CN113888533A - Display panel defect identification device, method, electronic device and medium - Google Patents
Display panel defect identification device, method, electronic device and medium Download PDFInfo
- Publication number
- CN113888533A CN113888533A CN202111362477.0A CN202111362477A CN113888533A CN 113888533 A CN113888533 A CN 113888533A CN 202111362477 A CN202111362477 A CN 202111362477A CN 113888533 A CN113888533 A CN 113888533A
- Authority
- CN
- China
- Prior art keywords
- defect
- display panel
- image
- defect identification
- acquisition unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 267
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 82
- 238000003860 storage Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 229920001621 AMOLED Polymers 0.000 description 13
- 230000008569 process Effects 0.000 description 13
- 239000010408 film Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 230000002411 adverse Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 206010052428 Wound Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000011368 organic material Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G3/00—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
- G09G3/006—Electronic inspection or testing of displays and display drivers, e.g. of LED or LCD displays
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G3/00—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
- G09G3/20—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters
- G09G3/22—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources
- G09G3/30—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels
- G09G3/32—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED]
- G09G3/3208—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED] organic, e.g. using organic light-emitting diodes [OLED]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application discloses a defect identification device and method of a display panel, an electronic device and a readable storage medium. The defect identification device comprises a first image acquisition unit, a defect detection unit, a second image acquisition unit and a defect identification unit. The defect identification device comprises a first image acquisition unit, a defect detection unit, a second image acquisition unit and a defect identification unit, wherein the first image acquisition unit is used for acquiring a characteristic image of the display panel, the defect detection unit is used for determining a defect coordinate of the display panel according to the characteristic image, the second image acquisition unit is used for shooting a local color image of a region corresponding to the position of the defect coordinate according to the defect coordinate, the defect identification unit comprises a processor and a memory storing a computer instruction of a defect identification model, and the processor executes the computer instruction to realize the identification of the local color image by using the defect identification model to obtain a defect type so as to classify the defect. This application is through detecting display panel to carry out accurate classification by the bad of stabbing, foreign matter production, reduce and miss the risk of examining, the cost of using manpower sparingly reduces the bad loss that causes.
Description
Technical Field
The present disclosure relates to display technologies, and in particular, to a defect recognition apparatus, a defect recognition method, a control apparatus, and a computer storage medium for a display panel.
Background
Generally, after the TFE process is completed, the cut back film (bottom film) attached to the lower surface of the panel is removed, and a U-shaped film (U-Lami) is attached to replace the back film. The U-shaped film has the function of ensuring that the U-shaped film and the panel of the flexible AMOLED are not separated when the panel is bent, and protecting the panel from being damaged in the following process. However, defects such as foreign matters and scratches are easily generated in the U-shaped film process, and it is difficult for the current detection device to detect and classify the defects generated on the flexible AMOLED panel.
Disclosure of Invention
The embodiment of the application provides a defect recognition device of a display panel, including:
the first image acquisition unit is used for acquiring a characteristic image of the display panel;
the defect detection unit is used for measuring the defect coordinates of the display panel according to the characteristic image;
the second image acquisition unit is used for acquiring a local color image of a region corresponding to the position of the defect coordinate according to the defect coordinate;
and the defect identification unit comprises a processor and a memory, wherein the memory stores computer instructions of a defect identification model, and the processor executes the computer instructions to identify the local color image by using the defect identification model to obtain a defect type so as to classify the defect.
In some embodiments, the defect identifying device includes a light source for emitting detection light to the display panel;
the acquiring the characteristic image of the display panel comprises: receiving the detection light passing through the display panel to obtain the characteristic image;
the acquiring of the local color image of the region corresponding to the position of the defect coordinate according to the defect coordinate comprises:
and receiving the detection light passing through the corresponding area of the position of the defect coordinate in the display panel to obtain the local color image.
In some embodiments, the defect identifying device includes a first stage and a guide rail, the first stage is used for carrying and fixing the display panel;
the guide rail is used for moving the first image acquisition unit from a first position to a preset position so as to scan the display panel to obtain the characteristic image, and moving the first image acquisition unit from the preset position to the first position;
the guide rail is further used for moving the second image acquisition unit from a second position to the preset position so as to acquire the local color image of the display panel, and moving the second image acquisition unit from the preset position to the second position.
