier to implement.
When the application is used, the steps are as follows:
1) and fixing the camera. Adjusting the size of a clamp of a fixed support 1 to vertically fix a camera 5 on the support, enabling a lens to face downwards, adjusting the height of the camera and adjusting the focal length of the camera by moving the clamp of the support up and down according to the placement position of pen caps and the distance between the pen caps, and enabling the camera to simultaneously shoot silicon beads of the pen caps and clearly display the silicon beads on a liquid crystal display;
2) the light source is fixed. Keeping the height of the camera 5 and the position of the pen cap 2 to be measured unchanged, irradiating the tail end of the pen cap by using a light source to ensure that the brightness displayed on the display screen by the silica bead part and the non-silica bead part is different, so that the brightness of the silica bead part is lower than that of the non-silica bead part, adjusting the height and the angle of the light source to ensure that the difference is more obvious, and fixing the light source at the moment;
3) the shot picture is transmitted to an upper computer 6, the picture is subjected to gray processing through a gray image processing system, a threshold value is set according to the calculated gray value of the silica bead part and the gray value of the non-silica bead part, and the gray image is converted into a binary image (the silica bead part is black, and the rest part is white). And calculating the area of the black silica bead part (the area is expressed by the number of pixel points) according to the binary image. And if the black silicon bead part pixel point is larger than 96212, the qualified pen cap is installed.
4) Connecting a trigger signal of the pen cap transmission device to the camera through a transmission line, when the trigger signal is transmitted, representing that a new pen cap sample exists, simultaneously shooting a picture by the camera, completing signal acquisition for one time, then transmitting the picture to a gray level image processing system in the industrial personal computer for processing, setting a standard silicon bead installation image area range according to the sample pen cap, outputting a logic value '1' when the image area is larger than 212 pixel points, otherwise outputting a logic value '0', not detecting that the image can output an 'invalid' value, and repeating the steps;
5) and transmitting the processed result to a pen cap conveying device, reserving the pen cap with the output logic result of '1', and removing the pen cap with the output logic result of '0'.
Claims (9)
1. The utility model provides a pen cap silica bead installation visual detection device, its characterized in that includes camera (5), host computer (6), is used for installing fixed bolster (1) of camera (5) to and the fixed workstation of the pen cap that awaits measuring of installation, be equipped with annular light source (3) on the workstation, this annular light source (3) are located the pen cap installation position department on the workstation, camera (5) pass through transmission line connection with host computer (6), the host computer is configured to carry out following step:
when the annular light source (3) is lightened, receiving an axial image of the pen cap (2) to be detected, which is acquired by a camera (5), wherein the image is shot from the opening direction of the pen cap, and the axial image contains a region of pen cap silica beads;
carrying out gray level processing and binarization processing on the acquired image in sequence;
and calculating the area of the pen cap silica bead region based on the image after the binarization processing, and outputting an abnormal value if the area is smaller than a threshold value.
2. The pen cap silica bead mounting visual inspection device of claim 1, wherein the threshold is specifically:
wherein: ST is a threshold value and is used as a threshold value,
the average value of the areas of the pen cap silica bead areas under the condition that all silica beads are normally installed is shown, alpha is a proportionality coefficient, and the proportionality coefficient is 0.9-1.
3. The pen-cap silica bead mounted visual inspection device of claim 2, wherein said α is 0.95.
4. The pen cap silicon bead installation visual inspection device according to claim 1, wherein the workbench is an annular rotatable workbench (4), a plurality of pen cap installation positions are arranged on the annular rotatable workbench (4), and an annular light source (3) is arranged at each pen cap installation position.
5. The pen cap silica bead mounting visual inspection device according to claim 1, wherein the upper computer (6) is a PC.
6. An automatic detection method for pen cap silicon bead installation is characterized by comprising the following steps:
when the annular light source (3) is lightened and the pen cap (2) to be detected is axially irradiated from the closed end part of the pen cap (2) to be detected, an axial image of the pen cap (2) to be detected, acquired by a camera (5), is received, wherein the image is obtained by shooting from the opening direction of the pen cap, and the axial image contains a region of pen cap silica beads;
carrying out gray level processing and binarization processing on the acquired image in sequence;
and calculating the area of the pen cap silica bead region based on the image after the binarization processing, and outputting an abnormal value if the area is smaller than a threshold value.
7. The automatic detection method for installation of the pen cap silicon bead as claimed in claim 6, wherein the threshold specifically is:
wherein: ST is a threshold value and is a threshold value,
the average value of the areas of the pen cap silica bead areas under the condition that all silica beads are normally installed is shown, alpha is a proportionality coefficient, and the proportionality coefficient is 0.9-1.
