CN118015340A - Method and device for detecting defects of light guide plate and storable medium - Google Patents
Method and device for detecting defects of light guide plate and storable medium Download PDFInfo
- Publication number
- CN118015340A CN118015340A CN202410061573.9A CN202410061573A CN118015340A CN 118015340 A CN118015340 A CN 118015340A CN 202410061573 A CN202410061573 A CN 202410061573A CN 118015340 A CN118015340 A CN 118015340A
- Authority
- CN
- China
- Prior art keywords
- model
- light guide
- guide plate
- detected
- image
- 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 84
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims description 27
- 238000003062 neural network model Methods 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000010200 validation analysis Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000004075 alteration Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 14
- 238000004519 manufacturing process Methods 0.000 description 9
- 239000004973 liquid crystal related substance Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 241000519995 Stachys sylvatica Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000010408 film Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000012788 optical film Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method, a device and a storage medium for detecting defects of a light guide plate, wherein the method comprises the steps of obtaining an image to be detected of the light guide plate to be detected, and processing the image to be detected to form complete image data of the light guide plate to be detected; inputting the complete image data into a preset AI algorithm for detection; the AI algorithm outputs a first detection result; and performing secondary repeated judgment on the product judged to be unqualified in the first detection result, and forming a second detection result. The AI algorithm is adopted to detect the defects of the light guide plate, so that the defects of the light guide plate are detected rapidly and accurately, the product delivery quality is effectively improved, the product consistency is improved, the frequency of manual re-judgment is reduced, the product is prevented from being polluted by secondary pollution, and meanwhile, the labor cost is saved.
Description
Technical Field
The present invention relates to the field of visual inspection technologies, and in particular, to a method and an apparatus for inspecting defects of a light guide plate, and a storable medium.
Background
The light guide plate is used as a transparent flat plate behind the liquid crystal display screen, and can convert a linear light source into a surface light source, so that the liquid crystal display screen is uniformly lightened, and the light guide plate is applied to display modules of various electronic devices at present. The liquid crystal does not emit light, and a backlight module capable of mapping out the illumination source is additionally arranged behind the liquid crystal so as to clearly display the display content, so that the backlight module is also one of important components of the liquid crystal panel. The backlight module is mainly composed of an illumination source, a light guide plate, an optical film and other mechanism components.
In the great background of rapid development of the current electronic product manufacturing industry, the light guide plate has become the display member foundation of a plurality of highly intelligent and informationized electronic products, and the products play a very key role in daily life and development of each product at the upstream and downstream of the daily life. Therefore, the defect detection of the light guide plate is particularly important. The defect detection of the front light guide plate is in a state of manual visual detection, and the manual detection is to observe defects through human eyes after being irradiated by a proper high-brightness light source under a dark factory dust-free environment, so that the defects are always in a two-shift mode, and the human eyes are easy to fatigue and damage vision after long-time work. The machine vision technology is applied to the defect detection of the light guide plate, so that the labor intensity of workers can be reduced, the reliability of detection results can be improved, the production efficiency can be improved, and labor force can be liberated from a large number of complex and repeated working environments.
However, in the existing visual detection, a shot image is converted into a gray level image, and the gray level difference of a defect and a background is detected to grasp the defect range, so that when the method detects the defect of the light guide plate, certain limitations exist, such as the defects of unobvious contrast and small defect size, and the problems of omission and the like exist; for irregular defects, there are problems such as incomplete grabbing.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a method, a device and a storable medium for detecting the defects of a light guide plate, which adopt an AI algorithm to detect the defects of the light guide plate, so as to rapidly and accurately detect the defects of the light guide plate, effectively improve the outgoing quality of products, improve the consistency of the products, reduce the frequency of manual re-judgment, avoid secondary pollution of the products and save the labor cost.