In some embodiments, the defect identifying apparatus includes a first stage, a second stage, and a transport unit connecting the first stage and the second stage, and the light source includes a first light source and a second light source;
the first carrying platform is used for carrying and fixing the display panel, and the first image acquisition unit is used for receiving detection light passing through the display panel on the first carrying platform so as to obtain the characteristic image of the display panel;
the transmission unit is used for transmitting the display panel on the first carrying platform to the second carrying platform;
the second stage bears and fixes the display panel transmitted by the first stage, the second light source is used for sending the detection light to the display panel on the second stage, and the second image acquisition unit is used for receiving the detection light passing through the display panel on the second stage so as to obtain the local color image of the display panel.
In some embodiments, the first image acquisition unit comprises a line scan camera or an area scan camera.
In some embodiments, the second image capturing unit includes a high power lens, and the second image capturing unit captures the partial color image at a preset magnification through the high power lens.
In certain embodiments, the processor of the defect identification unit executes the computer instructions to enable the acquisition of the classified local color images for training the defect identification model.
In some embodiments, the display panel is provided with a mark, and the defect detection unit determines the defect coordinates of the display panel according to the position of the mark in the feature image.
The embodiment of the application further provides a defect identification method of a display panel, which comprises the following steps:
scanning a display panel to obtain a characteristic image of the display panel;
determining defect coordinates of the display panel according to the characteristic image;
shooting a local color image of a region corresponding to the position of the defect coordinate according to the defect coordinate;
and identifying the local color image by using a defect identification model to obtain a defect type so as to classify the defect.
In some embodiments, the display panel is provided with a mark, and the detecting the defect coordinates of the display panel according to the characteristic image comprises:
and determining the defect coordinates of the display panel according to the positions of the marks in the characteristic image.
In some embodiments, the defect identification method includes:
establishing an algorithm model aiming at the defect type to be detected;
training the algorithm model by using a training image, wherein the training image comprises classified local color images;
detecting a verification image by using the trained algorithm model to obtain a verification detection result so as to optimize the algorithm model;
and repeating the training steps, and determining that the algorithm model is trained to be finished as the defect identification model under the condition that the accuracy of the verification detection result reaches a preset value.
The embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the defect identification method is implemented.
A non-transitory computer-readable storage medium containing a computer program which, when executed by a processor, causes the processor to perform the defect identification method described above is provided.
In the defect recognition device, the defect recognition method, and the computer-readable storage medium of the display panel according to the embodiments of the present application, the display panel is scanned by the first image acquisition unit to obtain a feature image related to the display panel, the defect detection unit can detect the defect coordinate position of the display panel according to the feature image of the display panel, the second image acquisition unit shoots a local color image of a region corresponding to the position of the defect coordinate according to the detected defect coordinate, and the defect recognition unit recognizes the local color image by using a preset defect recognition model to obtain the defect type to classify the defect. Therefore, the defects generated by stabbing and foreign matters in the display panel can be accurately classified, the missing detection risk is reduced, the labor cost is saved, and the loss caused by the defects is reduced.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a block diagram of a defect identifying apparatus according to some embodiments of the present application.
Fig. 2 is a characteristic diagram of a defect.
Fig. 3 is a schematic structural diagram of a defect identifying apparatus according to some embodiments of the present application.
Fig. 4 is a schematic view of another structure of a defect recognition apparatus according to some embodiments of the present application.
FIG. 5 is a schematic plan view of a display panel according to some embodiments of the present application.
FIG. 6 is a schematic flow chart diagram illustrating a defect identification method according to some embodiments.
FIG. 7 is a schematic flow chart diagram of a defect identification method according to some embodiments of the present application.
FIG. 8 is a schematic flow chart illustrating modeling and optimization of a defect identification model according to some embodiments of the present disclosure.
