CN107767377B - Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system - Google Patents
Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system Download PDFInfo
- Publication number
- CN107767377B CN107767377B CN201711100005.1A CN201711100005A CN107767377B CN 107767377 B CN107767377 B CN 107767377B CN 201711100005 A CN201711100005 A CN 201711100005A CN 107767377 B CN107767377 B CN 107767377B
- Authority
- CN
- China
- Prior art keywords
- image
- liquid crystal
- camera
- defect
- defects
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 96
- 239000004973 liquid crystal related substance Substances 0.000 title claims abstract description 70
- 239000000428 dust Substances 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000003384 imaging method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G02—OPTICS
- G02F—OPTICAL DEVICES OR ARRANGEMENTS FOR THE CONTROL OF LIGHT BY MODIFICATION OF THE OPTICAL PROPERTIES OF THE MEDIA OF THE ELEMENTS INVOLVED THEREIN; NON-LINEAR OPTICS; FREQUENCY-CHANGING OF LIGHT; OPTICAL LOGIC ELEMENTS; OPTICAL ANALOGUE/DIGITAL CONVERTERS
- G02F1/00—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics
- G02F1/01—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour
- G02F1/13—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour based on liquid crystals, e.g. single liquid crystal display cells
- G02F1/1306—Details
- G02F1/1309—Repairing; Testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N2021/9513—Liquid crystal panels
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Nonlinear Science (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Optics & Photonics (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Liquid Crystal (AREA)
Abstract
The invention discloses a liquid crystal display defect and dust distinguishing method based on a binocular vision system and a detection device. The distinguishing method comprises the following steps: the liquid crystal layer is used as a reference plane, a target image is used for calibrating a binocular vision system, and the mapping relation between image coordinate systems corresponding to the binocular vision system is determined; imaging the liquid crystal screen by using a binocular vision system to obtain a binocular image A and an binocular image B; respectively carrying out image processing on the image A and the image B to obtain defect information in the images; converting the image A and the image B to a reference plane coordinate system; in a reference plane coordinate system, obtaining parallax information of defects on a liquid crystal screen in the image A and the image B for the defects in the image A and the image B; judging parallax information of the defects in the image A and the image B, wherein the defects are foreign body defects if the parallax information is the same, and the surface dust is indicated if the parallax information is different. The problem that foreign matter defects and surface dust which cannot be distinguished in automatic detection equipment in the prior art can be solved.
Description
Technical Field
The invention relates to the technical field of visual detection, in particular to a liquid crystal display defect and dust distinguishing method and a detection device based on a binocular vision system.
Background
LCD (Liquid Crystal Display) the liquid crystal screen typically comprises, from top to bottom, TP (Touch Panel) glass, an upper polarizer, a color filter, a liquid crystal layer, a TFT (Thin Film Transistor) substrate, a lower polarizer, and a backlight. With the development of LCD technology, the LCD has the characteristics of high resolution, small volume, light weight, no radiation, flat panel, low power consumption and the like, rapidly becomes the main angle of the display market, and is ubiquitous in a plurality of fields from mobile phones to portable game machines, from manual operation platforms of industrial equipment to self-service equipment ATM (Automatic Teller Machine) of banks and the like. Therefore, quality inspection for LCD panels becomes particularly important.
The LCD screen process flow and quality detection mainly include: panel cutting, surface mounting, COG\FOG, dispensing and backlight assembly; the main quality detection comprises lighting inspection and appearance inspection after panel cutting, after pasting and after backlight assembly.
At present, quality detection of automatic lighting at each stage can be realized in the prior art, but the automatic detection device in the prior art cannot realize whether the foreign matters on the TP layer are surface dust which is not filtered during detection. Especially in the TP full-lamination post-process, defects are introduced in the assembly process of the process, foreign matters in the middle of a TP layer and a liquid crystal layer need to be detected, a light source is added on the surface of the liquid crystal layer in the traditional distinguishing mode at present, so that surface dust imaging is compared with internal real defects, but TP layer foreign matters can be imaged under the surface light source, are difficult to distinguish with dust, and TP foreign matters are missed in the detection process. The detection of the foreign matter of the TP layer is always in a blank state in the LCD detection apparatus.