In order to achieve the above purpose, the invention adopts the following technical scheme: the method for detecting the defects of the light guide plate comprises the following steps:
obtaining an image to be detected of the light guide plate to be detected, and processing the image to be detected to form complete image data of the light guide plate to be detected;
inputting the complete image data into a preset AI algorithm for detection;
the AI algorithm outputs a first detection result;
And performing secondary repeated judgment on the product judged to be unqualified in the first detection result, and forming a second detection result.
The invention has the beneficial effects that: and the AI algorithm is adopted to detect the defects of the light guide plate, so that the defects of the light guide plate are detected rapidly and accurately, the quality of products leaving factories is improved effectively, and the consistency of the products is improved. After primary detection is performed by the AI algorithm, secondary repeated judgment is added, the workload of the secondary repeated judgment is greatly reduced, and the detection accuracy can be improved.
Further, the AI algorithm specifically includes:
collecting a sample set comprising an image containing a defect and an image not containing a defect;
extracting characteristics, analyzing defect types, and marking defects on images in the sample set;
model training, namely outputting the image marked with the defects to a preset neural network model for training to obtain an initial AI model;
model evaluation and optimization, verifying the initial AI model using the verification data set, and optimizing the initial AI model according to the verification result to form a test AI model;
and the test AI model is used for completing the processing and detection of the image data.
The test AI model finally generated is more accurate and has better effect.
Further, the verifying the initial AI model using the verification data set specifically includes:
Outputting the verification data set into an initial AI model, and outputting a verification result, wherein the verification data set is an image marked with defects and not participating in training;
comparing the verification result with the marked defects in the verification data set;
And if the initial AI model is consistent, verifying the initial AI model to be qualified, otherwise, optimizing the initial AI model.
Further, outputting the image marked with the defect to a preset neural network model for training, and obtaining an initial AI model specifically includes:
The method comprises the steps of constructing a network, selecting a neural network model, wherein the neural network model comprises an input layer, a hidden layer and an output layer, and determining the node number and an activation function of each layer;
selecting a loss function, namely selecting the loss function to measure the difference between the prediction result of the model and the real label according to the type of the defect and the characteristics of the defect;
initializing parameters of the neural network model;
And forward transmission, namely forward transmission is carried out on the input data through the neural network, so that a prediction result of the neural network model is obtained.
Calculating loss, comparing the predicted result with a real label, and calculating the value of a loss function;
counter-propagating, namely calculating the gradient of the neural network model parameters through a counter-propagating algorithm according to the value of the loss function;
Updating parameters, namely updating parameters of the neural network model according to gradients of the parameters by using an optimization algorithm;
and repeating the iteration, and repeating the processes of forward propagation, calculation loss, reverse propagation and parameter updating until a preset stopping condition is reached to form an initial AI model.
Further, the AI algorithm also includes monitoring and maintenance, periodically monitoring and periodically training the performance of the test AI model. And updating the verification data periodically, and if the test result does not meet the production requirement, carrying out analysis optimization on all samples in the period so as to meet the production requirement.
Further, after optimizing the initial AI model, the validation data set is again used to validate until validation passes, forming a test AI model. Training is continued until the test AI model is fixed.
Further, the light guide plate at least collects two images to be measured, and the processing of the images to be measured to form the complete image data of the light guide plate to be measured specifically includes:
image preprocessing, namely correcting chromatic aberration of the image to be detected, reducing distortion of the image to be detected, and aligning all the images to be detected of the same light guide plate;
And splicing the images, extracting characteristic points of the images to be detected, and splicing the images to be detected to form complete image data.
Because the area of the light guide plate body is large, a single image to be detected is insufficient to cover the whole light guide plate to be detected, so that images to be detected are obtained by shooting different positions of the light guide plate to be detected, and the complete image data of the complete light guide plate to be detected is obtained through processing the images to be detected. It is ensured that there is an overlapping portion of the two images to be measured and that the same focal length, lighting conditions and settings are used to ensure continuity between the two images to be measured.