Reference numbers for the main elements of the drawings:
the defect recognition device 10, the first image acquisition unit 11, the defect detection unit 12, the second image acquisition unit 13, the defect recognition unit 14, the light source 15, the first light source 151, the second light source 152, the first stage 16, the guide rail 17, the first position a, the second position B, the preset position D, the second stage 18, and the conveyance unit 19.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and are only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As a novel display technology, an Active-matrix organic light-emitting diode (AMOLED) panel has the advantages of self-luminescence, wide viewing angle, high contrast, high color gamut, energy saving, ultrahigh corresponding rate, lightness, thinness, crimpability, and the like. The AMOLED panel has a wide application range.
Since the light emitting material of the AMOLED device is an organic material and is easily reacted with water vapor, oxygen, etc., the AMOLED device is easily rapidly aged, and thus the service life of the AMOLED device is affected, and therefore, the AMOLED device needs to be packaged.
Currently, most of the AMOLED devices are packaged by Thin Film Encapsulation (TFE) technology. The TFE technology can effectively prevent water vapor and oxygen from damaging organic luminescent materials in the AMOLED device, and the service life of the AMOLED device is prolonged. Generally, after the TFE process is completed, a U-lay film (U-lay) needs to be applied to the cut panel to ensure that the film and the panel are not separated when the panel is bent and to protect the panel from damage in the following processes. However, the U-Lami process is prone to defects such as foreign matters and scratches. The detection equipment in the existing production line is difficult to detect and accurately classify the defects on the flexible AMOLED panel.
In view of the above, please refer to fig. 1 and fig. 3, the present application provides a defect recognition apparatus 10 for a display panel, wherein the defect recognition apparatus 10 includes a first image capturing unit 11, a defect detecting unit 12, a second image capturing unit 13, and a defect recognizing unit 14. Defect identification unit 14 includes a processor and memory storing computer instructions for a defect identification model.
The first image acquisition unit 11 is configured to scan the display panel to obtain a feature image of the display panel, the defect detection unit 12 is configured to detect a defect coordinate of the display panel according to the feature image, the second image acquisition unit 13 is configured to shoot a local color image of a region corresponding to a position of the defect coordinate according to the defect coordinate, and the processor executes a computer instruction to implement identification of the local color image by using a defect identification model to obtain a defect type so as to classify the defect.
In the defect identification device 10, the display panel is scanned by the first image acquisition unit 11 to obtain a characteristic image of the display panel, the defect detection unit 12 detects the defect coordinate position of the display panel according to the characteristic image of the display panel, the second image acquisition unit 13 shoots a local color image of a corresponding area of the defect coordinate according to the detected defect coordinate, and finally the defect identification unit 14 identifies the local color image by using a preset defect identification model to obtain the defect type so as to classify the defects. Therefore, the defects generated by stabbing and foreign matters in the display panel can be accurately classified, the missing detection risk is reduced, the labor cost is saved, and the loss caused by the defects is reduced.
Specifically, the defect identifying apparatus 10 may be an Automated Optical Inspection (AOI) apparatus. An AOI device refers to a device that is based on optical principles to detect common defects encountered in production. When the AOI equipment is automatically detected, the characteristic image of the display panel can be obtained by automatically scanning through image acquisition units such as a camera and the like.
The first image acquisition unit 11 may include, but is not limited to, a line scan camera or an area scan camera. It will be understood by those skilled in the art that the line scan camera sensor is composed of only one line of photosensitive elements, and can perform high frequency scanning, and can also detect various high speed, rotating objects. Has the characteristics of low cost, high flexibility, wide dynamic range, high cost performance and the like. The surface scanning camera realizes pixel matrix shooting, the details of the image are not determined by the number of pixels but by the resolution, the resolution is determined by the focal length of the selected lens, and the same camera adopts lenses with different focal lengths, so that the resolutions are different.
For example, the first image capturing unit 11 may be a line scan camera, that is, the line scan camera can perform an omnidirectional scan on the display panel to obtain a line scan image of the display panel. In this way, the first image pickup unit 11 can detect the characteristic image of the display panel even when the display panel is in motion.
The defect recognition apparatus 10 may further include an image database, and the first image capturing unit 11 may store the detected feature image in the image database.
The defect detection unit 12 may be electrically connected to the first image capturing unit 11 to obtain the feature image detected by the first image capturing unit 11, or may directly obtain the feature image of the display panel from the image database.
