CN116051551A - Display screen defect detection method and related device based on image processing - Google Patents
Display screen defect detection method and related device based on image processing Download PDFInfo
- Publication number
- CN116051551A CN116051551A CN202310319623.4A CN202310319623A CN116051551A CN 116051551 A CN116051551 A CN 116051551A CN 202310319623 A CN202310319623 A CN 202310319623A CN 116051551 A CN116051551 A CN 116051551A
- Authority
- CN
- China
- Prior art keywords
- display screen
- image
- defect
- target image
- detection
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 216
- 238000001514 detection method Methods 0.000 title claims abstract description 199
- 238000012545 processing Methods 0.000 title claims abstract description 59
- 238000003709 image segmentation Methods 0.000 claims abstract description 135
- 239000004973 liquid crystal related substance Substances 0.000 claims abstract description 62
- 230000011218 segmentation Effects 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims description 39
- 230000004927 fusion Effects 0.000 claims description 38
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 4
- 230000036244 malformation Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000003702 image correction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of image processing, and discloses a display screen defect detection method and a related device based on image processing, which are used for improving the accuracy of display screen defect detection. The method comprises the following steps: setting at least one central region point and a plurality of edge region point according to the shape information of the display screen, matching an image segmentation model according to a target image segmentation strategy, inputting a target image into the image segmentation model for region segmentation to obtain at least one central region image and a plurality of edge region images; respectively inputting at least one center region image and a plurality of edge region images into a display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result; and marking the defect information of the liquid crystal display screen to obtain a target image with the defect type and the defect position.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a display screen defect detection method and related device based on image processing.
Background
The production of the liquid crystal display screen is carried out in a plurality of links, and the liquid crystal display screen is assembled, tested and transported. In these links, the liquid crystal display screen is produced by cutting or blanking, so that the liquid crystal display screen has many cracks or water drops, and the defects can cause the display effect of the liquid crystal display screen to be extremely poor, so that the factory standard is not met.
However, the existing scheme is usually detected by artificial vision, and the detection mode is greatly influenced by artificial experience, so that the accuracy of the existing scheme is lower.
Disclosure of Invention
The invention provides a display screen defect detection method and a related device based on image processing, which are used for improving the accuracy of display screen defect detection.
The first aspect of the present invention provides a display screen defect detection method based on image processing, the display screen defect detection method based on image processing includes:
acquiring a target image of a liquid crystal display screen, and carrying out display screen shape analysis on the liquid crystal display screen according to the target image to obtain display screen shape information;
according to the shape information of the display screen, performing image segmentation strategy matching on the target image to obtain a target image segmentation strategy;
Setting at least one central region point and a plurality of edge region points according to the target image segmentation strategy, and matching an image segmentation model according to the target image segmentation strategy;
inputting the target image into the image segmentation model for region segmentation according to the at least one central region point and the plurality of edge region points to obtain at least one central region image and a plurality of edge region images;
respectively inputting the at least one center region image and the plurality of edge region images into a preset display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result;
and carrying out defect feature fusion on the center region detection result and the edge region detection result to obtain fusion defect features, and carrying out defect information labeling on the liquid crystal display screen according to the fusion defect features to obtain a target image with defect types and defect positions.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the obtaining a target image of a liquid crystal display, and performing a display shape analysis on the liquid crystal display according to the target image, to obtain display shape information, includes:
Calling an image acquisition terminal of liquid crystal display equipment to acquire an initial image of a liquid crystal display to be detected;
performing image deformity correction and contrast enhancement processing on the initial image to obtain a target image;
invoking a preset shape template library, and performing shape template matching on the target image to obtain a target shape template corresponding to the target image;
and acquiring the shape information of the target shape template, and taking the shape information of the target shape template as the display screen shape information of the liquid crystal display screen.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, performing image segmentation policy matching on the target image according to the display screen shape information to obtain a target image segmentation policy, where the method includes:
analyzing the display screen shape information to obtain a shape analysis result, wherein the shape analysis result comprises any one of the following components: a hole digging screen shape, a Liu Haibing shape and a full screen shape;
constructing a corresponding relation between the shape analysis result and a candidate image segmentation strategy;
matching the corresponding relation of the target image to obtain a matching result;
and taking the candidate image segmentation strategy corresponding to the matching result as a target image segmentation strategy of the liquid crystal display screen.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the setting at least one center region point location and a plurality of edge region point locations according to the target image segmentation policy, and matching an image segmentation model according to the target image segmentation policy, includes:
acquiring center position information of the target image according to the target image segmentation strategy;
generating an image segmentation point set according to the central position information, wherein the image segmentation point set comprises: at least one center region point location and a plurality of edge region point locations;
calculating an image segmentation data amount according to the image segmentation point set, and obtaining a model load of a candidate segmentation model;
and matching the image segmentation model corresponding to the liquid crystal display screen according to the image segmentation data quantity and the model load quantity.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the inputting the target image into the image segmentation model according to the at least one central region point location and the plurality of edge region point locations to perform region segmentation to obtain at least one central region image and a plurality of edge region images includes:
Inputting the target image into the image segmentation model, and calculating a first communication area of the point positions of the at least one central area and a second communication area of the point positions of each edge area through the image segmentation model;
performing cross-over ratio calculation on the first communication area of the point location of the at least one central area and the second communication area of the point location of each edge area to obtain a cross-over ratio calculation result;
and if the intersection ratio calculation result meets a preset target value, extracting the segmentation image of the at least one central region point position and the plurality of edge region point positions to obtain at least one central region image and a plurality of edge region images.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set to perform display screen defect detection, to obtain a center area detection result and an edge area detection result, includes:
respectively inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set, wherein the display screen defect detection model set comprises: a crack detection model and a water drop detection model;
Performing defect detection on the at least one center region image through the crack detection model and the water drop detection model to obtain a center region detection result;
and carrying out display screen defect detection on the plurality of edge area images through the crack detection model and the water drop detection model to obtain an edge area detection result.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, performing defect feature fusion on the center region detection result and the edge region detection result to obtain a fused defect feature, and performing defect information labeling on the liquid crystal display according to the fused defect feature to obtain a target image with a defect type and a defect position, where the method includes:
respectively extracting features of the center region detection result and the edge region detection result to obtain a plurality of detection features;
performing defect feature fusion on the plurality of detection features to obtain fusion defect features;
generating defect information according to the fusion defect characteristics, and constructing a marking frame of the defect information;
and fusing the annotation frame and the target image to obtain the target image with the defect type and the defect position.
The second aspect of the present invention provides a display screen defect detection device based on image processing, the display screen defect detection device based on image processing includes:
the acquisition module is used for acquiring a target image of the liquid crystal display screen, and analyzing the shape of the liquid crystal display screen according to the target image to obtain the shape information of the display screen;
the matching module is used for matching the image segmentation strategy of the target image according to the shape information of the display screen to obtain the target image segmentation strategy;
the setting module is used for setting at least one central region point position and a plurality of edge region point positions according to the target image segmentation strategy and matching an image segmentation model according to the target image segmentation strategy;
the segmentation module is used for inputting the target image into the image segmentation model for region segmentation according to the at least one central region point and the plurality of edge region point to obtain at least one central region image and a plurality of edge region images;
the detection module is used for respectively inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set to detect display screen defects, so as to obtain a center area detection result and an edge area detection result;
And the output module is used for carrying out defect feature fusion on the central region detection result and the edge region detection result to obtain fusion defect features, and carrying out defect information labeling on the liquid crystal display screen according to the fusion defect features to obtain a target image with defect types and defect positions.
A third aspect of the present invention provides a display screen defect detection apparatus based on image processing, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the image processing-based display defect detection apparatus to perform the image processing-based display defect detection method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein that, when executed on a computer, cause the computer to perform the above-described image processing-based display screen defect detection method.
According to the technical scheme provided by the invention, at least one central region point position and a plurality of edge region point positions are set according to the shape information of the display screen, an image segmentation model is matched according to a target image segmentation strategy, and a target image is input into the image segmentation model for region segmentation, so that at least one central region image and a plurality of edge region images are obtained; respectively inputting at least one center region image and a plurality of edge region images into a display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result; the method comprises the steps of carrying out defect information labeling on the liquid crystal display to obtain a target image with a defect type and a defect position, constructing an image segmentation strategy to match an image segmentation model, then carrying out segmentation detection on the target image of the liquid crystal display to obtain a center region detection result and an edge region detection result, and further carrying out defect fusion on the detection results to generate the target image with the defect type and the defect position, thereby greatly improving the accuracy and the detection efficiency of the defect detection of the display.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a display defect detection method based on image processing according to an embodiment of the present invention;
FIG. 2 is a flow chart of image segmentation strategy matching in an embodiment of the present invention;
FIG. 3 is a flow chart of setting at least one center region point location and a plurality of edge region points in an embodiment of the present invention;
FIG. 4 is a flow chart of region segmentation in an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a display defect detection apparatus based on image processing according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a display defect detection apparatus based on image processing in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a display screen defect detection method and a related device based on image processing, which are used for improving the accuracy of display screen defect detection. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, referring to fig. 1, an embodiment of a display screen defect detection method based on image processing in the embodiment of the present invention includes:
s101, acquiring a target image of a liquid crystal display screen, and analyzing the shape of the liquid crystal display screen according to the target image to obtain the shape information of the display screen;
it is to be understood that the execution subject of the present invention may be a display screen defect detection device based on image processing, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the server performs image acquisition on the liquid crystal display screen through the image acquisition terminal of the liquid crystal display screen to determine a corresponding initial image, further, the server performs preprocessing on the initial image to determine a target image of the liquid crystal display screen, and further, the server performs contour analysis and shape matching on the target image to determine shape information of the liquid crystal display screen.
S102, performing image segmentation strategy matching on a target image according to the shape information of the display screen to obtain a target image segmentation strategy;
Specifically, the server analyzes the display screen display area of the display screen shape information to determine a corresponding display screen display area, further analyzes the display screen according to the display screen display area to determine a corresponding shape analysis result, and finally, the server performs image segmentation strategy matching on the target image through the shape analysis result to obtain a target image segmentation strategy.
S103, setting at least one central region point and a plurality of edge region points according to a target image segmentation strategy, and matching an image segmentation model according to the target image segmentation strategy;
the server firstly analyzes the target image segmentation strategy to determine corresponding image segmentation strategy information, and further, the server performs point location setting on the target image according to the image segmentation strategy information, wherein when the point location setting is performed, the server performs center area point location analysis and edge area point location analysis on the target image to determine at least one center area point location and a plurality of edge area point locations, and finally, the server performs image segmentation model matching according to the at least one center area point location and the plurality of edge area point locations through the target image segmentation strategy to determine a corresponding image segmentation model.
S104, inputting the target image into an image segmentation model to carry out region segmentation according to at least one central region point and a plurality of edge region point, so as to obtain at least one central region image and a plurality of edge region images;
specifically, according to at least one central region point and a plurality of edge region points, inputting a target image into an image segmentation model for region segmentation, wherein the server determines corresponding connected regions according to the at least one central region point, further, the server determines corresponding connected regions according to the plurality of edge region images, and finally, the server performs region segmentation on the target image according to the connected regions corresponding to the at least one central region point and the plurality of edge region images through the image segmentation model to obtain at least one central region image and a plurality of edge region images.
S105, respectively inputting at least one center area image and a plurality of edge area images into a preset display screen defect detection model set to detect display screen defects, so as to obtain a center area detection result and an edge area detection result;
it should be noted that the display screen defect detection model set includes a crack detection model and a water drop detection model, and further, the server performs display screen defect detection on at least one center area image and a plurality of edge area images through the crack detection model and the water drop detection model, so as to obtain a center area detection result and an edge area detection result.
S106, carrying out defect feature fusion on the center region detection result and the edge region detection result to obtain fusion defect features, and carrying out defect information labeling on the liquid crystal display according to the fusion defect features to obtain a target image with defect types and defect positions.
Specifically, the server performs similar defect feature analysis on the center region detection result and the edge region detection result, determines corresponding similar defect features, further, performs defect feature fusion according to the similar defect features to obtain fusion defect features, further, performs defect position analysis on the fusion defect features to determine corresponding defect positions, and finally, performs defect information labeling on the liquid crystal display according to the defect positions to obtain a target image with defect types and defect positions.
In the embodiment of the invention, at least one central area point position and a plurality of edge area point positions are set according to the shape information of a display screen, an image segmentation model is matched according to a target image segmentation strategy, and a target image is input into the image segmentation model for area segmentation, so that at least one central area image and a plurality of edge area images are obtained; respectively inputting at least one center region image and a plurality of edge region images into a display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result; the method comprises the steps of carrying out defect information labeling on the liquid crystal display to obtain a target image with a defect type and a defect position, constructing an image segmentation strategy to match an image segmentation model, then carrying out segmentation detection on the target image of the liquid crystal display to obtain a center region detection result and an edge region detection result, and further carrying out defect fusion on the detection results to generate the target image with the defect type and the defect position, thereby greatly improving the accuracy and the detection efficiency of the defect detection of the display.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Calling an image acquisition terminal of liquid crystal display equipment to acquire an initial image of a liquid crystal display to be detected;
(2) Carrying out image deformity correction and contrast enhancement processing on the initial image to obtain a target image;
(3) Invoking a preset shape template library, and performing shape template matching on the target image to obtain a target shape template corresponding to the target image;
(4) And acquiring the shape information of the target shape template, and taking the shape information of the target shape template as the display screen shape information of the liquid crystal display screen.
Specifically, the server calls an image acquisition terminal of the liquid crystal display device, acquires an initial image of the liquid crystal display device to be detected, performs image malformation correction and contrast enhancement processing on the initial image to obtain a target image, wherein the server performs malformation display image extraction on the initial image, determines a corresponding malformation display image, specifically, when performing malformation display image extraction, the server firstly acquires a standard display image, further, the server performs image comparison on the initial image according to the standard display image, determines a corresponding malformation display image, further, the server performs image correction processing on the malformation display image, and meanwhile, performs contrast enhancement processing on the malformation display image after the image correction processing to obtain a target image, invokes a preset shape template library, performs shape template matching on the target image to obtain a target shape template corresponding to the target image, performs shape template matching on the target image according to the image contour and the shape template library to obtain a target shape template corresponding to the target image, and obtains shape information of the target shape template as the shape information of the liquid crystal display device.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, analyzing the shape information of the display screen to obtain a shape analysis result, wherein the shape analysis result comprises any one of the following components: a hole digging screen shape, a Liu Haibing shape and a full screen shape;
s202, constructing a corresponding relation between a shape analysis result and a candidate image segmentation strategy;
s203, matching the corresponding relation of the target image to obtain a matching result;
s204, taking the candidate image segmentation strategy corresponding to the matching result as a target image segmentation strategy of the liquid crystal display screen.
Specifically, the server analyzes the shape information of the display screen to obtain a shape analysis result, wherein the shape analysis result comprises any one of the following components: the method comprises the steps of digging a screen shape, liu Haibing and comprehensively analyzing the shape information of the display screen by a server to determine a corresponding display screen display area, further analyzing the display screen by the server according to the display screen display area to determine a corresponding shape analysis result, and constructing a corresponding relation between the shape analysis result and a candidate image segmentation strategy, wherein the server determines a corresponding analysis mark according to the shape analysis result, further determines a corresponding image segmentation mark according to the analysis mark, finally, the server constructs a corresponding relation between the shape analysis result and the candidate image segmentation strategy according to the image segmentation mark and the analysis mark, further, performs corresponding relation matching on a target image to obtain a matching result, and finally, takes the candidate image segmentation strategy corresponding to the matching result as the target image segmentation strategy of the liquid crystal display screen.
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, acquiring center position information of a target image according to a target image segmentation strategy;
s302, generating an image segmentation point set according to the central position information, wherein the image segmentation point set comprises: at least one center region point location and a plurality of edge region point locations;
s303, calculating an image segmentation data amount according to the image segmentation point set, and obtaining a model load of a candidate segmentation model;
s304, matching an image segmentation model corresponding to the liquid crystal display according to the image segmentation data quantity and the model load quantity.
Specifically, the server acquires center position information of a target image according to a target image segmentation strategy;
generating an image segmentation point set according to the central position information, wherein the image segmentation point set comprises: the method comprises the steps of determining at least one center region point and a plurality of edge region points, wherein when determining the at least one center region point, a server firstly performs region rough segmentation on a target image to determine a plurality of corresponding rough segmentation regions, further, the server performs centroid analysis on each rough segmentation region to determine a plurality of centroids, and finally, the server performs center region point analysis according to the centroids to determine the corresponding center region point. Further, the server calculates the image segmentation data amount according to the image segmentation point set and obtains the model load of the candidate segmentation model, wherein the server determines the image segmentation area corresponding to each image segmentation point according to the image segmentation point set, finally, the server determines the corresponding image segmentation data amount according to the image segmentation area corresponding to each image segmentation point, finally, the server obtains the model load of the candidate segmentation model, and the image segmentation model corresponding to the liquid crystal display screen is matched according to the image segmentation data amount and the model load.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, inputting a target image into an image segmentation model, and calculating a first communication area of at least one central area point location and a second communication area of each edge area point location through the image segmentation model;
s402, performing cross-over ratio calculation on a first communication area of at least one central area point position and a second communication area of each edge area point position to obtain a cross-over ratio calculation result;
s403, if the intersection ratio calculation result meets the preset target value, extracting the segmentation image of at least one central region point position and a plurality of edge region point positions to obtain at least one central region image and a plurality of edge region images.
Specifically, the server inputs the target image into an image segmentation model, calculates a first connected region of at least one central region point and a second connected region of each edge region point through the image segmentation model, wherein when calculating the connected region, the server respectively carries out overlapping region segmentation on the at least one central region point and each edge region point, determines a corresponding overlapping region, further carries out connected region calculation according to the overlapping region, further carries out intersection ratio calculation on the first connected region of the at least one central region point and the second connected region of each edge region point, and obtains an intersection ratio calculation result, specifically, when carrying out intersection ratio calculation, the server carries out coincidence point analysis on the first connected region of at least one central region point and the second connected region of each edge region point, determines at least one coincidence point, and further carries out intersection ratio calculation according to the data quantity corresponding to the at least one coincidence point, and obtains an intersection ratio calculation result, and if the intersection ratio calculation result accords with a preset target value, carries out intersection ratio calculation on the at least one central region and a plurality of edge region points, and at least one image segmentation point is obtained.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Respectively inputting at least one center area image and a plurality of edge area images into a preset display screen defect detection model set, wherein the display screen defect detection model set comprises: a crack detection model and a water drop detection model;
(2) Performing defect detection on at least one center area image through a crack detection model and a water drop detection model to obtain a center area detection result;
(3) And carrying out display screen defect detection on the plurality of edge area images through the crack detection model and the water drop detection model to obtain an edge area detection result.
Specifically, at least one center area image and a plurality of edge area images are respectively input into a preset display screen defect detection model set, wherein the display screen defect detection model set comprises: a crack detection model and a water drop detection model; and performing defect detection on at least one central area image through the crack detection model and the water drop detection model to obtain a central area detection result, wherein the server performs water drop feature analysis on the at least one central area image through the water drop detection model to determine corresponding water drop features, and further the server determines the corresponding central area detection result according to the water drop features. The method comprises the steps that display screen defect detection is conducted on a plurality of edge area images through a crack detection model and a water drop detection model to obtain edge area detection results, specifically, a server displays crack analysis on the plurality of edge area images according to the crack detection model, when the crack analysis is conducted, the server conducts pixel analysis on the plurality of edge area images to determine corresponding pixel continuity, then the server determines corresponding crack characteristics according to the pixel continuity, meanwhile, the server conducts water drop characteristic detection on the plurality of edge area images according to the water drop detection model to determine corresponding water drop characteristics, and finally the edge detection results are obtained.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Respectively extracting features of the center region detection result and the edge region detection result to obtain a plurality of detection features;
(2) Performing defect feature fusion on the plurality of detection features to obtain fusion defect features;
(3) Generating defect information according to the fusion defect characteristics, and constructing a marking frame of the defect information;
(4) And fusing the annotation frame and the target image to obtain the target image with the defect type and the defect position.
Specifically, feature extraction is respectively carried out on a center region detection result and an edge region detection result to obtain a plurality of detection features, and defect feature fusion is carried out on the plurality of detection features to obtain fusion defect features;
generating defect information according to the fused defect characteristics, constructing a marking frame of the defect information, wherein a server performs similar defect characteristic analysis on the center region detection result and the edge region detection result to determine corresponding similar defect characteristics, further, performing defect characteristic fusion according to the similar characteristic defects to obtain the fused defect characteristics, further, performing defect position analysis on the fused defect characteristics by the server to determine corresponding defect positions, and finally, marking the defect information on the liquid crystal display according to the defect positions by the server to obtain a target image with defect types and defect positions.
The method for detecting the display screen defect based on the image processing in the embodiment of the present invention is described above, and the device for detecting the display screen defect based on the image processing in the embodiment of the present invention is described below, referring to fig. 5, one embodiment of the device for detecting the display screen defect based on the image processing in the embodiment of the present invention includes:
the acquisition module 501 is configured to acquire a target image of a liquid crystal display, and perform display shape analysis on the liquid crystal display according to the target image to obtain display shape information;
the matching module 502 is configured to perform image segmentation policy matching on the target image according to the display screen shape information, so as to obtain a target image segmentation policy;
a setting module 503, configured to set at least one center region point location and a plurality of edge region point locations according to the target image segmentation policy, and match an image segmentation model according to the target image segmentation policy;
the segmentation module 504 is configured to input the target image into the image segmentation model for region segmentation according to the at least one central region point location and the plurality of edge region point locations, so as to obtain at least one central region image and a plurality of edge region images;
The detection module 505 is configured to input the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set to perform display screen defect detection, so as to obtain a center area detection result and an edge area detection result;
and the output module 506 is configured to perform defect feature fusion on the center region detection result and the edge region detection result to obtain a fused defect feature, and perform defect information labeling on the liquid crystal display according to the fused defect feature to obtain a target image with a defect type and a defect position.
Setting at least one central region point location and a plurality of edge region point locations according to the shape information of the display screen through the cooperative cooperation of the components, matching an image segmentation model according to a target image segmentation strategy, inputting a target image into the image segmentation model for region segmentation, and obtaining at least one central region image and a plurality of edge region images; respectively inputting at least one center region image and a plurality of edge region images into a display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result; the method comprises the steps of carrying out defect information labeling on the liquid crystal display to obtain a target image with a defect type and a defect position, constructing an image segmentation strategy to match an image segmentation model, then carrying out segmentation detection on the target image of the liquid crystal display to obtain a center region detection result and an edge region detection result, and further carrying out defect fusion on the detection results to generate the target image with the defect type and the defect position, thereby greatly improving the accuracy and the detection efficiency of the defect detection of the display.
The display screen defect detection apparatus based on image processing in the embodiment of the present invention is described in detail above in terms of modularized functional entities in fig. 5, and the display screen defect detection device based on image processing in the embodiment of the present invention is described in detail below in terms of hardware processing.