As shown in fig. 1, a schematic diagram of a liquid crystal display 10 is shown. The liquid crystal display 10 comprises a cover plate 11, an upper polarizer 12, a liquid crystal layer 13, a lower polarizer 14 and a backlight source 15 which are sequentially attached. The minute object located on the surface of the cover plate 11 is defined as surface dust 16, and the minute object located between the cover plate 11 and the upper polarizer 12 is defined as a foreign matter defect 17. The foreign matter defect 17 is caused by the fact that when the liquid crystal module 10 is assembled and attached to the cover plate 11, a small part of foreign matter falls between the cover plate 11 and the upper polarizer 12, and the cover plate 11 is used for receiving the foreign matter existing in the cover plate.
The foreign matter defect 17 is usually missed because most of the foreign matter defect 17 is beaten out and filtered out as dust when the surface is polished, and the surface dust 16 and the foreign matter defect 17 only separate the transparent cover plate 11, so that the shot characteristics are basically no difference and cannot be accurately distinguished.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a liquid crystal display defect and dust distinguishing method and a detection device based on a binocular vision system, so as to solve the problem that automatic detection equipment in the prior art cannot distinguish foreign body defects from surface dust.
The aim of the invention is realized by the following technical scheme:
a liquid crystal display defect and dust distinguishing method based on a binocular vision system comprises the following steps:
placing a liquid crystal screen to be detected in detection equipment, wherein the detection equipment comprises a main camera and a plurality of side cameras distributed around the main camera, and a binocular vision system is formed by the main camera and any one side camera;
the method comprises the steps of calibrating a binocular vision system by using a target image by taking a liquid crystal layer of a liquid crystal screen to be detected as a reference plane, and determining a mapping relation between image coordinate systems corresponding to the binocular vision system;
using a binocular vision system to image the liquid crystal screen to obtain a binocular image A and an image B, wherein the image A is the image of the liquid crystal screen by the main camera, and the image B is the image of the liquid crystal screen by the side camera;
respectively carrying out image processing on the image A and the image B, and acquiring defect information in the image according to gray information;
converting the image A and the image B into a reference plane coordinate system according to the mapping relation;
in a reference plane coordinate system, carrying out defect registration on defects in the image A and the image B according to a matching criterion, and obtaining parallax information of the defects on the liquid crystal screen in the image A and the image B;
the parallax information of the defect in the image a and the image B is judged, and if the same, it is indicated as a foreign matter defect, and if different, it is indicated as surface dust.
In one embodiment, the detection device includes a main camera and four side cameras distributed around the main camera, and the four side cameras are distributed in a ring array shape with the main camera as a center.
In one embodiment, the primary camera is a high resolution camera and the side camera is a low resolution camera.
In one embodiment, the defect information includes: foreign matter defect information in the liquid crystal screen and surface dust information on the surface of the liquid crystal screen.
In one embodiment, determining parallax information for a defect in image a and image B includes:
judging whether the image parallax of the corresponding defect is larger than a preset error threshold value or not;
if the image parallax is larger than the error threshold, judging that the defect is not a foreign object defect;
and if the image parallax is smaller than the error threshold, judging that the defect is a foreign object defect.
A detection apparatus, comprising: one main camera, a plurality of side cameras, an annular track, a main camera lifting adjusting structure and a plurality of side camera lifting and angle adjusting structures;
the main cameras are arranged at the center of the annular track, and the side cameras are slidably arranged on the annular track and distributed around the main cameras;
the main camera lifting adjusting structure corresponds to one main camera, and the side cameras are respectively in one-to-one correspondence with the side camera lifting and angle adjusting structures;
the main camera lifting adjusting structure drives the main camera to lift along the vertical direction;
the side camera lifting and angle adjusting structure drives the side camera to lift or rotate, the side camera moves in a lifting manner along the vertical direction, and the rotating shaft of the side camera is parallel to the horizontal plane.
In one embodiment, the main camera lifting adjustment structure is a motor lead screw drive structure.
In one embodiment, the lifting and angle adjusting structure of the side camera comprises a lifting driving part and an angle adjusting part, the lifting driving part drives the side camera to move in a lifting mode along the vertical direction, the angle adjusting part drives the side camera to rotate, the lifting driving part is of a motor screw rod driving structure, the angle adjusting part is of a cylinder driving structure, a rack is arranged at the telescopic end of the angle adjusting part, and a gear meshed with the rack is arranged on the side camera.
According to the method steps, the defects can be automatically detected, and meanwhile, the function of distinguishing the foreign body defects from the surface dust in the liquid crystal automatic detection equipment can be realized according to the parallax of the defects in the binocular vision system, so that the problem that the foreign body defects and the surface dust which cannot be distinguished in the automatic detection equipment in the prior art can be solved.