The defect detecting unit 12 may perform detection based on the feature image to determine whether the display panel has a defect such as a puncture or a foreign object, and determine a position of the defect in the feature image when the display panel has the defect such as the puncture or the foreign object, wherein a defect center point may be used as a coordinate of the defect.
It is understood that if there is a defect such as a puncture or a foreign matter after the U-Lami process is performed on the display panel, the surface of the panel is not flat and the punctured portion is missing or lifted when the defect is a puncture. When the defect is a foreign object, a convex region is formed on the surface of the display panel. For example, please refer to FIG. 2, wherein FIG. 2(a) is a schematic plan view of puncture and foreign matter (particle) on Panel U-lami. FIG. 2(b) is a schematic cross-sectional view of puncture and foreign matter (particle) on Panel U-lami. When the defect is puncture, the surface of the panel is punctured by a hard object, so that the surface of the panel is not flat any more, and the punctured part is lost or jacked up and is shown as the surface is concave or convex upwards; and when a bad foreign matter (particle), the particle is attached to the surface of the panel, which forms a convex region. That is, when the defect of the feature image is clearly displayed. In this way, a good display panel and a defective display panel can be distinguished by the defect detection unit 12, so that the display panels can be preliminarily classified.
Since the feature image is a planar image and has a limited resolution, and the stab defect and the foreign object defect cannot be distinguished only by the feature image, in order to further confirm the defect for subsequent classification, the second image acquisition unit 13 may acquire a local image of the defect position in the display panel, so as to facilitate subsequent analysis according to the local image of the defect position, and determine whether the defect is a foreign object or a stab.
Specifically, the second image capturing unit 13 may include a high power lens, and the high power lens captures a partial color image at a preset magnification. The second image collecting unit 13 can adjust the high power lens according to the coordinates of the defect, so that the high power lens is aligned to a corresponding area of the display panel where the coordinates of the defect are located, and the high power lens can shoot a local color image with a preset magnification to obtain an image of the defect position. The preset magnification factor may be 50 times, 80 times, 100 times, 150 times, 200 times or even more, that is, the specific value of the preset magnification factor is not limited, and may be set according to the size of the display panel. Therefore, the defect can be conveniently analyzed according to the local color image of the defect, so that the defect is confirmed to be a puncture wound or a foreign body.
In some embodiments, there may be one or more second image capturing units 13. For example, in some embodiments, the second image capturing unit 13 may be plural. It can be understood that the display panel may have a plurality of defects distributed in different regions, and the second image capturing unit 13 captures a local image with a preset magnification, and the area of the captured region is limited, so that the plurality of second image capturing units 13 can simultaneously align to different defects, thereby obtaining a plurality of local color images simultaneously and improving the detection efficiency.
Further, it is understood that it is inefficient if the type of the defect is identified by artificially identifying the local color image, and therefore, the defect type may be identified by the processor of the defect identification unit 14 executing computer instructions to identify the local color image using a defect identification model to classify the defect.
It should be noted that the defect identification model is a mathematical model for detecting and judging defects of a local color image of the display panel, and the detection model can be established according to preset logic and a mathematical algorithm. The preset logic is a business logic, which refers to rules and processes that one entity unit should have in order to provide services to another entity unit. The mathematical algorithm may be a deep learning network algorithm based on a Feature Pyramid Network (FPN).
The characteristic diagram pyramid network mainly solves the multi-scale problem in object detection, and greatly improves the performance of small object detection under the condition of basically not increasing the calculated amount of an original model through simple network connection change.
In some embodiments, in order to enable a relevant person to visually see the classification result of the detected display panel, the obtained classification result may be marked, and the marked classification result may be displayed. Therefore, related personnel can monitor the specific adverse phenomena of the display panel, so that the problems can be quickly found and timely improved according to the specific adverse phenomena, and the quality and capacity influence caused by the adverse occurrence is reduced.
Referring to fig. 3, in some embodiments, the defect recognition apparatus 10 includes a light source, the light source is configured to emit detection light to the display panel, the first image capturing unit 11 is configured to receive the detection light passing through the display panel to obtain a characteristic image through scanning, and the second image capturing unit 13 is specifically configured to receive the detection light passing through a region corresponding to a position of a defect coordinate in the display panel to obtain a local color image.
