CN208383732U - Bend glass defect detecting device based on machine vision - Google Patents
Bend glass defect detecting device based on machine vision Download PDFInfo
- Publication number
- CN208383732U CN208383732U CN201820998965.8U CN201820998965U CN208383732U CN 208383732 U CN208383732 U CN 208383732U CN 201820998965 U CN201820998965 U CN 201820998965U CN 208383732 U CN208383732 U CN 208383732U
- Authority
- CN
- China
- Prior art keywords
- curved glass
- light source
- axis
- bend glass
- image acquisition
- 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.)
- Expired - Fee Related
Links
- 239000011521 glass Substances 0.000 title claims abstract description 69
- 230000007547 defect Effects 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 230000005540 biological transmission Effects 0.000 claims abstract description 16
- 208000037656 Respiratory Sounds Diseases 0.000 abstract description 2
- 238000003384 imaging method Methods 0.000 description 7
- 238000000034 method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses the bend glass defect detecting device based on machine vision, described device includes image collecting device, transmission device and fixture；Described image acquisition device is used to acquire the image of bend glass；The fixture is for positioning and clamping bend glass；Described image acquisition device and the fixture are installed on the transmission device, and the position of transmission device the control image collecting device and bend glass makes to form effective detection zone on the bend glass immediately below image collecting device.The device flexibly can steadily detect 3D bend glass, solving curved-surface structure feature causes reflective bring defect image to obtain difficult problem, realizes the common open defects such as automatic detection scratch, crackle, chipping, avoids detection leakage phenomenon, apparatus structure is simple, easy to operate.
Description
Technical Field
The utility model relates to a visual detection technical field, in particular to curved surface glass defect detecting device based on machine vision.
Background
In recent years, 3D curved glass is favored by 3C product enterprises under the push of technologies such as 5G, wireless charging, and OLED. Meanwhile, the 3D curved glass is popular with consumers in terms of beautiful appearance and excellent performance. As an important part of the smart phone, the 3D curved glass plays a role in protection, and simultaneously determines the aesthetic degree of the smart phone and the use experience of consumers. However, during the manufacturing, transportation and the like, defects such as scratches, cracks, edge chipping, foreign matter and the like are inevitably generated. Therefore, the 3D curved glass should be detected in the production process in time.
The machine vision detection technology has the characteristics of high automation degree, low cost, high efficiency and the like, and can be widely applied to the field of product detection. Currently, conventional visual inspection equipment is generally applicable to the inspection of planar 2D cell phone screens. Due to the structural characteristics of three-dimensional curved edges, smoothness, transparency and the like, the 3D curved surface glass cannot be detected by adopting a 2D mobile phone screen visual detection device. The peripheral structural characteristics of the curved glass are transparent curved surfaces, and images shot by a camera have highlight light reflecting areas. On one hand, when defects are extracted in an image processing mode, some highlight areas may become pseudo defects, and the judgment of sample appearance quality detection is interfered. On the other hand, when the area of the highlight area is large, the existing defect features may be covered, and the defect missing problem may be caused.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to overcome prior art's defect and not enough, provide a curved surface glass defect detecting device based on machine vision, the device can detect 3D curved surface glass in a flexible way steadily, realizes automated inspection mar, crackle, collapses common appearance defects such as limit, has solved curved surface structural feature and has aroused the defect image acquisition difficulty problem that the reflection of light brought, avoids lou examining the phenomenon, device simple structure, convenient operation.
The purpose of the utility model can be realized by the following technical scheme: the device for detecting the defects of the curved glass based on machine vision comprises an image acquisition device, a transmission device and a clamp; the image acquisition device is used for acquiring an image of the curved glass; the clamp is used for positioning and clamping the curved glass; the image acquisition device and the clamp are arranged on the transmission device, and the transmission device controls the positions of the image acquisition device and the curved glass so that an effective detection area is formed on the curved glass right below the image acquisition device.