The invention also discloses a device for detecting the defect of the light guide plate, which comprises:
the acquisition module is used for acquiring an image to be detected of the light guide plate to be detected;
and the controller is used for receiving the image to be detected and adopting the detection method.
The invention also discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program realizes the detection method when being executed by a processor.
Drawings
FIG. 1 is a flowchart showing a first embodiment of the present invention;
FIG. 2 is a flow chart II of a first embodiment of the present invention;
FIG. 3 is a block diagram of a second embodiment of the present invention;
fig. 4 is a comparison diagram of the conventional algorithm and the AI algorithm of the present embodiment for processing the complete image data.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making clear and defining the scope of the present invention.
Example 1
Referring to fig. 1, the method for detecting defects of a light guide plate is used for detecting defects of the light guide plate, and the defect types comprise white spots, scratches and film drawing. The detection method comprises the following steps:
And 100, acquiring an image to be detected of the light guide plate to be detected, and processing the image to be detected to form complete image data of the light guide plate to be detected.
The image to be measured is obtained by photographing through the CCD cameras, and because the area of the light guide plate is large, the single CCD camera is insufficient to cover the whole light guide plate to be measured, two CCD cameras are arranged, the image to be measured is obtained by photographing different positions of the light guide plate to be measured, and the whole image data of the whole light guide plate to be measured is obtained through the image processing to be measured. It is to be ensured that the two CCD cameras take images with overlapping portions and that the same focal length, lighting conditions and settings are used to ensure continuity between the two images to be measured.
The CCD cameras can be three, the number of the CCD cameras is determined according to the size of the light guide plate to be detected, and all images to be detected of one light guide plate to be detected can be spliced into one complete image data.
Processing the image to be detected to form complete image data of the light guide plate to be detected specifically comprises:
And (5) preprocessing an image. Some pre-processing of the images to be measured is typically required before they are stitched. The preprocessing comprises correcting chromatic aberration of the image to be detected, reducing distortion of the image to be detected, and aligning all the images to be detected of the same light guide plate. The images to be measured are aligned so that they are in the same coordinate system.
And splicing the images, extracting characteristic points of the images to be detected, and splicing the images to be detected to form complete image data. The feature points include corner points, edges and the like, and the extraction of the feature points is the prior art and will not be described here.
And 200, inputting the complete image data into a preset AI algorithm for detection.
The AI algorithm has the advantages of shorter detection time, higher detection efficiency, more accurate and objective capturing of defects, greatly reduced misjudgment and missed detection, and improved customer production quality.
And 300, outputting a first detection result by the AI algorithm.
The first detection result is unqualified product data and qualified products, wherein the unqualified product data comprises defect types of the unqualified products.
And 400, performing secondary repeated judgment on the product judged to be unqualified in the first detection result, and forming a second detection result.
The light guide plate to be tested, which is judged to be an unqualified product, may have a false judgment, so that the light guide plates to be tested are subjected to secondary judgment, and the light guide plate to be tested, which is judged to be unqualified in the secondary judgment, is judged to be an unqualified product. The secondary re-judgment adopts manual re-judgment and is checked manually. However, since the AI algorithm has been performed once in step 200 and step 300, the workload of manual re-judgment is greatly reduced, but the accuracy of detection can be improved.
Referring to fig. 4, for the same defect type, the graph obtained by processing the conventional detection and the detection method in this embodiment is a graph comparing the graph, where fig. 4 (a) is a graph of the effect of the conventional algorithm on the image to be detected, and fig. 4 (a) is a graph of the effect of the AI algorithm on the image to be detected in this embodiment. In this embodiment, the conventional algorithm cannot detect a slight defect, and the AI can be detected more clearly.
Referring to fig. 2, the AI algorithm specifically includes:
Step 11, collecting a sample set, wherein the sample set comprises images containing defects and images not containing defects.
In this step, an image containing the defect and an image not containing the defect can be photographed by a CCD camera.