In this way, by illuminating the display panel with the light source, the defects in the feature image scanned by the first image capturing unit 11 and the local color image obtained by the second image capturing unit 13 can be made more obvious, which is beneficial to distinguishing the defects. The detection accuracy is improved.
Referring further to fig. 3, in some embodiments, the defect recognition apparatus 10 includes a first stage 16 and a guide rail 17, the first stage 16 is used for carrying and fixing the display panel, the light source is used for emitting detection light to the display panel on the first stage 16, and the guide rail 17 is used for moving the first image capturing unit 11 from the first position a to the preset position D, so as to scan the display panel for the feature image, and moving the first image capturing unit 11 from the preset position D to the first position a. The guide rail 17 is also used for moving the second image pickup unit 13 from the second position B to the preset position D to pick up the display panel for a partial color image, and for moving the second image pickup unit 13 from the preset position D to the second position B.
In the present embodiment, the display panel is fixed to the first stage 16 by a suction cup, and the position, light intensity, and incident angle of the light source 15 can be adjusted. The preset position D is a shooting position, and is located on a light path of the detection light emitted by the light source.
Specifically, in the process of detecting and classifying the display panels, the display panels are placed on the first stage 16, the light source 15 is started to emit detection light to the display panels along the light path, meanwhile, the first image acquisition unit 11 is moved from the first position a of the guide rail 17 to the preset position D of the guide rail 17, the detection light passing through the display panels on the first stage 16 is received by the first image acquisition unit 11, and the characteristic images of the display panels are obtained by scanning the display panels. Further, after the first image capturing unit 11 receives the characteristic image of the display panel, the first image capturing unit 11 is moved from the preset position D of the guide rail 17 to the first position a of the guide rail 17, so that the first image capturing unit 11 is returned, and then the second image capturing unit 13 is transferred from the second position B of the guide rail 17 to the preset position D of the guide rail 17 through the guide rail 17. So that the second image collecting unit 13 can receive the detection light passing through the display panel on the second stage 18 to obtain a local color image of the area corresponding to the position of the defect coordinate.
In this way, by moving the settings of the first image capturing unit 11 and the second image capturing unit 13, it is realized that the characteristic image and the partial color image of the display panel can be acquired with the display panel fixed.
Referring to fig. 4, in some embodiments, the defect recognition apparatus 10 includes a first stage 16, a second stage 18, and a transmission unit 19 and/or a manipulator connecting the first stage 16 and the second stage 18, the light source 15 includes a first light source 151 and a second light source 152, the first stage 16 is used for carrying and fixing a display panel, the first light source 151 is used for emitting detection light from the display panel on the first stage 16, the first image collection unit 11 is used for receiving the detection light passing through the display panel on the first stage 16 to obtain a characteristic image of the display panel, the transmission unit 19 is used for transmitting the display panel on the first stage 16 to the second stage 18, the second stage 18 is used for carrying and fixing the display panel transmitted by the first stage 16, the second light source 152 is used for emitting detection light to the display panel on the second stage 18, the second image collection unit 13 is used for receiving the detection light passing through the display panel on the second stage 18, to obtain a partial color image of the display panel.
Specifically, the first stage 16, the transfer unit 19, and the second stage 18 are arranged in this order, the first light source 151 and the first image capturing unit 11 are arranged above the first stage 16 at intervals, and the first image capturing unit 11 is located on the optical path of the detection light emitted from the first light source 151. A second light source 152 and a second image collecting unit 13 are arranged above the second stage 18 at intervals, and the second image collecting unit 13 is located on the optical path of the detection light emitted by the second light source 152.
In the process of detecting and classifying the display panels, the display panels are placed on the first stage 16, the first light source 151 is turned on, the first light source 151 emits detection light to the display panels on the first stage 16, and meanwhile, the first image acquisition unit 11 receives the detection light passing through the display panels on the first stage 16 to obtain the characteristic images of the display panels. After the first image capturing unit 11 receives the characteristic image of the display panel, the transfer unit 19 and/or the manipulator are/is started, and the display panel is transferred to the second stage 18 through the transfer unit 19 and/or the manipulator. Further, after the display panel is conveyed to the second stage 18, the second light source 152 is turned on to send the detection light to the display panel on the second stage 18, and at the same time, the second image capturing unit 13 receives the detection light passing through the display panel on the second stage 18 to capture the display panel, so as to obtain a local color image.