Fig. 6 is a schematic structural diagram of an image processing-based display defect detection apparatus 600 according to an embodiment of the present invention, where the image processing-based display defect detection apparatus 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing applications 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations on the image processing-based display screen defect detection apparatus 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the image processing-based display defect detection apparatus 600.
The image processing based display defect detection apparatus 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the image processing-based display defect detection apparatus structure shown in fig. 6 is not limiting of the image processing-based display defect detection apparatus and may include more or fewer components than shown, or may be combined with certain components, or may be arranged with different components.
The present invention also provides an image processing-based display screen defect detection apparatus, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the image processing-based display screen defect detection method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the display screen defect detection method based on image processing.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, 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 U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The display screen defect detection method based on the image processing is characterized by comprising the following steps of:
acquiring a target image of a liquid crystal display screen, and carrying out display screen shape analysis on the liquid crystal display screen according to the target image to obtain display screen shape information;
according to the shape information of the display screen, performing image segmentation strategy matching on the target image to obtain a target image segmentation strategy;
setting at least one central region point and a plurality of edge region points according to the target image segmentation strategy, and matching an image segmentation model according to the target image segmentation strategy;
Inputting the target image into the image segmentation model for region segmentation according to the at least one central region point and the plurality of edge region points to obtain at least one central region image and a plurality of edge region images;
respectively inputting the at least one center region image and the plurality of edge region images into a preset display screen defect detection model set to detect display screen defects, so as to obtain a center region detection result and an edge region detection result;
and carrying out defect feature fusion on the center region detection result and the edge region detection result to obtain fusion defect features, and carrying out defect information labeling on the liquid crystal display screen according to the fusion defect features to obtain a target image with defect types and defect positions.
2. The method for detecting defects of a display screen based on image processing according to claim 1, wherein the steps of obtaining a target image of a liquid crystal display screen, and performing display screen shape analysis on the liquid crystal display screen according to the target image to obtain display screen shape information, include:
calling an image acquisition terminal of liquid crystal display equipment to acquire an initial image of a liquid crystal display to be detected;
Performing image deformity correction and contrast enhancement processing on the initial image to obtain a target image;
invoking a preset shape template library, and performing shape template matching on the target image to obtain a target shape template corresponding to the target image;
and acquiring the shape information of the target shape template, and taking the shape information of the target shape template as the display screen shape information of the liquid crystal display screen.
3. The method for detecting defects of a display screen based on image processing according to claim 1, wherein the performing image segmentation policy matching on the target image according to the display screen shape information to obtain a target image segmentation policy comprises:
analyzing the display screen shape information to obtain a shape analysis result, wherein the shape analysis result comprises any one of the following components: a hole digging screen shape, a Liu Haibing shape and a full screen shape;
constructing a corresponding relation between the shape analysis result and a candidate image segmentation strategy;
matching the corresponding relation of the target image to obtain a matching result;
and taking the candidate image segmentation strategy corresponding to the matching result as a target image segmentation strategy of the liquid crystal display screen.
4. The method for detecting defects of a display screen based on image processing according to claim 1, wherein the setting at least one center region point and a plurality of edge region points according to the target image segmentation strategy, and matching an image segmentation model according to the target image segmentation strategy, comprises:
acquiring center position information of the target image according to the target image segmentation strategy;
generating an image segmentation point set according to the central position information, wherein the image segmentation point set comprises: at least one center region point location and a plurality of edge region point locations;
calculating an image segmentation data amount according to the image segmentation point set, and obtaining a model load of a candidate segmentation model;
and matching the image segmentation model corresponding to the liquid crystal display screen according to the image segmentation data quantity and the model load quantity.
5. The method for detecting defects of a display screen based on image processing according to claim 1, wherein inputting the target image into the image segmentation model for region segmentation according to the at least one center region point location and the plurality of edge region point locations, obtaining at least one center region image and a plurality of edge region images, comprises:
Inputting the target image into the image segmentation model, and calculating a first communication area of the point positions of the at least one central area and a second communication area of the point positions of each edge area through the image segmentation model;
performing cross-over ratio calculation on the first communication area of the point location of the at least one central area and the second communication area of the point location of each edge area to obtain a cross-over ratio calculation result;
and if the intersection ratio calculation result meets a preset target value, extracting the segmentation image of the at least one central region point position and the plurality of edge region point positions to obtain at least one central region image and a plurality of edge region images.
6. The method for detecting defects of a display screen based on image processing according to claim 1, wherein the step of inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set to detect defects of the display screen to obtain a center area detection result and an edge area detection result includes:
respectively inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set, wherein the display screen defect detection model set comprises: a crack detection model and a water drop detection model;
Performing defect detection on the at least one center region image through the crack detection model and the water drop detection model to obtain a center region detection result;
and carrying out display screen defect detection on the plurality of edge area images through the crack detection model and the water drop detection model to obtain an edge area detection result.