As a preferred technical scheme, the transmission device comprises an X-axis linear module, a Y-axis linear module, a Z-axis linear module, an electric rotary table rotating around a Y axis and an electric rotary table rotating around a Z axis; the Y-axis rotating electric rotary table is connected with the image acquisition device, the Y-axis rotating electric rotary table is installed on the Z-axis linear module, the Z-axis rotating electric rotary table is connected with the clamp, and the Z-axis rotating electric rotary table is installed on the Y-axis linear module.
As a preferred technical solution, the image capturing device includes a camera, a lens and a light source, the lens is connected to the camera, and the light source is installed below the lens.
As a preferred technical solution, the light source is a combined light source composed of two strip light sources.
As a preferred technical solution, the light source is a combined light source composed of four strip light sources. The polishing in different directions can effectively enhance the clear imaging of direction-sensitive defects (such as scratches) and reduce the defect omission phenomenon.
As a preferred technical solution, the light source is controlled by a light source controller.
Compared with the prior art, the utility model, following advantage and beneficial effect have:
1. the utility model discloses a dark field imaging principle gathers curved surface glass defect image, and through control camera, light source and curved surface glass's relative position relation, forms effective detection area, has effectively avoided leaking of defect to examine.
2. The utility model discloses a motion control realizes that the curved surface glass of five degrees of freedom detects, realizes the effective defect detection of curved surface glass curved surface all around.
3. The utility model discloses consider to polish from a plurality of angles, defect image formation of image contrast is high, reduces the defect and leaks to examine the phenomenon.
Drawings
FIG. 1 is the embodiment of the utility model provides an in the embodiment of curved surface glass defect detecting device based on machine vision
FIG. 2 is a schematic view of the embodiment of the present invention showing the structure of an image capturing device
FIG. 3 is a light path diagram of an embodiment of the present invention for forming an effective detection area
FIG. 4 is a diagram of the relative positions of the camera, the light source and the curved glass in the embodiment of the present invention
Description of the drawings: 1: a camera, 2: lens, 3: camera jig, 4: connecting ring, 5: light source, 6: light source fixture, 7: rotating the electric turntable around the Y axis, 8: z-axis linear module, 9: x-axis linear module, 10: a jig, 11: rotation of the electric turntable around Z circumference, 12: y-axis linear module, 13: curved glass, 14: bar light source, 15: first region, 16: second region, 17: third region, 18: parallel light beam
Detailed Description
The present invention will be described in further detail with reference to the following examples and drawings, but the present invention is not limited thereto.
As shown in fig. 1-2, the embodiment of the present invention provides a device for detecting defects of curved glass based on machine vision, which comprises an image acquisition device, a transmission device and a clamp 10. The image acquisition device is used for acquiring an image of the curved glass; the clamp 10 is used for positioning and clamping the curved glass; the image acquisition device and the clamp are arranged on the transmission device. The transmission device controls the positions of the image acquisition device and the curved glass, so that an effective detection area is formed on the curved glass right below the image acquisition device.
The image acquisition device comprises a camera 1, a lens 2 and a light source 5, wherein the lens 2 is connected with the camera 1 through a connecting ring 4, and the connecting ring 1 can increase the distance from a focal plane to the lens 2, so that the distance of the lens 2 for shooting an object is closer. The light source 2 is mounted below the lens 2 by a light source holder 6. The light source 2 comprises two parallel bar-shaped light sources 14, the light intensity of which is controlled by a light source controller. For some defects (such as scratches) with low imaging contrast and sensitivity to the light emitting direction, light emitting in different directions can be added, for example, two strip light sources are added in the vertical direction of two parallel strip light sources 14 to form a regular quadrilateral combined light source, thereby effectively enhancing clear imaging of the defects, improving the defect detection efficiency of curved glass, and reducing the missing detection phenomenon. The camera clamp 3 is connected with the electric rotating platform rotating around the Y axis, and the electric rotating platform rotating around the Y axis can drive the camera 1 and the light source 5 to rotate around the Y axis.
The transmission device comprises an X-axis linear module 9, a Y-axis linear module 12, a Z-axis linear module 8, an electric rotary table 7 rotating around a Y axis and an electric rotary table 11 rotating around a Z axis. The electric rotating platform 7 rotating around the Y axis is connected with the camera clamp 3, and the electric rotating platform 7 rotating around the Y axis is arranged on the Z axis linear module 8. The electric rotary table 11 rotating around the Z axis is connected with the clamp, and the electric rotary table 11 rotating around the Z axis is installed on the Y axis linear module 12. Due to the three-dimensional structure shape of the curved glass, at least five degrees of freedom are required for realizing the detection of the peripheral curved surfaces of the curved glass: three translational degrees of freedom and two rotational degrees of freedom. The X-axis linear module 9, the Z-axis linear module 8 and the electric turntable 7 rotating around the Y-axis can realize the translational motion of the camera 1 and the light source 5 in two directions X, Z and the rotational motion around the Y-axis. The Y-axis linear module 12 and the electric rotary table 11 rotating around the Z axis can realize the translation motion of the fixture 10 and the curved glass in the Y-axis direction and the rotation motion around the Z axis.
The fixture 10 can position and clamp the curved glass 13, and preferably, the influence of the light reflection of the fixture body on the detection can be reduced through the design of the fixture. An electric rotating table 11 rotating around the Z axis is arranged below the clamp 10, and the clamp 10 can be driven to rotate around the Z axis by rotating the electric rotating table 11 around the Z axis.
The embodiment of the utility model provides an in still provide a curved surface glass defect detecting method based on machine vision, this method includes following step:
and (3) mounting the curved glass on a clamp, and positioning and clamping the curved glass by the clamp.
And controlling the X-axis linear module 9, the Z-axis linear module 8 and the electric rotary table 7 to rotate around the Y axis, so that the camera 1 and the light source 5 are adjusted to form an effective detection area on the curved glass 13 right below. At this time, the camera 1 captures an image of the curved glass 13, and the defect is extracted on the computer by an image processing algorithm. Defects may also be classified according to image processing algorithms.
And the Y-axis linear module 12 is controlled to adjust the position of the curved glass 13, the X-axis linear module 9, the Z-axis linear module 8 and the electric rotary table 7 rotating around the Y axis are controlled to adjust the positions of the camera 1 and the light source 5, and the defect detection of different sections of the same curved edge of the curved glass 13 is realized.
And controlling the electric rotary table 11 to rotate around the Z axis to move, rotating the curved glass 13 to another curved edge, and repeating the detection steps for detecting the curved edge in sections, so that the detection of different curved edges of the curved glass 13 can be realized, and the detection of four curved edges of the curved glass 13 is finished.
And a reasonable polishing mode is determined, so that the problem that the defect images on the peripheral curved surfaces of the curved glass 13 are difficult to obtain can be solved. The embodiment of the utility model provides an in the curved surface glass defect detecting device and the method based on machine vision that will obtain effective detection area is obtained according to dark field imaging principle, and the contrast of the defect image of acquisition is higher. Fig. 3 is an optical path diagram forming an effective detection region. Two parallel light beams 18 are symmetrically irradiated onto the curved glass 13 from two sides and collected by the camera 1 to obtain a defect image. The light of the parallel light beam 18 impinging on the first area 15 cannot be picked up by the camera 1 and the image appears black. The parallel light beam 18 irradiates the light rays of the second area 16, and the image appears white and high. The light of the parallel light beam 18 irradiated to the third area 17 cannot be collected by the camera 1, and the image appears black. The third region 17 is located directly below the camera, and when a defect such as a scratch occurs in this region, light scattered by the defect is easily collected by the camera 1, and the third region 17 is less affected by curvature. The third region 17 is an effective detection region according to the dark field imaging principle.
An XY axis coordinate system is established by the circle center of a GH circular arc of a detection area of the curved glass, the radius of the circle of the GH circular arc is r.MN, the diameter of the effective light received by the camera is the coordinate of M (-D/2, H), the coordinate of N is (D/2, H), the coordinates of two strip-shaped light sources A and F are (-B, H) and (B, H), α is the included angle between the light emitted by the strip-shaped light source A, F and the vertical direction, the effective detection area of the curved glass is BE, the coordinate of B is (-x, y), the coordinate of E is (x, y), 2 β is the central angle corresponding to the BE circular arc, and k is determined according to the dark field imaging principle1、k2The slope of the reflected light and the slope of the incident light at the critical positions of the effective detection area and the highlight area respectively; k is a radical of3Slope of the normal to arc GH at this position.
The derivation process of the relative position relationship of the camera, the light source and the curved glass is as follows:
the coordinates of the point B and the point E on the circular arc are (-x, y), (x, y), and can obtain:
EQ is an angular bisector of EF and EM, BP is an angular bisector of BA and BN, and the following angular formula is obtained:
can be solved to obtain:
wherein,
therefore, the expression of the bar light source incidence angle α and the bar light source installation height h is:
α＝90°-atan(k2)，h＝k2(b-x)+y
the relative positions of the camera, the light source and the curved glass can be determined according to the above reversing process. After the relative position relation of the camera, the light source and the curved glass is determined, the transmission device in the detection device can be controlled through a control algorithm, so that the positions of the camera, the light source and the curved glass are adjusted to form an effective detection area, the defects of the curved glass are effectively detected, and the phenomenon of missing detection is avoided.
The above-mentioned embodiments only represent some embodiments of the present invention, and the description thereof is specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that, for those skilled in the art, without departing from the spirit of the present invention, several variations and modifications can be made, which are within the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.
Claims (6)
1. The curved glass defect detection device based on machine vision is characterized by comprising an image acquisition device, a transmission device and a clamp; the image acquisition device is used for acquiring an image of the curved glass; the clamp is used for positioning and clamping the curved glass; the image acquisition device and the clamp are arranged on the transmission device, and the transmission device controls the positions of the image acquisition device and the curved glass so that an effective detection area is formed on the curved glass right below the image acquisition device.
2. The machine vision based curved glass defect detection device of claim 1, wherein said transmission comprises an X-axis linear module, a Y-axis linear module, a Z-axis linear module, an electric rotary table rotating around the Y-axis, and an electric rotary table rotating around the Z-axis; the Y-axis rotating electric rotary table is connected with the image acquisition device, the Y-axis rotating electric rotary table is installed on the Z-axis linear module, the Z-axis rotating electric rotary table is connected with the clamp, and the Z-axis rotating electric rotary table is installed on the Y-axis linear module.
3. The machine vision-based curved glass defect detection device of claim 1, wherein the image capture device comprises a camera, a lens and a light source, the lens is connected with the camera, and the light source is installed below the lens.
4. The machine-vision based curved glass defect detection apparatus of claim 3, wherein said light source is a combined light source consisting of two strip light sources.
5. The machine-vision-based curved glass defect detection apparatus of claim 3, wherein said light source is a combined light source consisting of four bar light sources.
6. The machine-vision-based curved glass defect detection apparatus of any one of claims 3-5, wherein the light source is controlled by a light source controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820998965.8U CN208383732U (en) | 2018-06-26 | 2018-06-26 | Bend glass defect detecting device based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820998965.8U CN208383732U (en) | 2018-06-26 | 2018-06-26 | Bend glass defect detecting device based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208383732U true CN208383732U (en) | 2019-01-15 |
Family
ID=64965887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820998965.8U Expired - Fee Related CN208383732U (en) | 2018-06-26 | 2018-06-26 | Bend glass defect detecting device based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208383732U (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108709890A (en) * | 2018-06-26 | 2018-10-26 | 华南理工大学 | Bend glass defect detecting device based on machine vision and method |
| CN109724989A (en) * | 2019-02-28 | 2019-05-07 | 广东银宝山新科技有限公司 | Full-automatic optical detection device |
| CN111458342A (en) * | 2020-05-21 | 2020-07-28 | 佛山职业技术学院 | PET bottle blank defect detection platform based on machine vision |
| CN111795971A (en) * | 2020-07-14 | 2020-10-20 | 深圳市格灵人工智能与机器人研究院有限公司 | Optical appearance detection device |
| CN112763493A (en) * | 2019-11-05 | 2021-05-07 | 华硕电脑股份有限公司 | Appearance image capturing device and appearance detection device comprising same |
| CN115326813A (en) * | 2022-09-05 | 2022-11-11 | 科为升视觉技术（苏州）有限公司 | Visual detection method and device used after pad printing of 3D curved glass cover plate of mobile phone |
| CN117871415A (en) * | 2024-03-11 | 2024-04-12 | 天津大学四川创新研究院 | Exposure type structural flaw detection system and method based on parallel light source |
-
2018
- 2018-06-26 CN CN201820998965.8U patent/CN208383732U/en not_active Expired - Fee Related
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108709890A (en) * | 2018-06-26 | 2018-10-26 | 华南理工大学 | Bend glass defect detecting device based on machine vision and method |
| CN109724989A (en) * | 2019-02-28 | 2019-05-07 | 广东银宝山新科技有限公司 | Full-automatic optical detection device |
| CN112763493A (en) * | 2019-11-05 | 2021-05-07 | 华硕电脑股份有限公司 | Appearance image capturing device and appearance detection device comprising same |
| CN111458342A (en) * | 2020-05-21 | 2020-07-28 | 佛山职业技术学院 | PET bottle blank defect detection platform based on machine vision |
| CN111795971A (en) * | 2020-07-14 | 2020-10-20 | 深圳市格灵人工智能与机器人研究院有限公司 | Optical appearance detection device |
| CN115326813A (en) * | 2022-09-05 | 2022-11-11 | 科为升视觉技术（苏州）有限公司 | Visual detection method and device used after pad printing of 3D curved glass cover plate of mobile phone |
| CN115326813B (en) * | 2022-09-05 | 2024-04-19 | 科为升视觉技术（苏州）有限公司 | Visual detection method and device used for mobile phone 3D curved surface glass cover plate after pad printing |
| CN117871415A (en) * | 2024-03-11 | 2024-04-12 | 天津大学四川创新研究院 | Exposure type structural flaw detection system and method based on parallel light source |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108709890B (en) | Curved glass defect detection device and method based on machine vision | |
| CN208383732U (en) | Bend glass defect detecting device based on machine vision | |
| CN107764834B (en) | Device for automatically detecting surface defects of transparent part and detection method thereof | |
| CN106959293B (en) | System and method for detecting defects on reflective surface through vision system | |
| CN106442327B (en) | Optical system for detecting object side image information | |
| CN112945988B (en) | Lens defect detection system and detection method | |
| CN210604434U (en) | Online detection device for typical defects of curved glass of mobile phone | |
| CN106226327B (en) | A kind of cambered surface external surface of objects defect inspection method and system | |
| JP2010016048A (en) | Inspection device for wafer | |
| CN111337518A (en) | Lens defect detecting system | |
| CN103105403A (en) | Method and device for detecting surface defect of transparent optical component | |
| CN110987970A (en) | Object surface defect detection system and detection method | |
| CN102621152A (en) | Surface defect detecting system of crystalline silicon polished wafer | |
| CN102374997A (en) | High-precision detection device of coin surface quality based on vision system | |
| KR102267990B1 (en) | Wafer edge inspectoin with trajectory following edge profile | |
| CN208833689U (en) | Detection device | |
| CN109856155A (en) | A kind of liquid crystal display surface detection apparatus and method based on polarised light | |
| CN102609152A (en) | Large-field-angle detection image acquisition method for electronic white board and device | |
| CN110849886A (en) | Device and method for realizing simultaneous detection of semiconductor crystal grain top surface and bottom surface based on image transfer lens | |
| JP2011164062A (en) | Transparent flat plate detection system | |
| CN114624245A (en) | Optical device and method for realizing asynchronous aplanatic imaging detection of two end faces and two side faces of semiconductor crystal grain | |
| CN110082361B (en) | Object appearance and crack detection device and detection method | |
| CN207662807U (en) | A kind of device of automatic detection transparent parts surface defect | |
| JP5312182B2 (en) | Tire inner surface inspection device | |
| CN211014053U (en) | High-precision automatic object surface flaw image capturing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190115 |