In this way, by moving the display panel, it is realized that the characteristic image and the partial color image of the display panel can be acquired with the first image capturing unit 11 and the second image capturing unit 13 fixed.
In certain embodiments, the processor of defect identification unit 14 executes computer instructions to implement training of the defect identification model by obtaining classified local color images.
It can be understood that the more classified local color images, the more accurate the result obtained by training the defect recognition model. Therefore, in the present embodiment, each type of partial color image may be larger than 200 sheets. For example, each type of partial color image may be 300 sheets.
Specifically, the defect identification model may include a plurality of defect identification models, each corresponding to a type of local color image, for example, the defect identification model includes a foreign object identification model and a puncture identification model, the local color image includes a puncture local color image and a foreign object local color image, wherein the foreign object identification model is used for performing test training on the foreign object local color image, and the puncture identification model is used for performing test training on the puncture local color image. And comparing the obtained training detection result with the actual detection result, and continuously adjusting and optimizing the defect identification model to enable the training detection result to be close to the actual detection result. And when the accuracy and the over-inspection rate of the training detection result reach the standards, the defect identification model can be considered to reach the standards, and the defect identification can be carried out on the trained defect identification model.
In some embodiments, the display panel is provided with markers, and the defect detection unit 12 determines the defect coordinates of the display panel based on the positions of the markers in the feature image.
Referring to fig. 5, in particular, the display panel may be divided into a display area and a wiring area, wherein the edges of the display area and the wiring area are provided with partition marks. The defect detecting unit 12 may determine whether the defect is in the display area or the wiring area according to the mark in the feature image, and may further determine the specific coordinate where the defect exists according to the mark in the feature image.
For example, in some examples, the defect detection unit 12 may establish a rectangular plane coordinate system for the origin based on any one of the markers in the feature image, and then determine the coordinates of the defect in the display panel based on the relative position of the defect to the origin of coordinates.
In some embodiments, the defect detecting unit 12 further divides the feature image by the mark in the feature image to obtain the feature image of the display area and the feature image of the wiring area, and then detects the defect in the feature image of the display area and the defect in the feature image of the wiring area respectively. Therefore, the characteristic images are divided, and then the defect detection is respectively carried out on the characteristic images of the display area and the characteristic images of the wiring area, so that the detection accuracy of the defect identification model can be improved subsequently.
Referring to fig. 6, an embodiment of the present application provides a defect recognition method for a display panel, which is applied to the defect recognition apparatus 10 of any one of the above embodiments, and the defect recognition method includes the steps of:
01, scanning the display panel to obtain a characteristic image of the display panel;
02, measuring the defect coordinates of the display panel according to the characteristic image;
03, shooting a local color image of a region corresponding to the position of the defect coordinate according to the defect coordinate; and
and 04, identifying the local color image by using a defect identification model to obtain a defect type so as to classify the defect.
The embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the defect identification method may be implemented by the processor of the electronic device.
Or the processor is used for scanning the display panel to obtain a characteristic image of the display panel and determining the defect coordinates of the display panel according to the characteristic image, and the processor is also used for shooting a local color image of a region corresponding to the position of the defect coordinates according to the defect coordinates and identifying the local color image by using a defect identification model to obtain the defect type so as to classify the defects.
In the defect identification method and the electronic device for the display panel, the display panel is scanned through the first image acquisition unit to obtain the characteristic image of the display panel, the defect detection unit can determine the defect coordinate position of the display panel according to the characteristic image of the display panel, the second image acquisition unit shoots the local color image of the corresponding area of the defect coordinate according to the detected defect coordinate, and finally the defect identification unit identifies the local color image by using the preset defect identification model to obtain the defect type so as to classify the defects. Therefore, the defects generated by stabbing and foreign matters in the display panel can be accurately classified, the missing detection risk is reduced, the labor cost is saved, and the loss caused by the defects is reduced.
In some embodiments, the electronic device may be a server, and the server may be in communication with a defect recognition apparatus for detecting the display panel. Thereby acquiring a characteristic image of the display panel from the defect recognition device. The server can comprise a big data platform, and the big data platform is a platform integrating data access, data processing, data storage, query retrieval, analysis mining and the like, an application interface and the like, so that the electronic equipment can realize the defect identification method of the embodiment of the application.
In addition, in other embodiments, the processor can also generate a defect fluctuation notice according to the classification result and send the defect fluctuation notice to inform related personnel. For example, a large number of panels with stabbing defects appear, so that related personnel can conveniently and quickly check and analyze the panels, and the notification mode can be short message notification, telephone notification, mail notification and the like. For example, after the defect fluctuation is monitored, the process management personnel can be reminded and notified in a mail mode and a real-time alarm mode, so that the process management personnel can quickly check and analyze details according to the mail, and problems can be found and improved in time.
Referring to fig. 7, in some embodiments, the display panel is provided with a logo, and step 02 includes the sub-steps of:
021, determining the defect coordinates of the display panel according to the positions of the marks in the characteristic image.
In some embodiments, the processor may be configured to determine the defect coordinates of the display panel based on the locations of the markers in the feature image.
Therefore, the defect coordinate of the display panel is determined through the position of the mark in the characteristic image, and the efficiency of determining the defect coordinate is improved.
Referring to fig. 8, in some embodiments, before step 01, the defect detection method further includes the steps of:
001, establishing an algorithm model aiming at the defect type to be detected;
002, training the algorithm model by using a training image, wherein the training image comprises a classified local color image;
003, detecting the verification image by using the trained algorithm model to obtain a verification detection result so as to optimize the algorithm model;
004, repeating the training steps, and determining that the algorithm model is trained to be used as a defect identification model under the condition that the accuracy of the detection result reaches a preset value.
In some embodiments, the processor is further configured to establish an algorithm model for the defect type to be detected, train the algorithm model by using a training image, the training image including the classified local color images, detect the verification image by using the trained algorithm model to obtain a verification detection result so as to optimize the algorithm model, and finally repeat the training step.
In particular, the types of defects to be detected may include puncture defects, foreign body defects.
The algorithm model may include a plurality of algorithm models, each corresponding to a defect type, and the training image may be divided into two types of partial color images, i.e., a partial color image in which a puncture is present and a partial color image in which a foreign object is present. That is, the two types of local color images are used for training the corresponding algorithm models respectively, and the trained algorithm models are used for detecting the verification images to obtain the verification detection results so as to optimize the algorithm models. And under the condition that the accuracy of the detection result reaches a preset value, determining that the algorithm model is trained to be used as a defect identification model.
The training detection result obtained by training the algorithm model through the training image is compared with the actual detection result, so that the optimization algorithm model is continuously adjusted, the training detection result is close to the actual detection result, when the accuracy and the over-detection rate of the training detection result reach the standard, the algorithm model can be considered to reach the standard, and the trained algorithm model can be used as a defect identification model to carry out defect detection.
Therefore, the algorithm model can be trained by utilizing the training image and the training recognition result to obtain a trained defect recognition model, and the trained defect recognition model can be obtained according to the defect detection module.
The present application further provides a non-transitory computer-readable storage medium containing a computer program, and when the computer program is executed by a processor, the processor is enabled to execute the defect identification method of any of the above embodiments.
In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware or any other combination. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Video Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (13)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111362477.0A CN113888533A (en) | 2021-11-17 | 2021-11-17 | Display panel defect identification device, method, electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111362477.0A CN113888533A (en) | 2021-11-17 | 2021-11-17 | Display panel defect identification device, method, electronic device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113888533A true CN113888533A (en) | 2022-01-04 |
Family
ID=79018148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111362477.0A Pending CN113888533A (en) | 2021-11-17 | 2021-11-17 | Display panel defect identification device, method, electronic device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888533A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115326705A (en) * | 2022-07-22 | 2022-11-11 | 成都中嘉微视科技有限公司 | A four-way and back panel defect detection method |
| CN115564755A (en) * | 2022-10-24 | 2023-01-03 | 珠海格力电器股份有限公司 | Method, device and system for detecting single component of PCB board |
| CN116167992A (en) * | 2023-02-02 | 2023-05-26 | 北京百度网讯科技有限公司 | Defect detection method, defect detection device, electronic device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
| WO2021010430A1 (en) * | 2019-07-16 | 2021-01-21 | 株式会社テクムズ | Method for detecting defect of item to be inspected, device therefor, and computer program therefor |
| JP2021032894A (en) * | 2019-08-16 | 2021-03-01 | ラオンピープル株式会社 | Substrate defect inspection device and method |
| CN113176276A (en) * | 2021-03-19 | 2021-07-27 | 哈工大机器人(中山)无人装备与人工智能研究院 | Panel defect detection equipment and panel defect detection method |
| CN113222913A (en) * | 2021-04-28 | 2021-08-06 | 南京南瑞继保电气有限公司 | Circuit board defect detection positioning method and device and storage medium |
-
2021
- 2021-11-17 CN CN202111362477.0A patent/CN113888533A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
| WO2021010430A1 (en) * | 2019-07-16 | 2021-01-21 | 株式会社テクムズ | Method for detecting defect of item to be inspected, device therefor, and computer program therefor |
| JP2021032894A (en) * | 2019-08-16 | 2021-03-01 | ラオンピープル株式会社 | Substrate defect inspection device and method |
| CN113176276A (en) * | 2021-03-19 | 2021-07-27 | 哈工大机器人(中山)无人装备与人工智能研究院 | Panel defect detection equipment and panel defect detection method |
| CN113222913A (en) * | 2021-04-28 | 2021-08-06 | 南京南瑞继保电气有限公司 | Circuit board defect detection positioning method and device and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115326705A (en) * | 2022-07-22 | 2022-11-11 | 成都中嘉微视科技有限公司 | A four-way and back panel defect detection method |
| CN115564755A (en) * | 2022-10-24 | 2023-01-03 | 珠海格力电器股份有限公司 | Method, device and system for detecting single component of PCB board |
| CN116167992A (en) * | 2023-02-02 | 2023-05-26 | 北京百度网讯科技有限公司 | Defect detection method, defect detection device, electronic device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12020417B2 (en) | Method and system for classifying defects in wafer using wafer-defect images, based on deep learning | |
| CN113888533A (en) | Display panel defect identification device, method, electronic device and medium | |
| US10733723B2 (en) | Methods and system for improved quality inspection | |
| US10706525B2 (en) | Methods and systems for improved quality inspection | |
| CN108686978B (en) | ARM-based fruit category and color sorting method and system | |
| CN113111903B (en) | Intelligent production line monitoring system and monitoring method | |
| US20250069091A1 (en) | Identifying and grading system and related methods for collectible items | |
| CN117893817A (en) | Wafer defect classification method, device and system thereof, electronic equipment and storage medium | |
| CN112053318A (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
| CN111612757A (en) | Screen crack detection method, device, equipment and storage medium | |
| CN110569841A (en) | Object detection method for key components of catenary based on convolutional neural network | |
| US20230152781A1 (en) | Manufacturing intelligence service system connected to mes in smart factory | |
| CN115266757A (en) | Defect detection apparatus and method | |
| CN113030095B (en) | A polarizer appearance defect detection system | |
| CN111079831A (en) | Intelligent optical detection sample characteristic and flaw automatic marking method and device | |
| US11176419B1 (en) | Method for labeling image | |
| CN116664491A (en) | Soft film circuit board defect detection method and related device | |
| CN115165925A (en) | PCB detection device with marking function, marking method, equipment and medium | |
| CN110929755A (en) | Poultry egg detection method, device and system, electronic equipment and storage medium | |
| CN116894832B (en) | Method, system, equipment and storage medium for detecting bottleneck cracks of milk glass bottle | |
| CN112964723A (en) | Double-sided multi-target equal-spacing array visual detection method and detection system | |
| CN116840244A (en) | Software and hardware coordinated packaged chip detection device and method and electronic equipment | |
| CN117288756A (en) | Product defect detection method and system | |
| CN114332017A (en) | Wafer control detection method and device | |
| CN112149660A (en) | Gun recognition system |
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 |