8. The automatic detection method for pen cap silica bead installation according to claim 7, wherein α is 0.95.
9. The method according to claim 6, wherein the axial image contains all areas of the pen cap silica beads.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110076671.6A CN112858312B (en) | 2021-01-20 | 2021-01-20 | Pen cap silicon bead installation visual detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110076671.6A CN112858312B (en) | 2021-01-20 | 2021-01-20 | Pen cap silicon bead installation visual detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112858312A CN112858312A (en) | 2021-05-28 |
| CN112858312B true CN112858312B (en) | 2022-09-02 |
Family
ID=76007786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110076671.6A Active CN112858312B (en) | 2021-01-20 | 2021-01-20 | Pen cap silicon bead installation visual detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112858312B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104132943A (en) * | 2013-05-02 | 2014-11-05 | 上海工程技术大学 | Method and device of vehicle-mounted high-speed dynamic railway surface defect video detection |
| CN211292638U (en) * | 2019-08-07 | 2020-08-18 | 上海晨光文具股份有限公司 | Quick automatic checkout device of pen tube printing |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3293257B2 (en) * | 1993-08-30 | 2002-06-17 | 株式会社デンソー | Surface defect inspection equipment |
| JP2009171561A (en) * | 2007-12-21 | 2009-07-30 | Canon Inc | Image processing device, and image processing method |
| CN106093051A (en) * | 2016-06-06 | 2016-11-09 | 佛山市智人机器人有限公司 | Paper roll tangent plane burr detection method based on machine vision and device |
| CN109146841B (en) * | 2018-07-02 | 2021-07-02 | 广州市讯思视控科技有限公司 | Visual detection method and system for filling defects of dry battery coated paper |
| CN109225941B (en) * | 2018-10-10 | 2021-03-19 | 常熟理工学院 | Automatic detection and sorting system and method for internal thread tapping condition |
| CN109461156B (en) * | 2018-12-20 | 2021-07-16 | 浙江大学台州研究院 | Threaded sealing plug assembly detection method based on vision |
| CN109991215B (en) * | 2019-03-08 | 2021-09-24 | 深圳市象形字科技股份有限公司 | Abnormal condition early warning method for urine detector |
| CN111145165A (en) * | 2019-12-30 | 2020-05-12 | 北京工业大学 | Rubber seal ring surface defect detection method based on machine vision |
| CN111141746B (en) * | 2020-02-10 | 2022-07-15 | 上海工程技术大学 | Method and system for automatically detecting length of refill tail oil |
-
2021
- 2021-01-20 CN CN202110076671.6A patent/CN112858312B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104132943A (en) * | 2013-05-02 | 2014-11-05 | 上海工程技术大学 | Method and device of vehicle-mounted high-speed dynamic railway surface defect video detection |
| CN211292638U (en) * | 2019-08-07 | 2020-08-18 | 上海晨光文具股份有限公司 | Quick automatic checkout device of pen tube printing |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉汽车扶手箱卡簧装配质量检测系统的研究;郝存明等;《河北省科学院学报》;20170315(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112858312A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110501342B (en) | Cheese yarn rod positioning visual detection method | |
| CN103499303A (en) | Wool fineness automatic measuring method | |
| CN107345789B (en) | PCB hole position detection device and method | |
| CN111179362B (en) | Test paper color uniformity detection method based on dynamic illumination correction algorithm | |
| CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
| CN112129783B (en) | Transparent medicine bottle bottom defect detection method based on deep learning | |
| CN108037142A (en) | Mask plate optical defect detection method based on image intensity value | |
| CN112819844B (en) | Image edge detection method and device | |
| CN111157532A (en) | Visual detection device and method for scratches of mobile phone shell | |
| CN114359253A (en) | Image pollution detection method and system based on convolutional neural network | |
| US7238930B2 (en) | Inspection device for mouth of container | |
| EP2584307A1 (en) | Glass bottle inspection device | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN112858312B (en) | Pen cap silicon bead installation visual detection device and method | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN114187348B (en) | Method for measuring elongation at break of cable sheath based on computer vision | |
| CN113189002B (en) | Online detection method and device for stripe defects of ultrathin electronic glass substrate | |
| CN111141746B (en) | Method and system for automatically detecting length of refill tail oil | |
| CN115406808A (en) | Coke particle size diameter and proportion analysis detector based on vision | |
| CN113793321A (en) | Casting surface defect dynamic detection method and device based on machine vision | |
| US9136185B2 (en) | Methods and systems for grain size evaluation of multi-cystalline solar wafers | |
| JP4036048B2 (en) | Defect identification method | |
| KR870000631B1 (en) | Device for measurement of skin mill area | |
| CN203083937U (en) | Machine vision-based detection system of U-shaped powder tube | |
| CN110596746B (en) | Method for automatic testing/calibrating device using dose equivalent instrument |
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 |