And 12, extracting the characteristics, analyzing the defect types, and marking the defects of the images in the sample set.
When the images in the sample set are marked with defects, manual operation is adopted, namely the defect areas and defect types on the images are marked manually.
And 13, training the model, namely outputting the image marked with the defect to a preset neural network model for training, and obtaining an initial AI model.
And (3) putting the image marked with the defects into AI software for training, extracting defect characteristics (color, shape, background, brightness, characteristics and the like), and ensuring that the AI model can detect and position the defects. The method specifically comprises the following steps:
And (3) constructing a network, selecting a neural network model, wherein the neural network model comprises an input layer, a hidden layer and an output layer, and determining the node number and the activation function of each layer. The structure and parameter settings of the network directly affect the performance of the model.
And selecting a loss function, namely selecting the loss function to measure the difference between the predicted result of the model and the real label according to the type of the defect and the characteristics of the defect. Common loss functions include mean square error, cross entropy, etc.
And initializing parameters of the neural network model. Random initialization methods are typically used to avoid model sinking to locally optimal solutions.
And forward transmission, namely forward transmission is carried out on the input data through the neural network, so that a prediction result of the neural network model is obtained.
And calculating the loss, comparing the predicted result with the real label, and calculating the value of the loss function.
Back propagation, the gradient of the neural network model parameters is calculated by a back propagation algorithm (e.g., gradient descent) based on the value of the loss function.
Updating parameters, namely updating parameters of the neural network model according to gradients of the parameters by using an optimization algorithm;
And repeating the iteration, and repeating the processes of forward propagation, calculation loss, reverse propagation and parameter updating until a preset stopping condition is reached to form an initial AI model. Stop conditions such as maximum number of iterations reached or loss function convergence, etc.
Step 14, model evaluation and optimization, using the verification data set to verify the initial AI model, and optimizing the initial AI model according to the verification result to form the test AI model.
The verification data set is an atlas with known defects and without participating in training, namely, the initial AI model needs to be optimized to be good in effect to form a test AI model, and the test AI model can be applied to the defect detection of the light guide plate, otherwise, the training is repeated until the model evaluation passes.
The verifying the initial AI model using the verification data set specifically includes:
Outputting the verification data set into an initial AI model, and outputting a verification result;
comparing the verification result with the marked defects in the verification data set;
And if the initial AI model is consistent, verifying the initial AI model to be qualified, otherwise, optimizing the initial AI model.
After optimizing the initial AI model, the validation data set is again used to validate until validation passes, forming a test AI model.
And evaluating the initial AI model obtained through training by using the verification data, and calculating indexes such as the accuracy, the precision, the recall rate and the like of the initial AI model so as to evaluate the performance of the initial AI model. If the production requirement is not met, according to the evaluation result of the initial AI model, super parameters such as a network structure, a loss function, a learning rate and the like are adjusted so as to further improve the performance of the model, and the model is tested again after being generated, so that the model OK is ensured, and the production quality is ensured.
And 15, deploying a model, wherein the test AI model is used for completing the processing and detection of the image data.
The AI algorithm also includes monitoring and maintenance, periodically monitoring and periodically training the performance of the test AI model.
And updating the verification data periodically, and if the test result does not meet the production requirement, carrying out analysis optimization on all samples in the period so as to meet the production requirement.
In the embodiment, the conventional manual visual inspection is improved, and the defect of the light guide plate is detected by adopting an AI algorithm, so that the defect of the light guide plate is detected rapidly and accurately: white spots, scratches and film drawing; the product delivery quality is effectively improved, and the product consistency is improved; the frequency of manual repeated judgment is reduced, the secondary pollution of the product is avoided, and the labor cost is saved.
Example two
Referring to fig. 3, a device for detecting defects of a light guide plate includes an acquisition module and a controller.
The acquisition module is used for acquiring an image to be detected of the light guide plate to be detected. The acquisition module comprises two CCD cameras, the two CCD cameras shoot different positions of the light guide plate to be detected to form images to be detected, and the images to be detected are overlapped.
And the controller is used for receiving the image to be detected and adopting the detection method of the first embodiment.
The controller outputs a first detection result, carries out manual re-judgment according to the first detection result, and finally produces a second detection result.
Example III
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a detection method as described above.
In summary, compared with the traditional algorithm, the method, the device and the storable medium for detecting the defects of the light guide plate provided by the invention have the advantages that the AI algorithm is adopted to detect the defects of the light guide plate, so that the defects of the light guide plate are rapidly and accurately detected, the outgoing quality of products is effectively improved, the consistency of the products is improved, the frequency of manual re-judgment is reduced, the secondary pollution of the products is avoided, and the labor cost is saved.
In the foregoing embodiments of the present application, it should be understood that the disclosed method, apparatus, computer readable storage medium and electronic device may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple components or modules may be combined or integrated into another apparatus, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with respect to each other may be an indirect coupling or communication connection via some interfaces, devices or components or modules, which may be in electrical, mechanical, or other forms.
The integrated modules, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present invention is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the present invention.
The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and to implement the same, but are not intended to limit the scope of the present invention, and all equivalent changes or modifications made according to the spirit of the present invention should be included in the scope of the present invention.
Claims (9)
1. The detection method of the defect of the light guide plate is characterized by comprising the following steps: the method comprises the following steps:
obtaining an image to be detected of the light guide plate to be detected, and processing the image to be detected to form complete image data of the light guide plate to be detected;
inputting the complete image data into a preset AI algorithm for detection;
the AI algorithm outputs a first detection result;
And performing secondary repeated judgment on the product judged to be unqualified in the first detection result, and forming a second detection result.
2. The method for detecting defects of a light guide plate according to claim 1, wherein: the AI algorithm specifically comprises:
collecting a sample set comprising an image containing a defect and an image not containing a defect;
extracting characteristics, analyzing defect types, and marking defects on images in the sample set;
model training, namely outputting the image marked with the defects to a preset neural network model for training to obtain an initial AI model;
model evaluation and optimization, verifying the initial AI model using the verification data set, and optimizing the initial AI model according to the verification result to form a test AI model;
and the test AI model is used for completing the processing and detection of the image data.
3. The method for detecting defects of a light guide plate according to claim 2, wherein: the verifying the initial AI model using the verification data set specifically includes:
Outputting the verification data set into an initial AI model, and outputting a verification result, wherein the verification data set is an image marked with defects and not participating in training;
comparing the verification result with the marked defects in the verification data set;
And if the initial AI model is consistent, verifying the initial AI model to be qualified, otherwise, optimizing the initial AI model.
4. The method for detecting defects of a light guide plate according to claim 2, wherein: outputting the image marked with the defects to a preset neural network model for training, wherein the obtaining of an initial AI model specifically comprises the following steps:
The method comprises the steps of constructing a network, selecting a neural network model, wherein the neural network model comprises an input layer, a hidden layer and an output layer, and determining the node number and an activation function of each layer;
selecting a loss function, namely selecting the loss function to measure the difference between the prediction result of the model and the real label according to the type of the defect and the characteristics of the defect;
initializing parameters of the neural network model;
Forward propagation, namely forward propagation is carried out on input data through the neural network to obtain a prediction result of a neural network model;
calculating loss, comparing the predicted result with a real label, and calculating the value of a loss function;
counter-propagating, namely calculating the gradient of the neural network model parameters through a counter-propagating algorithm according to the value of the loss function;
Updating parameters, namely updating parameters of the neural network model according to gradients of the parameters by using an optimization algorithm;
and repeating the iteration, and repeating the processes of forward propagation, calculation loss, reverse propagation and parameter updating until a preset stopping condition is reached to form an initial AI model.
5. The method for detecting defects of a light guide plate according to claim 2, wherein: the AI algorithm also includes monitoring and maintenance, periodically monitoring and periodically training the performance of the test AI model.
6. The method for detecting defects of a light guide plate according to claim 1, wherein: after optimizing the initial AI model, the validation data set is again used to validate until validation passes, forming a test AI model.
7. The method for detecting defects of a light guide plate according to any one of claims 1 to 6, wherein: the method for processing the images to be detected to form the complete image data of the light guide plate to be detected specifically comprises the following steps:
image preprocessing, namely correcting chromatic aberration of the image to be detected, reducing distortion of the image to be detected, and aligning all the images to be detected of the same light guide plate;
And splicing the images, extracting characteristic points of the images to be detected, and splicing the images to be detected to form complete image data.
8. The utility model provides a detection device of light guide plate defect which characterized in that: comprising the following steps:
the acquisition module is used for acquiring an image to be detected of the light guide plate to be detected;
a controller for receiving an image to be measured and employing the detection method of any one of claims 1-7.
9. A computer-storable medium, characterized by: the computer-storable medium has stored thereon a computer program which, when executed by a processor, implements the detection method as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410061573.9A CN118015340A (en) | 2024-01-16 | 2024-01-16 | Method and device for detecting defects of light guide plate and storable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410061573.9A CN118015340A (en) | 2024-01-16 | 2024-01-16 | Method and device for detecting defects of light guide plate and storable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118015340A true CN118015340A (en) | 2024-05-10 |
Family
ID=90949718
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410061573.9A Pending CN118015340A (en) | 2024-01-16 | 2024-01-16 | Method and device for detecting defects of light guide plate and storable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118015340A (en) |
-
2024
- 2024-01-16 CN CN202410061573.9A patent/CN118015340A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102353519B (en) | Resolving power evaluation method for three-generation dim light image intensifier | |
CN105842885B (en) | A kind of liquid crystal display defect Hierarchical Location method and device | |
EP3557216B1 (en) | Inspecting device, inspecting method, and program | |
US20220222855A1 (en) | System and method for determining whether a camera component is damaged | |
WO2017202114A1 (en) | Method and apparatus for determining illumination intensity for inspection, and optical inspection method and apparatus | |
CN116128881B (en) | Lens detection system and method for defect product synchronous marking | |
KR20090076166A (en) | Automatic inspection system using image analysis method for stain in the polarizing film | |
CN113092489A (en) | System and method for detecting appearance defects of battery | |
CN110567967B (en) | Display panel detection method, system, terminal device and computer readable medium | |
CN109712115B (en) | Automatic PCB detection method and system | |
CN112304969A (en) | Display module detection device, method, apparatus and system and storage medium | |
CN109632269A (en) | Method based on image grayscale infomation detection diffractive-optical element performance | |
CN116067671B (en) | Method, system and medium for testing vehicle paint quality | |
CN111292300B (en) | Method and apparatus for detecting bright spot defect of display panel, and readable storage medium | |
CN118015340A (en) | Method and device for detecting defects of light guide plate and storable medium | |
KR20150125155A (en) | Apparatus and method for brightness uniformity inspecting of display panel | |
CN112858341B (en) | Detection method, shooting system and detection system | |
Adamo et al. | An online defects inspection system for satin glass based on machine vision | |
US9219890B1 (en) | Optical surface analysis system and method | |
KR100847740B1 (en) | Trace inspection system and control method thereof | |
KR102188568B1 (en) | Display panel inspection method based on artificial intelligence | |
KR100591853B1 (en) | Apparatus and method for diagnosing LCD module | |
CN103630547B (en) | There is flaw detection method and the pick-up unit thereof of the optical thin film of periodic structure | |
TW201514474A (en) | Method of detecting defect on optical film with periodic structure and device thereof | |
CN110286505B (en) | Automatic pin searching method and system applied to AOI (automated optical inspection) test of LCD (liquid Crystal display) white glass |
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 |