Drawings
FIG. 1 is a schematic diagram of a liquid crystal display;
FIG. 2 is a flow chart showing steps of the method for distinguishing defects from dust of a liquid crystal display based on a binocular vision system according to the present invention;
FIG. 3 is a schematic diagram of a detection apparatus;
FIG. 4 is a schematic diagram of a binocular vision system for detecting a liquid crystal screen;
FIG. 5 is a binocular image A obtained by imaging a liquid crystal screen using a binocular vision system;
FIG. 6 is a binocular image B obtained by imaging a liquid crystal screen using a binocular vision system;
FIG. 7 is a schematic diagram of a detection apparatus according to another embodiment;
FIG. 8 is a schematic view of the main camera lift adjustment structure shown in FIG. 7;
fig. 9 is a schematic view of the lifting and angle adjusting structure of the side camera shown in fig. 7.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. The drawings illustrate preferred embodiments of the invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only and are not meant to be the only embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
As shown in fig. 2, a method for distinguishing defects from dust of a liquid crystal display based on a binocular vision system includes the following steps:
step 1, placing a liquid crystal screen to be detected in detection equipment, wherein the detection equipment comprises a main camera and a plurality of side cameras distributed around the main camera, and a binocular vision system is formed by the main camera and any one side camera;
step 2, calibrating a binocular vision system by using a target image by taking a liquid crystal layer of a liquid crystal screen to be detected as a reference surface, and determining a mapping relation between image coordinate systems corresponding to the binocular vision system;
step 3, imaging the liquid crystal screen by using a binocular vision system to obtain a binocular image A and an image B, wherein the image A is the imaging of the liquid crystal screen by the main camera, and the image B is the imaging of the liquid crystal screen by the side camera;
step 4, respectively carrying out image processing on the image A and the image B, and acquiring defect information in the image according to gray information; in the present embodiment, the defect information includes: foreign matter defect information in the liquid crystal screen and surface dust information on the surface of the liquid crystal screen.
Step 5, converting the image A and the image B into a reference plane coordinate system according to the mapping relation;
step 6, in a reference plane coordinate system, carrying out defect registration on defects in the image A and the image B according to a matching criterion, and obtaining parallax information of the defects on the liquid crystal screen in the image A and the image B; wherein the matching criteria include epipolar constraint criteria, similarity constraint criteria, parallax continuity constraint criteria, sequential constraint criteria, parallax constraint criteria, interoperability constraint criteria, and the like.
And 7, judging parallax information of the defects in the image A and the image B, if the parallax information is the same, indicating that the defects are foreign body defects, and if the parallax information is different, indicating that the defects are surface dust. Further, judging parallax information of the defect in the image a and the image B includes: judging whether the image parallax of the corresponding defect is larger than a preset error threshold value or not; if the image parallax is larger than the error threshold, judging that the defect is not a foreign object defect; and if the image parallax is smaller than the error threshold, judging that the defect is a foreign object defect.
As shown in fig. 3, specifically, in the present embodiment, the detection apparatus 20 includes a main camera 21 and four side cameras 22 distributed around the main camera 21, and the four side cameras 22 are distributed in a ring-shaped array with the main camera 21 as a center. The main camera 21 is a high-resolution camera, the side camera 22 is a low-resolution camera, and the camera acquisition view covers the whole liquid crystal area. A binocular vision system is formed by a main camera 21 and any one side camera 22, and defect detection is performed on the liquid crystal display. For example, a binocular vision system is formed by one main camera 21 and one of the four side cameras 22 in sequence to image the liquid crystal screen, so that four binocular images are obtained, and comprehensive comparison is performed on the four binocular images, so that defect detection can be performed on the liquid crystal screen more accurately.
As shown in fig. 4, 5 and 6, the following is specifically described:
the liquid crystal display 10 to be detected is placed in detection equipment, and the liquid crystal module 10 comprises a cover plate 11, an upper polaroid 12, a liquid crystal layer 13, a lower polaroid 14 and a backlight source 15 which are sequentially attached. The minute object located on the surface of the cover plate 11 is defined as surface dust 16, and the minute object located between the cover plate 11 and the upper polarizer 12 is defined as a foreign matter defect 17.
The liquid crystal layer 13 of the liquid crystal screen 10 to be detected is used as a reference plane, a target image is used for calibrating a binocular vision system, and the mapping relation between image coordinate systems corresponding to the binocular vision system is determined;
using a binocular vision system to image the liquid crystal screen to obtain a binocular image A and an image B, wherein the image A is the image of the liquid crystal screen by the main camera, and the image B is the image of the liquid crystal screen by the side camera; respectively carrying out image processing on the image A and the image B, and acquiring defect information in the image according to gray information; converting the image A and the image B into a reference plane coordinate system according to the mapping relation; for example, in image a, the main camera images the surface dust 16 to obtain a surface dust image 16', and the main camera images the foreign object defect 17 to obtain a foreign object defect 17'; in image B, the side camera images the surface dust 16 to obtain a surface dust image 16", and the side camera images the foreign matter defect 17 to obtain a foreign matter defect 17". Since the surface dust 16 is located above the cover plate 11 and is farther from the liquid crystal layer 13, after the side view of the surface dust 16 imaged by the side camera to obtain the surface dust image 16″ is converted into the front view, compared with the image shot by the main camera, the dot shape can deviate farther, otherwise, the foreign matter defect 17 deviates smaller, so that the surface dust 16 can be distinguished from the foreign matter defect 17, and whether the liquid crystal screen is a foreign matter defect can be identified;
in a reference plane coordinate system, carrying out defect registration on defects in the image A and the image B according to a matching criterion, and obtaining parallax information of the defects on the liquid crystal screen in the image A and the image B; the parallax information of the defect in the image a and the image B is judged, and if the same, it is indicated as a foreign matter defect, and if different, it is indicated as surface dust. For example, in the image a, two images are closer to each other, and in the image B, two images are farther from each other, it can be determined that the present liquid crystal panel 10 has a foreign matter defect.
According to the method steps, the defects can be automatically detected, and meanwhile, the function of distinguishing the foreign body defects from the surface dust in the liquid crystal automatic detection equipment can be realized according to the parallax of the defects in the binocular vision system, so that the problem that the foreign body defects and the surface dust which cannot be distinguished in the automatic detection equipment in the prior art can be solved.
As shown in fig. 7, 8 and 9, specifically, the detection device 20 includes: a main camera 21, a plurality of side cameras 22, a circular track 23, a main camera lifting and lowering adjusting structure 24, a plurality of side camera lifting and lowering and angle adjusting structures 25.
One main camera 21 is placed at the center of the circular orbit 23, and a plurality of side cameras 22 are slidably mounted on the circular orbit 23 and distributed around one main camera 21.
One main camera lifting and lowering adjusting structure 24 corresponds to one main camera 21, and a plurality of side camera lifting and lowering and angle adjusting structures 25 correspond to a plurality of side cameras 22 one by one, respectively.
The main camera elevation adjustment structure 24 drives the main camera 21 to be elevated in the vertical direction.
The side camera lifting and angle adjusting structure 25 drives the side camera 22 to lift or rotate, the side camera 22 moves up and down in the vertical direction, and the rotation axis of the side camera 22 is parallel to the horizontal plane.
The detection device 20 has the following beneficial effects through the structural improvement:
the plurality of side cameras 22 are slidably arranged on the annular track 23 and distributed around the main camera 21, and the position among the plurality of side cameras 22 can be adjusted by adopting the structural design, so that the positions among the plurality of side cameras 22 can be adjusted adaptively according to the size of the product and the detected actual conditions;
the main camera lifting adjusting structure 24 drives the main camera 21 to lift along the vertical direction, so that the height position of the main camera 21 can be adaptively adjusted according to the size and thickness of a product, the purpose of adjusting the focal length is achieved, and a clearer image is obtained;
the side camera lifting and angle adjusting structure 25 drives the side camera 22 to lift or rotate, on one hand, the height position of the side camera 22 can be adjusted, on the other hand, the angle of the side camera 22 can be adjusted, and according to the actual conditions such as the size of a product, the height and angle of the side camera 22 can be adjusted adaptively, so that a clearer image can be obtained.
In this embodiment, the main camera lifting adjustment structure 24 is a motor screw drive structure; the side camera lifting and angle adjusting structure 25 comprises a lifting driving part and an angle adjusting part, wherein the lifting driving part drives the side camera to move in a lifting manner along the vertical direction, the angle adjusting part drives the side camera to rotate, the lifting driving part is of a motor screw rod driving structure, the angle adjusting part is of a cylinder driving structure, a rack is arranged at the telescopic end of the angle adjusting part, and a gear meshed with the rack is arranged on the side camera.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (1)
1. The method for distinguishing the defects from dust of the liquid crystal display based on the binocular vision system is characterized by comprising the following steps of:
placing a liquid crystal screen to be detected in detection equipment, wherein the detection equipment comprises a main camera and a plurality of side cameras distributed around the main camera, the plurality of side cameras are distributed in an annular array shape by taking the main camera as a center, and a binocular vision system is formed by the main camera and any one side camera; the main camera is a high-resolution camera, and the side camera is a low-resolution camera;
the method comprises the steps of calibrating a binocular vision system by using a target image by taking a liquid crystal layer of a liquid crystal screen to be detected as a reference plane, and determining a mapping relation between image coordinate systems corresponding to the binocular vision system;
imaging the liquid crystal screen by using a binocular vision system to obtain a binocular image A and an image B, wherein the image A is a binocular image
The main camera images the liquid crystal screen, and the image B images the liquid crystal screen;
respectively carrying out image processing on the image A and the image B, and acquiring defect information in the image according to gray information; the defect information includes: foreign matter defect information in the liquid crystal screen and surface dust information on the surface of the liquid crystal screen;
converting the image A and the image B into a reference plane coordinate system according to the mapping relation;
in a reference plane coordinate system, carrying out defect registration on defects in the image A and the image B according to a matching criterion, and obtaining parallax information of the defects on the liquid crystal screen in the image A and the image B; the matching criteria comprise epipolar constraint criteria, similarity constraint criteria, parallax continuity constraint criteria, order constraint criteria, parallax constraint criteria and interoperability constraint criteria;
judging parallax information of the defects in the image A and the image B, if the parallax information is the same, indicating that the defects are foreign matter defects, and if the parallax information is different, indicating that the defects are surface dust; the judging of parallax information of the defect in the image a and the image B includes:
judging whether the image parallax of the corresponding defect is larger than a preset error threshold value or not;
if the image parallax is larger than the error threshold, judging that the defect is not a foreign object defect;
if the image parallax is smaller than the error threshold, judging that the defect is a foreign object defect;
the detection apparatus further includes: the device comprises an annular track, a main camera lifting adjusting structure and a plurality of side camera lifting and angle adjusting structures;
the main cameras are arranged at the center of the annular track, and the side cameras are slidably arranged on the annular track and distributed around the main cameras;
one main camera lifting and lowering adjusting structure corresponds to one main camera, and a plurality of side camera lifting and lowering and angle adjusting structures correspond to a plurality of side cameras one by one respectively;
the main camera lifting adjusting structure drives the main camera to lift along the vertical direction; the main camera lifting adjusting structure is a motor screw rod driving structure;
the side camera lifting and angle adjusting structure drives the side camera to lift or rotate, the side camera moves in a lifting manner along the vertical direction, and the rotating shaft of the side camera is parallel to the horizontal plane; the side camera lifting and angle adjusting structure comprises a lifting driving part and an angle adjusting part, the lifting driving part drives the side camera to move in a lifting mode along the vertical direction, the angle adjusting part drives the side camera to rotate, the lifting driving part is of a motor screw rod driving structure, the angle adjusting part is of a cylinder driving structure, a rack is arranged at the telescopic end of the angle adjusting part, and a gear meshed with the rack is arranged on the side camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711100005.1A CN107767377B (en) | 2017-11-09 | 2017-11-09 | Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711100005.1A CN107767377B (en) | 2017-11-09 | 2017-11-09 | Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107767377A CN107767377A (en) | 2018-03-06 |
CN107767377B true CN107767377B (en) | 2024-02-06 |
Family
ID=61272209
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711100005.1A Active CN107767377B (en) | 2017-11-09 | 2017-11-09 | Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107767377B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108760755A (en) * | 2018-07-03 | 2018-11-06 | 银河水滴科技(北京)有限公司 | A kind of dust granule detection method and device |
CN109580644B (en) * | 2018-12-17 | 2022-01-11 | 海南联新科技有限公司 | Visual inspection equipment for automobile parts |
CN112200760A (en) * | 2019-06-20 | 2021-01-08 | 惠州旭鑫智能技术有限公司 | Device and method for measuring and layering depth of defect of liquid crystal module |
CN110782782B (en) * | 2019-11-28 | 2022-03-29 | 合肥维信诺科技有限公司 | Array substrate repairing method and system |
CN111445452B (en) * | 2020-03-23 | 2022-03-01 | Oppo(重庆)智能科技有限公司 | Defect detection method and device of electronic product and computer readable storage medium |
CN111551559A (en) * | 2020-05-13 | 2020-08-18 | 深圳市全洲自动化设备有限公司 | LCD (liquid Crystal display) liquid crystal screen defect detection method based on multi-view vision system |
CN112964642A (en) * | 2021-04-21 | 2021-06-15 | 广东速美达自动化股份有限公司 | Method and system for detecting foreign matters in liquid crystal display based on binocular stereo reconstruction |
CN112858318B (en) * | 2021-04-26 | 2021-08-06 | 高视科技(苏州)有限公司 | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794717A (en) * | 2015-04-27 | 2015-07-22 | 中国科学院光电技术研究所 | Binocular vision system based depth information comparison method |
KR20160084212A (en) * | 2015-01-05 | 2016-07-13 | 한화테크윈 주식회사 | Apparatus for inspecting defect and method thereof |
CN105842885A (en) * | 2016-03-21 | 2016-08-10 | 凌云光技术集团有限责任公司 | Liquid crystal screen defect layered positioning method and device |
GB201711412D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
-
2017
- 2017-11-09 CN CN201711100005.1A patent/CN107767377B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160084212A (en) * | 2015-01-05 | 2016-07-13 | 한화테크윈 주식회사 | Apparatus for inspecting defect and method thereof |
CN104794717A (en) * | 2015-04-27 | 2015-07-22 | 中国科学院光电技术研究所 | Binocular vision system based depth information comparison method |
CN105842885A (en) * | 2016-03-21 | 2016-08-10 | 凌云光技术集团有限责任公司 | Liquid crystal screen defect layered positioning method and device |
GB201711412D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
Also Published As
Publication number | Publication date |
---|---|
CN107767377A (en) | 2018-03-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107767377B (en) | Liquid crystal display defect and dust distinguishing method and detection device based on binocular vision system | |
CN110657946B (en) | Screen defect detection system, screen detection line and screen defect detection method | |
CN205384134U (en) | Multistation cell -phone camera module detects machine | |
CN107390393B (en) | Re-judgment layering method after defect detection of liquid crystal module | |
CN203337939U (en) | Detection device of liquid crystal display panel | |
CN205377994U (en) | Multistation cell -phone camera module detects machine | |
CN101682798A (en) | Be used to control the universal test system of a plurality of parameters relevant with the operation of the device that is used to present various types of optoelectronic informations | |
CN205356603U (en) | Multistation cell -phone camera module detects machine | |
CN108956623B (en) | Demura multiaxis automated inspection mechanism | |
CN112595727B (en) | Imaging system and detection method for detecting defects of ink glass of rear cover plate of mobile phone | |
CN209927732U (en) | Binocular camera structure for grain detection imaging | |
CN107966836A (en) | A kind of TFT-LCD defects optics automatic checkout system | |
KR102037384B1 (en) | Apparatus and method for inspecting a panel | |
CN105892109B (en) | Device and method for detecting defective point of liquid crystal glass PI (polyimide) | |
CN204287670U (en) | Polaroid visual-alignment device | |
CN108414197B (en) | Panel lighting test device | |
CN108918533B (en) | Full-automatic Demura multiaxis detection mechanism | |
CN110426400A (en) | For touch screen can operating space automatic polisher and its automatic method for polishing | |
CN106249450A (en) | A kind of LCDs detecting system | |
CN103837545A (en) | Lens imaging device and method | |
CN101408520A (en) | Detection method and system for discriminating flaws of inner and outer layers | |
CN201096966Y (en) | 3D video microscope | |
CN207503282U (en) | Liquid crystal display defect based on binocular vision system distinguishes detection device with dust | |
CN201629797U (en) | Broad-spectrum digital camera | |
CN210294729U (en) | Novel LCD screen circuit detection device |
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 | ||
CB02 | Change of applicant information |
Address after: 215129 Rooms 101, 102, 901, 902, Floor 9, Building 11, No. 198, Jialing River Road, High tech Zone, Suzhou City, Jiangsu Province Applicant after: Gaoshi Technology (Suzhou) Co.,Ltd. Address before: 516006 District 75, Zhongkai high tech Industrial Development Zone, Huizhou City, Guangdong Province Applicant before: HUIZHOU GOVION TECHNOLOGY CO.,LTD. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |