CN113870255A - Mini LED product defect detection method and related equipment - Google Patents
Mini LED product defect detection method and related equipment Download PDFInfo
- Publication number
- CN113870255A CN113870255A CN202111444639.5A CN202111444639A CN113870255A CN 113870255 A CN113870255 A CN 113870255A CN 202111444639 A CN202111444639 A CN 202111444639A CN 113870255 A CN113870255 A CN 113870255A
- Authority
- CN
- China
- Prior art keywords
- image
- mini led
- led product
- detection
- template
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 121
- 230000007547 defect Effects 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 34
- 230000006870 function Effects 0.000 claims description 21
- 230000002950 deficient Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims 7
- 239000000047 product Substances 0.000 description 113
- 238000012545 processing Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
The invention relates to a Mini LED product defect detection method and related equipment, wherein the method comprises the following steps: acquiring a Mini LED product image and taking the Mini LED product image as a detection image; selecting a template characteristic database corresponding to the Mini LED product, inputting a detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library; based on the detection image and the reference image, obtaining a residual image by utilizing an ET algorithm; and marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points. The invention can effectively improve the real defect detection rate of the Mini LED product and can reduce the false defect detection frequency.
Description
Technical Field
The invention relates to the field of defect detection, in particular to a method and related equipment for detecting defects of a Mini LED product.
Background
The Mini LED is a flat panel display, the existing defect detection methods aiming at the Mini LED are fewer, and the existing commonly used defect detection methods are mainly divided into an electrical detection method and an optical detection method. Common electrical detection methods include full-screen lighting detection, probe scanning detection, voltage imaging, and the like; the commonly used optical detection method specifically includes imaging the surface of the LCD panel through the CCD, acquiring an image, transmitting the image to the image data processing unit, analyzing and processing the data by the image data processing unit, and displaying the detection result to a user. The existing defect detection method has large error and is easy to detect false defects.
Disclosure of Invention
The invention mainly aims to provide a Mini LED product defect detection method and related equipment, and aims to solve the problems that the existing defect detection method has large error and is easy to detect false defects.
In a first aspect, the present invention provides a method for detecting defects of a Mini LED product, the method for detecting defects of a Mini LED product comprising:
acquiring a Mini LED product image and taking the Mini LED product image as a detection image;
selecting a template characteristic database corresponding to the Mini LED product, inputting a detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library;
based on the detection image and the reference image, obtaining a residual image by utilizing an ET algorithm;
and marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points.
Optionally, before the step of acquiring the Mini LED product image and taking the Mini LED product image as the detection image, the method further includes:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
Optionally, the step of obtaining the template feature database by using the second template image includes:
and obtaining a characteristic value and a characteristic vector of the second template image by using a principal component analysis method based on the second template image, and storing the characteristic value and the characteristic vector of the second template image in a template characteristic database.
Optionally, the step of obtaining the residual image by using the ET algorithm based on the detection image and the reference image includes:
calculating to obtain a gray value of the detection image, a gradient value of the detection image, a gray value of the reference image and a gradient value of the reference image according to the detection image and the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
Optionally, before the step of obtaining the gray scale value of the detected image, the gradient value of the detected image, the gray scale value of the reference image, and the gradient value of the reference image by calculation according to the detected image and the reference image, the method further includes:
and registering the detection image and the reference image by adopting a cross-correlation algorithm.
In a second aspect, the present invention further provides a Mini LED product defect detecting apparatus, including:
the acquisition module is used for acquiring the image of the Mini LED product and taking the image of the Mini LED product as a detection image;
the first control module is used for selecting a template characteristic database corresponding to the Mini LED product, inputting the detection image into the template characteristic database corresponding to the Mini LED product and obtaining a reference image by using the function library;
the second control module is used for obtaining a residual image by utilizing an ET algorithm based on the detection image and the reference image;
and the detection module is used for marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points.
Optionally, the Mini LED product defect detecting apparatus further includes a generating module, where the generating module is configured to:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
Optionally, the second control module is further configured to:
calculating to obtain a gray value of the detection image, a gradient value of the detection image, a gray value of the reference image and a gradient value of the reference image according to the detection image and the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
Optionally, the generating module is further configured to:
and obtaining a characteristic value and a characteristic vector of the second template image by using a principal component analysis method based on the second template image, and storing the characteristic value and the characteristic vector of the second template image in a template characteristic database.
Optionally, the Mini LED product defect detecting apparatus further includes a registration module, and the registration module is configured to register the detected image and the reference image by using a cross-correlation algorithm.
In a third aspect, the present invention further provides a Mini LED product defect detecting apparatus, where the Mini LED product defect detecting apparatus includes a processor, a memory, and a Mini LED product defect detecting program stored on the memory and executable by the processor, where the Mini LED product defect detecting program is executed by the processor to implement the steps of the Mini LED product defect detecting method described above.
In a fourth aspect, the present invention further provides a readable storage medium, where a Mini LED product defect detection program is stored on the readable storage medium, where the Mini LED product defect detection program, when executed by a processor, implements the steps of the method for detecting the defect of the Mini LED product as described above.
The invention relates to a Mini LED product defect detection method and related equipment, wherein the method comprises the following steps: acquiring a Mini LED product image and taking the Mini LED product image as a detection image; selecting a template characteristic database corresponding to the Mini LED product, inputting a detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library; based on the detection image and the reference image, obtaining a residual image by utilizing an ET algorithm; and marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points. The invention can effectively improve the real defect detection rate of the Mini LED product and can reduce the false defect detection frequency.
Drawings
FIG. 1 is a schematic flow chart of a defect detection method for Mini LED products according to a first embodiment of the present invention;
FIG. 2 is a functional block diagram of a Mini LED product defect detecting apparatus according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of a hardware structure of a Mini LED product defect detection device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In a first aspect, the embodiment of the invention provides a method for detecting defects of a Mini LED product.
In an embodiment, referring to fig. 1, fig. 1 is a schematic flow chart of a defect detection method for a Mini LED product according to a first embodiment of the present invention. As shown in fig. 1, the defect detection method for Mini LED products includes:
step S10, acquiring a Mini LED product image and taking the Mini LED product image as a detection image;
in this embodiment, the definition of Mini LED is an LED device with an imaging unit size between 50-200 microns. The Mini LED technology has many advantages, such as the ability to adjust the brightness of the area, and has the features of high color rendering and high contrast. The product is more outstanding in embodiment, and the product has the characteristics of thinner thickness, longer endurance time, capability of bending a screen and the like by applying the Mini LED technology. Compared with an OLED, the Mini LED is lower in cost and longer in service life, and the risk of screen burning can be avoided.
The object of the step of acquiring the image of the Mini LED product is the Mini LED product on the production line, when the production line works, the produced Mini LED product continuously appears on the conveyor belt, at the moment, the image of the Mini LED product on the production line needs to be acquired in real time, and the specific mode can be that a camera or a scanner configured on a production machine is used for acquiring the image of the Mini LED product. The type of the Mini LED product needs to be determined after the image of the Mini LED product is collected, different manufacturers have different imaging requirements (resolution requirements), and different patterns and different sizes can appear under different imaging requirements. After the type of the Mini LED product is determined, the follow-up work is convenient to carry out. The acquired Mini LED product image will be marked as a detection image as a data source for subsequent generation of the template feature database.
Step S20, selecting a template characteristic database corresponding to the Mini LED product, inputting the detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library;
in this embodiment, the template feature database is of various types, before detection, the type of the Mini LED product to be detected in the current detection needs to be determined, and the template feature database corresponding to the type is selected according to the type of the Mini LED product.
After the detection image is input into the template feature database, an output reference image needs to be obtained, and in the process, a function library needs to be utilized for operation and processing. The function library specifically refers to an intel mathematic core function library, which is a wide scientific/engineering mathematic library and contains a large number of functions, so that high-complexity processing of data can be realized. In the defect detection of the Mini LED product, specifically, after the detection image is input into the template feature database corresponding to the Mini LED product, the corresponding function in the function library is called to obtain the corresponding reference image.
Step S30, obtaining a residual image by utilizing an ET algorithm based on the detection image and the reference image;
in this embodiment, the obtaining of the residual image based on the detection image and the reference image by using the ET algorithm specifically means calculating gray information and gradient information of the detection image and the reference image; and processing the gray information and the gradient information of the detection image and the reference image by utilizing an ET algorithm. Specifically, gray level residual images of a detection image and a reference image are calculated respectively; the image and reference image gradient residual maps are detected and then combined to form the final residual map. The ghost image is an object for subsequently detecting the defect, and specifically, the detection is performed on the gray value of the pixel point of the ghost image to judge whether the pixel point is a defect point.
Step S40, marking the pixel points with the gray value larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray value not larger than the threshold value as non-defect points.
In this embodiment, the obtained residual image map needs to be detected, specifically, the size relationship between the gray value of each pixel point in the residual image map and the threshold is detected. Pixels may also be referred to as resolution and refer to an array of horizontal and vertical pixels that may be displayed. Taking 1200 × 1000 as an example, such a resolution actually represents that 1200 pixels are divided in the horizontal direction and 1000 pixels are divided in the vertical direction of the plasma screen. Interpolation of pixel points is to supplement some data among discrete data, so that the group of discrete data can accord with a certain continuous function. Interpolation is the most basic and common means in computational mathematics and is an important method in function approximation theory. The value of the function elsewhere is estimated by using the value state of the function at a limited number of points, namely, by limited data, so as to obtain a complete mathematical description. For example, interpolation of a digital camera is a method in which actual pixels formed by a light sensing device in the digital camera are calculated according to pixels of an actual light sensing image by software built in the camera according to a certain operation method to generate new pixel points, and the new pixel points are inserted into gaps near the original pixels, so that an image with increased total pixel amount and increased pixel density is generated.
The resolution of the pixel points is an important index of the flat panel television, and mainly refers to the number of the pixel points on the screen. The numbers such as 1366 × 768 and 1920 × 1080 represent the number of pixels in the horizontal and vertical directions of the screen. The higher the resolution, the greater the ability of the screen to represent image details. However, it cannot be blindly assumed that the larger the resolution is, the better, since flat-panel televisions generally have the best resolution, also called the maximum resolution, at which the television can display the best image. For any video signal which is not the best resolution of the liquid crystal screen, the liquid crystal television needs to convert the image resolution and then display the converted image.
The threshold is preset and is determined according to specific detection requirements. For example, presetting, using a gray value 200 as a threshold, if the gray value of a pixel point is greater than the threshold, marking the gray value of the pixel point as 255, and marking the pixel point as a defect point; and if the gray value of the pixel point is not larger than the threshold value, recording the gray value of the pixel point as 0, and marking the pixel point as a non-defect point.
Further, in an embodiment, before the step of acquiring the Mini LED product image and using the Mini LED product image as the detection image, the method further includes:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
In this embodiment, the defect detection of the Mini LED product needs to use the template feature database, and the work of generating the template feature database must be completed before the defect detection. The work of generating the template feature database is not to generate only one template feature database, but to generate the template feature databases of different types of Mini LED products according to different types of the Mini LED products. After the Mini LED product image is collected, the collected Mini LED product image needs to be preprocessed, wherein the preprocessing specifically refers to the steps of calibrating and noise processing the collected Mini LED product image, a first template image can be obtained after preprocessing, the image quality of the first template image can be higher, and subsequent detection is facilitated. However, the first detected image merely improves the quality of the image, and does not screen out the image with the generated template feature database. Therefore, it is necessary to eliminate the defective image in the first template image and use the remaining image as the second template image. The second template image obtained at this time is subjected to one-time screening, which belongs to coarse screening and mainly removes the image with obvious defects, and then needs to be subjected to more precise defect detection.
The first template image needs to be stored in a hard disk, the adopted rule is a repeating unit grouping principle, specifically, patterns with the same shape are divided into a group, and in this way, the data acquisition amount of the Mini LED product can be effectively reduced. For example, assuming that the number of training samples required by the principal component analysis method is 1000, if the repeating unit grouping is not performed, 1000 Mini LEDs need to be collected, which is certainly a disaster, because 5 minutes are required for collecting one Mini LED image, and it takes about 5000 minutes to collect 1000 images; the MiniLed product pattern is repetitive (one product has about 108 repeat units), and according to the repeat unit grouping principle, only 10 MiniLed products need to be collected to meet the training sample.
Further, in an embodiment, the step of obtaining the template feature database by using the second template image includes:
and obtaining a characteristic value and a characteristic vector of the second template image by using a principal component analysis method based on the second template image, and storing the characteristic value and the characteristic vector of the second template image in a template characteristic database.
In this embodiment, a specific process of generating the template feature database by principal component analysis is to assume that an image has n rows and m columns, and form an n row and m column matrix X from the image according to the columns; zero-averaging each row of X (representing an attribute field), i.e. subtracting the average of this row; solving a covariance matrix C =1/m × XXT; solving the eigenvalue of the covariance matrix and the corresponding eigenvector; arranging the eigenvectors into a matrix from top to bottom according to the size of the corresponding eigenvalue, and taking the first k rows to form a matrix P; y = PX is data after dimensionality reduction
Further, in an embodiment, the step of obtaining the residual map by using the ET algorithm based on the detection image and the reference image includes:
calculating to obtain a gray value of the detected image and a gradient value of the detected image according to the detected image and the reference image; gray values of the reference image and gradient values of the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
In this embodiment, the formula of the ET algorithm is:
Rmax(x , y) = R (x, y)+p {max (R(x -p, y -q))-R(x , y)}
Rmin(x , y) = R (x, y)- p {R(X, y)-min (R( x -p, y- q))}
Imax(x , y) = I (x, y)+p {max (I (x -p, y -q))- I (x , y)}
Imin(x , y) = I (x, y)- p { I (X, y)-min (I ( x -p, y- q))}
r represents a reference image, I represents a detection image, (x, y) represents row-column coordinates in the image, p, q are weight coefficients with the value range of (-1, 1), and max and min represent the maximum value and the minimum value respectively
The generation formula of the ghost image is as follows:
Rresult(x,y)=（Rmax(x , y)- Rmin(x , y)）-（Imax(x , y) - Imin(x , y)）
further, in an embodiment, before the step of calculating the gray-level value of the detected image, the gradient value of the detected image, the gray-level value of the reference image, and the gradient value of the reference image according to the detected image and the reference image, the method further includes:
and registering the detection image and the reference image by adopting a cross-correlation algorithm.
In this embodiment, a normalized cross-correlation-NCC algorithm is required for registration of the detection image and the reference image, and the NCC is an algorithm for calculating the correlation between two sets of sample data based on statistics. Registration is the acquisition of overlapping portions of the detection image and the reference image.
The first embodiment of the invention relates to a Mini LED product defect detection method and related equipment, wherein the method comprises the following steps: acquiring a Mini LED product image and taking the Mini LED product image as a detection image; selecting a template characteristic database corresponding to the Mini LED product, inputting a detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library; based on the detection image and the reference image, obtaining a residual image by utilizing an ET algorithm; and marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points. The first embodiment of the invention can effectively improve the real defect detection rate of the Mini LED product and can reduce the false defect detection frequency.
In a second aspect, the embodiment of the invention further provides a device for detecting the defect of the Mini LED product.
Referring to fig. 2, a functional module of a defect detection apparatus for Mini LED products in a first embodiment is shown.
In this embodiment, the Mini LED product defect detecting apparatus includes:
the acquisition module 10 is used for acquiring the image of the Mini LED product and taking the image of the Mini LED product as a detection image;
the first control module 20 is used for selecting a template characteristic database corresponding to the Mini LED product, inputting the detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using the function library;
a second control module 30, configured to obtain a residual image by using an ET algorithm based on the detection image and the reference image;
and the detection module 40 is configured to mark pixel points in the ghost image, whose gray values are greater than the threshold, as defective points, and mark pixel points, whose gray values are not greater than the threshold, as non-defective points.
Further, in an embodiment, the Mini LED product defect detecting apparatus further includes a generating module, where the generating module is configured to:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
Further, in an embodiment, the second control module 30 is further configured to:
calculating to obtain a gray value of the detection image, a gradient value of the detection image, a gray value of the reference image and a gradient value of the reference image according to the detection image and the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
Further, in an embodiment, the generating module is further configured to:
and obtaining a characteristic value and a characteristic vector of the second template image by using a principal component analysis method based on the second template image, and storing the characteristic value and the characteristic vector of the second template image in a template characteristic database.
Further, in an embodiment, the Mini LED product defect detecting apparatus further includes a registration module, and the registration module is configured to register the detected image and the reference image by using a cross-correlation algorithm.
The function realization of each module in the Mini LED product defect detection device corresponds to each step in the Mini LED product defect detection method embodiment, and the function and realization process are not described in detail herein.
In a third aspect, an embodiment of the present invention provides a Mini LED product defect detecting apparatus, where the Mini LED product defect detecting apparatus may be an apparatus having a data processing function, such as a Personal Computer (PC), a notebook computer, and a server.
Referring to fig. 3, fig. 3 is a schematic diagram of a hardware structure of an xx device according to an embodiment of the present invention. In this embodiment of the present invention, the Mini LED product defect detecting apparatus may include a processor 1001 (e.g., a Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used for realizing connection communication among the components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WI-FI interface, WI-FI interface); the memory 1005 may be a Random Access Memory (RAM) or a non-volatile memory (non-volatile memory), such as a magnetic disk memory, and the memory 1005 may optionally be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration shown in fig. 3 is not intended to be limiting of the present invention and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
With continued reference to fig. 3, the memory 1005 of fig. 3, which is one type of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a Mini LED product defect detection program. The processor 1001 may call a Mini LED product defect detection program stored in the memory 1005, and execute the Mini LED product defect detection method provided by the embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a readable storage medium.
The readable storage medium of the present invention stores a Mini LED product defect detection program, wherein when the Mini LED product defect detection program is executed by a processor, the steps of the Mini LED product defect detection method as described above are implemented.
The method for implementing the Mini LED product defect detection program when executed can refer to the embodiments of the Mini LED product defect detection method of the present invention, and is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for causing a terminal device to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A Mini LED product defect detection method is characterized by comprising the following steps:
acquiring a Mini LED product image and taking the Mini LED product image as a detection image;
selecting a template characteristic database corresponding to the Mini LED product, inputting a detection image into the template characteristic database corresponding to the Mini LED product, and obtaining a reference image by using a function library;
based on the detection image and the reference image, obtaining a residual image by utilizing an ET algorithm;
and marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points.
2. The method for defect inspection of a Mini LED product of claim 1, wherein prior to the step of acquiring the image of the Mini LED product and using the image of the Mini LED product as the inspection image, further comprising:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
3. The method of claim 2, wherein the step of obtaining the template feature database using the second template image comprises:
and obtaining a characteristic value and a characteristic vector of the second template image by using a principal component analysis method based on the second template image, and storing the characteristic value and the characteristic vector of the second template image in a template characteristic database.
4. The method for detecting the defect of the Mini LED product according to claim 1, wherein the step of obtaining the residual image by the ET algorithm based on the detection image and the reference image comprises:
calculating to obtain a gray value of the detection image, a gradient value of the detection image, a gray value of the reference image and a gradient value of the reference image according to the detection image and the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
5. The Mini LED product defect detecting method of claim 4, wherein before the step of calculating the gray-level value of the detected image, the gradient value of the detected image, the gray-level value of the reference image and the gradient value of the reference image according to the detected image and the reference image, further comprising:
and registering the detection image and the reference image by adopting a cross-correlation algorithm.
6. The Mini LED product defect detection device is characterized by comprising the following components:
the acquisition module is used for acquiring the image of the Mini LED product and taking the image of the Mini LED product as a detection image;
the first control module is used for selecting a template characteristic database corresponding to the Mini LED product, inputting the detection image into the template characteristic database corresponding to the Mini LED product and obtaining a reference image by using the function library;
the second control module is used for obtaining a residual image by utilizing an ET algorithm based on the detection image and the reference image;
and the detection module is used for marking the pixel points with the gray values larger than the threshold value in the ghost image as defect points, and marking the pixel points with the gray values not larger than the threshold value as non-defect points.
7. The Mini LED product defect inspection apparatus of claim 6, wherein the Mini LED product defect inspection apparatus further comprises a generation module, the generation module is configured to:
acquiring Mini LED product images in real time and classifying according to product types;
calibrating and noise-filtering the images of the Mini LED products of all types to obtain a first template image corresponding to each type of Mini LED product;
removing the defective image in the first template image to obtain a second template image;
and obtaining a template feature database based on the second template image.
8. The Mini LED product defect detection apparatus of claim 6, wherein the second control module is further configured to:
calculating to obtain a gray value of the detection image, a gradient value of the detection image, a gray value of the reference image and a gradient value of the reference image according to the detection image and the reference image;
and obtaining a residual image by utilizing an ET algorithm based on the gray value of the detection image, the gradient value of the detection image, the gray value of the reference image and the gradient value of the reference image.
9. A Mini LED product defect inspection apparatus, wherein the Mini LED product defect inspection apparatus comprises a processor, a memory, and a Mini LED product defect inspection program stored on the memory and executable by the processor, wherein the Mini LED product defect inspection program when executed by the processor implements the steps of the Mini LED product defect inspection method of any of claims 1 to 5.
10. A readable storage medium, on which a Mini LED product defect detection program is stored, wherein the Mini LED product defect detection program, when executed by a processor, implements the steps of the Mini LED product defect detection method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444639.5A CN113870255B (en) | 2021-11-30 | 2021-11-30 | Mini LED product defect detection method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444639.5A CN113870255B (en) | 2021-11-30 | 2021-11-30 | Mini LED product defect detection method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113870255A true CN113870255A (en) | 2021-12-31 |
| CN113870255B CN113870255B (en) | 2022-03-15 |
Family
ID=78985448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111444639.5A Active CN113870255B (en) | 2021-11-30 | 2021-11-30 | Mini LED product defect detection method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870255B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200234420A1 (en) * | 2019-01-17 | 2020-07-23 | Beijing Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for detecting image defects, computing device, and computer readable storage medium |
| CN112599438A (en) * | 2021-03-03 | 2021-04-02 | 惠州高视科技有限公司 | High-precision detection system and detection method for MiniLED wafer defects |
| CN113674273A (en) * | 2021-09-16 | 2021-11-19 | 深圳市光明顶照明科技有限公司 | Optical detection method and system based on product defects and readable storage medium |
-
2021
- 2021-11-30 CN CN202111444639.5A patent/CN113870255B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200234420A1 (en) * | 2019-01-17 | 2020-07-23 | Beijing Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for detecting image defects, computing device, and computer readable storage medium |
| CN112599438A (en) * | 2021-03-03 | 2021-04-02 | 惠州高视科技有限公司 | High-precision detection system and detection method for MiniLED wafer defects |
| CN113674273A (en) * | 2021-09-16 | 2021-11-19 | 深圳市光明顶照明科技有限公司 | Optical detection method and system based on product defects and readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| DOMEN TABERNIK,ET AL: "Segmentation-based deep-learning approach for surface-defect detection", 《JOURNAL OF INTELLIGENT MANUFACTURING》 * |
| 王标 等: "改进型Faster R-CNN网络在电子元件LED气泡缺陷检测中的应用", 《电子测量与仪器学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113870255B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6678414B1 (en) | Loose-gray-scale template matching | |
| US7978903B2 (en) | Defect detecting method and defect detecting device | |
| JP2005529388A (en) | Pattern inspection method | |
| KR20060051443A (en) | Defect detection apparatus and defect detection method | |
| JP4769764B2 (en) | Input method for entering points into the system, setting method, calibration method | |
| KR100734935B1 (en) | Area segmentation of an image | |
| US20020076107A1 (en) | Document image segmentation using loose gray scale template matching | |
| CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
| CN114972173A (en) | Defect detection method, defect detection device and system | |
| KR100336904B1 (en) | Failure analyzing method and apparatus | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| KR20210086303A (en) | Pattern inspection apparatus based on deep learning and inspection method using the same | |
| US5881164A (en) | Image data processing method and image data processing apparatus | |
| Ramesh et al. | Digital image processing of photoelastic fringes—a new approach | |
| JP2006113073A (en) | System and method for pattern defect inspection | |
| JP2005165387A (en) | Method and device for detecting stripe defective of picture and display device | |
| CN113870255B (en) | Mini LED product defect detection method and related equipment | |
| CN117274258A (en) | Method, system, equipment and storage medium for detecting defects of main board image | |
| CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
| JP3127598B2 (en) | Method for extracting density-varying constituent pixels in image and method for determining density-fluctuation block | |
| RU2346331C1 (en) | Method of automatic estimate of lcd data display correctness | |
| JP3279099B2 (en) | Mark recognition device and mark recognition method | |
| JP2004219291A (en) | Line defect detection method and device for screen | |
| CN113362781A (en) | Brightness compensation method and brightness compensation system of display panel | |
| JP2004239870A (en) | Spatial filter, method and program for generating the same, and method and apparatus for inspecting screen defect |
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 |