7. The method for detecting defects of a display screen based on image processing according to claim 1, wherein the step of performing defect feature fusion on the center region detection result and the edge region detection result to obtain fusion defect features, and performing defect information labeling on the liquid crystal display screen according to the fusion defect features to obtain a target image with defect types and defect positions comprises the steps of:
respectively extracting features of the center region detection result and the edge region detection result to obtain a plurality of detection features;
performing defect feature fusion on the plurality of detection features to obtain fusion defect features;
generating defect information according to the fusion defect characteristics, and constructing a marking frame of the defect information;
and fusing the annotation frame and the target image to obtain the target image with the defect type and the defect position.
8. An image processing-based display screen defect detection device, characterized in that the image processing-based display screen defect detection device comprises:
the acquisition module is used for acquiring a target image of the liquid crystal display screen, and analyzing the shape of the liquid crystal display screen according to the target image to obtain the shape information of the display screen;
the matching module is used for matching the image segmentation strategy of the target image according to the shape information of the display screen to obtain the target image segmentation strategy;
the setting module is used for setting at least one central region point position and a plurality of edge region point positions according to the target image segmentation strategy and matching an image segmentation model according to the target image segmentation strategy;
the segmentation module is used for inputting the target image into the image segmentation model for region segmentation according to the at least one central region point and the plurality of edge region point to obtain at least one central region image and a plurality of edge region images;
the detection module is used for respectively inputting the at least one center area image and the plurality of edge area images into a preset display screen defect detection model set to detect display screen defects, so as to obtain a center area detection result and an edge area detection result;
And the output module is used for carrying out defect feature fusion on the central region detection result and the edge region detection result to obtain fusion defect features, and carrying out defect information labeling on the liquid crystal display screen according to the fusion defect features to obtain a target image with defect types and defect positions.
9. An image processing-based display screen defect detection apparatus, characterized in that the image processing-based display screen defect detection apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invoking the instructions in the memory to cause the image processing based display defect detection apparatus to perform the image processing based display defect detection method of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the image processing-based display screen defect detection method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310319623.4A CN116051551B (en) | 2023-03-29 | 2023-03-29 | Display screen defect detection method and related device based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310319623.4A CN116051551B (en) | 2023-03-29 | 2023-03-29 | Display screen defect detection method and related device based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116051551A true CN116051551A (en) | 2023-05-02 |
| CN116051551B CN116051551B (en) | 2023-06-09 |
Family
ID=86116717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310319623.4A Active CN116051551B (en) | 2023-03-29 | 2023-03-29 | Display screen defect detection method and related device based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051551B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664551A (en) * | 2023-07-21 | 2023-08-29 | 深圳市长荣科机电设备有限公司 | Display screen detection method, device, equipment and storage medium based on machine vision |
| CN116797553A (en) * | 2023-05-30 | 2023-09-22 | 钛玛科（北京）工业科技有限公司 | Image processing method, device, equipment and storage medium |
| CN116894939A (en) * | 2023-09-11 | 2023-10-17 | 深圳精智达技术股份有限公司 | Regional positioning method and device for special-shaped screen, electronic equipment and storage medium |
| CN117392225A (en) * | 2023-12-06 | 2024-01-12 | 中导光电设备股份有限公司 | Method and system for correcting position of detection area of display screen |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004294202A (en) * | 2003-03-26 | 2004-10-21 | Seiko Epson Corp | Defect detection method and device of screen |
| JP2006250895A (en) * | 2005-03-14 | 2006-09-21 | Sharp Corp | Method for manufacturing display panel, and inspection device for display panel |
| CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
| CN109084955A (en) * | 2018-07-02 | 2018-12-25 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
| CN109345528A (en) * | 2018-09-28 | 2019-02-15 | 凌云光技术集团有限责任公司 | A kind of display screen defect inspection method and device based on human-eye visual characteristic |
| CN110987938A (en) * | 2019-11-28 | 2020-04-10 | 意力(广州)电子科技有限公司 | Automatic visual inspection method and device for display screen |
| CN111612781A (en) * | 2020-05-27 | 2020-09-01 | 歌尔股份有限公司 | Screen defect detection method and device and head-mounted display equipment |
| CN114299070A (en) * | 2022-03-09 | 2022-04-08 | 深圳精智达技术股份有限公司 | Method and related device for detecting mura defects of display screen |
| CN114862845A (en) * | 2022-07-04 | 2022-08-05 | 深圳市瑞桔电子有限公司 | Defect detection method, device and equipment for mobile phone touch screen and storage medium |
| CN115601355A (en) * | 2022-11-10 | 2023-01-13 | 四川启睿克科技有限公司（Cn） | Method and device for detecting and classifying product surface defects and storage medium |
-
2023
- 2023-03-29 CN CN202310319623.4A patent/CN116051551B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004294202A (en) * | 2003-03-26 | 2004-10-21 | Seiko Epson Corp | Defect detection method and device of screen |
| JP2006250895A (en) * | 2005-03-14 | 2006-09-21 | Sharp Corp | Method for manufacturing display panel, and inspection device for display panel |
| CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
| CN109084955A (en) * | 2018-07-02 | 2018-12-25 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
| CN109345528A (en) * | 2018-09-28 | 2019-02-15 | 凌云光技术集团有限责任公司 | A kind of display screen defect inspection method and device based on human-eye visual characteristic |
| CN110987938A (en) * | 2019-11-28 | 2020-04-10 | 意力(广州)电子科技有限公司 | Automatic visual inspection method and device for display screen |
| CN111612781A (en) * | 2020-05-27 | 2020-09-01 | 歌尔股份有限公司 | Screen defect detection method and device and head-mounted display equipment |
| CN114299070A (en) * | 2022-03-09 | 2022-04-08 | 深圳精智达技术股份有限公司 | Method and related device for detecting mura defects of display screen |
| CN114862845A (en) * | 2022-07-04 | 2022-08-05 | 深圳市瑞桔电子有限公司 | Defect detection method, device and equipment for mobile phone touch screen and storage medium |
| CN115601355A (en) * | 2022-11-10 | 2023-01-13 | 四川启睿克科技有限公司（Cn） | Method and device for detecting and classifying product surface defects and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797553A (en) * | 2023-05-30 | 2023-09-22 | 钛玛科（北京）工业科技有限公司 | Image processing method, device, equipment and storage medium |
| CN116664551A (en) * | 2023-07-21 | 2023-08-29 | 深圳市长荣科机电设备有限公司 | Display screen detection method, device, equipment and storage medium based on machine vision |
| CN116664551B (en) * | 2023-07-21 | 2023-10-31 | 深圳市长荣科机电设备有限公司 | Display screen detection method, device, equipment and storage medium based on machine vision |
| CN116894939A (en) * | 2023-09-11 | 2023-10-17 | 深圳精智达技术股份有限公司 | Regional positioning method and device for special-shaped screen, electronic equipment and storage medium |
| CN116894939B (en) * | 2023-09-11 | 2024-01-09 | 深圳精智达技术股份有限公司 | Regional positioning method and device for special-shaped screen, electronic equipment and storage medium |
| CN117392225A (en) * | 2023-12-06 | 2024-01-12 | 中导光电设备股份有限公司 | Method and system for correcting position of detection area of display screen |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116051551B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116051551B (en) | Display screen defect detection method and related device based on image processing | |
| CN106097361B (en) | Defect area detection method and device | |
| CN111340796B (en) | Defect detection method and device, electronic equipment and storage medium | |
| CN112348765A (en) | Data enhancement method and device, computer readable storage medium and terminal equipment | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN110346704B (en) | Method, device and equipment for determining test file in board test and storage medium | |
| CN112348835A (en) | Method and device for detecting material quantity, electronic equipment and storage medium | |
| CN115908988B (en) | Defect detection model generation method, device, equipment and storage medium | |
| CN113065538A (en) | Pressure sensor detection method, device and equipment based on image recognition | |
| CN115236074A (en) | Detection method, system and platform for lithium battery pole piece lamination | |
| CN110991357A (en) | Answer matching method and device and electronic equipment | |
| CN116137061B (en) | Training method and device for quantity statistical model, electronic equipment and storage medium | |
| CN117132583A (en) | Wafer defect detection method and device, electronic equipment and nonvolatile storage medium | |
| CN115223165B (en) | Method and device for acquiring cell image to be interpreted | |
| CN111079752A (en) | Method and device for identifying circuit breaker in infrared image and readable storage medium | |
| CN116342585A (en) | Product defect detection method, device, equipment and storage medium | |
| CN113012137B (en) | Panel defect inspection method, system, terminal device and storage medium | |
| JP2022185872A (en) | Image processing device, image processing method and imaging apparatus | |
| CN113313125A (en) | Image processing method and device, electronic equipment and computer readable medium | |
| CN116258714B (en) | Defect identification method and device, electronic equipment and storage medium | |
| CN115375854B (en) | Ultrasonic image equipment image processing method fused with liquid crystal device and related device | |
| CN114782710B (en) | Image feature extraction method and device and display panel restoration method | |
| CN114120016B (en) | Character string extraction method, device, equipment and storage medium | |
| CN117173720B (en) | Processing method and device suitable for intelligent energy unit | |
| CN116363464A (en) | Model performance information generation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |