CN114519714B - Method and system for judging smudgy defect of display screen - Google Patents
Method and system for judging smudgy defect of display screen Download PDFInfo
- Publication number
- CN114519714B CN114519714B CN202210413304.5A CN202210413304A CN114519714B CN 114519714 B CN114519714 B CN 114519714B CN 202210413304 A CN202210413304 A CN 202210413304A CN 114519714 B CN114519714 B CN 114519714B
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- gray
- threshold value
- width
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
Abstract
The invention discloses a method and a system for judging the smudgy defect of a display screen, which comprises the following steps: acquiring a segmentation threshold of a defect image; acquiring a mean value filtering image of the defect image; calculating the gray average value difference of the bright and dark regions, and determining the bright and dark properties of the defects; acquiring defect characteristic parameters according to the brightness and darkness attributes of the defects; and judging whether the defect belongs to dirt or not. The result of the processing method is reliable, and the method is suitable for judging the dirt defects of similar display screens.
Description
Technical Field
The invention belongs to the technical field of computer vision detection, and particularly relates to a method and a system for judging the smudgy defect of a display screen.
Background
Computer vision inspection is widely applied in the field of object inspection, and the computer vision inspection technology has the advantages of high speed, high efficiency, high precision, integration and the like, and gradually becomes a main method for inspection in various industries. The method is widely applied to the fields of flat plate detection, circuit board detection, workpiece detection and the like. The invention aims at judging the dirt defect of a display screen. Similar patents have been directed to a method for detecting contamination of a liquid crystal display, and for example, patent application No. CN202010280491.5 discloses a method and an apparatus for detecting contamination of a screen of a liquid crystal display, which pre-select a contaminated area through the screen, then perform connected area search, calculate an average gray value of each connected area, and use the average gray values of all connected areas as a final evaluation value to evaluate the contamination degree of a defect. And removing textures of the actual detection area, enhancing the image, acquiring a gray threshold of the dirty area by using the information entropy, and taking the area with the gray value smaller than the gray threshold in the enhanced image as the dirty area.
The defects of the invention patent are as follows: first, a known dirty region needs to be selected, and a detection unknown region is determined by an evaluation value of the region, which easily causes erroneous judgment if the selected dirty region and the detection region have large differences in image texture. Secondly, using texture filtering results in partial defect signal loss. Finally, searching for connected regions has no explicit search rules. This results in a search that is not directional.
Disclosure of Invention
Based on the defects of the current display screen defect judgment, the invention provides a method for judging the contamination defect of a display screen. Firstly, acquiring a segmentation threshold of a defect image; carrying out mean value filtering on the defect image to obtain a mean value filtering image; determining the light and dark properties of the defect; acquiring defect characteristic parameters; and judging whether the defect belongs to dirt or not according to the defect characteristic parameters.
Specifically, the invention provides a method for judging the smudgy defect of a display screen, which comprises the following steps of:
acquiring a segmentation threshold of a defect image;
acquiring a mean value filtering image of the defect image;
calculating the gray average value difference of the bright and dark regions, and determining the bright and dark properties of the defects;
acquiring defect characteristic parameters according to the brightness and darkness attributes of the defects;
and judging whether the defect belongs to dirt or not.
Further, the segmentation threshold process for acquiring the defect image is as follows:
and acquiring a segmentation threshold of the defect image in real time by adopting a maximum inter-class variance method.
Further, the process of obtaining the mean value filtering image of the defect image is as follows:
and (4) adopting a 3X3 mean filter to the defect image to obtain a mean filter image of the defect image.
Further, the process of determining the light and dark properties of the defect is as follows:
A) presetting a defect image into a bright area and a dark area; if the length and the width of the defect image are both larger than 30 pixels, the horizontal starting position of the bright area is 1/6 of the width of the defect image, the vertical starting position is 1/6 of the height of the defect image, the horizontal ending position is 5/6 of the width of the defect image, the vertical ending position is 5/6 of the height of the defect image, and the rest areas are dark areas; if at least one of the length and the width of the defect image is less than or equal to 30 pixels, the horizontal starting position of the bright area is 1/4 of the width of the defect image, the vertical starting position is 1/4 of the height of the defect image, the horizontal ending position is 3/4 of the width of the defect image, the vertical ending position is 3/4 of the height of the defect image, and the rest are dark areas;
B) and respectively calculating the gray average values of the bright area and the dark area, wherein if the gray average value of the bright area is greater than that of the dark area, the defect is a bright defect, and otherwise, the defect is a dark defect.
Further, the method for obtaining the defect characteristic parameters comprises the following steps:
A) if the gray level average value difference of the bright area and the dark area is more than 3 and the defect is a bright defect, the threshold value of the defect image binaryzation is 3 more than the segmentation threshold value T obtained by adopting the maximum inter-class variance method, otherwise, the threshold value of the defect image binaryzation is 3 less than the segmentation threshold value T obtained by adopting the maximum inter-class variance method;
B) binarizing the defect image according to the binarized threshold value of the defect image, searching the position of a seed point from the binary image until a pixel point with any gray scale of 255 is found, and recording the coordinate of the pixel point at the moment;
C) acquiring a defect connected image; taking pixel points at the same positions as the pixel points in the mean filtering image as seed points, adopting an eight-neighborhood region growing method, namely, eight pixel points which are nearest to the seed points are searched according to a set gray scale difference threshold value, searching the pixel points of which the gray scale difference with the seed points is within a gray scale difference threshold value range, obtaining the position coordinates of the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range, taking the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range as new seed points to be searched next time, and repeating the steps until no pixel point meets the gray scale difference threshold value, and stopping searching; setting initial gray values of all pixel points of the defect communicated image to be 0, acquiring all points with gray-scale differences smaller than a gray-scale difference threshold value from the seed points, then marking the gray values of all the points with gray-scale differences smaller than the gray-scale difference threshold value from the seed points in the defect communicated image as 255, and setting the gray values of the rest pixel points to be 0, and finally acquiring the defect communicated image;
D) extracting a skeleton of the defect connected image;
E) acquiring the average line width of the defects; counting the number of all pixel points with the gray value of 255 in the defect connected image, namely the defect area; the average line width of the defect is represented by the ratio F1 of the defect area to the skeleton length;
F) the ratio F2 of the skeleton length to the average line width F1 is used for indicating whether the defect belongs to a long defect or a short defect;
G) acquiring the bending degree of the defect image; in the defect connected image, in all pixel point coordinates with the gray value of 255, the difference between the maximum value and the minimum value of the transverse coordinate is the length of the defect circumscribed rectangle, and the difference between the maximum value and the minimum value of the longitudinal coordinate is the width of the defect circumscribed rectangle; the larger of the length and width of the rectangle circumscribing the defect is obtained, and the degree of curvature of the defect is expressed by the ratio F3 between the absolute value of the difference between the length of the skeleton and the larger of the length and width of the defect and the length of the skeleton.
Further, the method for determining whether the defect belongs to the contamination is as follows:
and when the F2 and the F3 are simultaneously larger than the set judgment threshold value, judging the defect to be dirty, otherwise, judging the defect not to be dirty.
According to another aspect of the present invention, the present invention further provides an electronic device, which includes a memory, a processor and a computer program stored in and executable on the memory, wherein the processor executes the program to implement the method for determining the smudge defect of the display screen.
According to another aspect of the invention, a non-transitory computer readable storage medium has stored thereon a computer program which is executed by a processor to implement the method for display screen smudge defect determination as described above.
Compared with the prior art, the invention has the beneficial effects that: firstly, acquiring a segmentation threshold of a defect image; carrying out mean value filtering on the defect image to obtain a mean value filtering image; determining the light and dark properties of the defect; acquiring defect characteristic parameters; and judging whether the defect belongs to dirt or not according to the defect characteristic parameters. The result of the processing method is reliable, and the method is suitable for judging the dirt defects of similar display screens.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of an embodiment of a method for determining a contamination defect of a display screen according to the present invention;
FIG. 2 is an exemplary display screen smudge defect determination defect image of the present invention;
FIG. 3 is a system diagram of the dirty defect determination of a display screen according to the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a storage medium according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example 1
As shown in fig. 1, the present invention is directed to a display screen smudge defect determination. The calculation process is as follows:
1. obtaining a segmentation threshold for a defect image
And acquiring a segmentation threshold T of the defect image in real time by adopting a maximum inter-class variance method.
2. Obtaining mean filtered images
And (4) adopting a 3X3 mean filter for the defect image to obtain a mean filtered image of the defect image.
3. Determining light and dark properties of defects
A) The defect image is preset as a bright area and a dark area. If the defect image length and width are both greater than 30 pixels, the bright area starts at 1/6 where the defect image width is wide, starts at 1/6 where the defect image height is vertical, ends at 5/6 where the defect image width is horizontal, ends at 5/6 where the defect height is vertical, and the rest areas are dark areas. If at least one of the length and the width of the defect image is less than or equal to 30 pixels, the horizontal starting position of the bright area is 1/4 of the width of the defect image, the vertical starting position is 1/4 of the height of the defect image, the horizontal ending position is 3/4 of the width of the defect image, the vertical ending position is 3/4 of the height of the defect image, and the rest are dark areas;
B) and respectively calculating the gray average values of the bright area and the dark area, wherein if the gray average value of the bright area is greater than that of the dark area, the defect is a bright defect, and otherwise, the defect is a dark defect.
4. Obtaining defect characteristic parameters
A) If the gray level average difference of the bright area and the dark area is more than 3 and the defect is a bright defect, the threshold value of the defect image binaryzation is 3 larger than the segmentation threshold value T acquired by adopting the maximum inter-class variance method, otherwise, the threshold value of the defect image binaryzation is 3 smaller than the segmentation threshold value T acquired by adopting the maximum inter-class variance method;
B) binarizing the defect image from the obtained binarization threshold value of the defect image, searching the position of a seed point from the binary image, and recording the coordinate of the pixel point p at the moment only by finding out any pixel point with the gray scale of 255;
C) and acquiring a defect connected image. And taking pixel points at the same positions as the pixel points p in the mean filtering image as seed points, searching pixel points with the gray scale difference of the seed points within the range of the gray scale difference threshold value according to the set gray scale difference threshold value 6 by adopting an eight-neighborhood region growing method, namely searching the pixel points which are closest to the seed points, acquiring the position coordinates of the pixel points, taking the pixel points as new seed points for the next search, and repeating the steps until no pixel point meets the gray scale difference threshold value. Setting initial gray values of all pixel points of the defect connected image to be 0, acquiring all points of which the gray-scale difference from the seed points is smaller than a gray-scale difference threshold, marking the corresponding gray values of the points in the defect connected image to be 255, and setting the gray values of the rest pixel points to be 0, so as to finally acquire the defect connected image;
D) extracting a skeleton of the defect connected image;
E) and acquiring the average line width of the defects. And counting the number of all pixel points with the gray value of 255 in the defect connected image, namely the defect area. The average line width of the defect is represented by the ratio F1 of the defect area to the skeleton length;
F) the ratio F2 of the length of the framework to the average line width F1 is used for indicating whether the defect belongs to a long defect or a short defect;
G) the degree of curvature of the defect image is acquired. In the defect connected image, in all pixel point coordinates with the gray value of 255, the difference between the maximum value and the minimum value of the transverse coordinate is the length of the defect circumscribed rectangle, and the difference between the maximum value and the minimum value of the longitudinal coordinate is the width of the defect circumscribed rectangle. The larger of the length and width of the rectangle circumscribing the defect is obtained, and the degree of curvature of the defect is expressed by the ratio F3 between the absolute value of the difference between the length of the skeleton and the larger of the length and width of the defect and the length of the skeleton.
5. Determining whether the defect belongs to dirt
The judgment thresholds of F2 and F3 are set to 4 and 0.5 respectively, when F2 and F3 are simultaneously larger than the set judgment threshold, the defect is judged to be dirty, otherwise, the defect is judged not to be dirty.
Example 2
The present embodiment provides a system for determining a dirty defect on a display screen, as shown in fig. 3, including:
an obtaining segmentation threshold module 100, configured to obtain a threshold for defect image segmentation;
an average filtering image obtaining module 200 configured to obtain an average filtering preprocessed image;
a determine light and dark attributes of the defect module 300, configured to determine light and dark attributes of the defect;
a defect feature parameter obtaining module 400, configured to obtain defect feature parameters;
and a defect determining module 500, configured to determine whether the defect belongs to a stain.
According to another aspect of the present invention, the present invention further provides a computer program stored in the memory and executable on the memory, and a processor executing the program to implement the method for determining the dirtiness defect of the display screen.
According to another aspect of the present invention, there is also provided a non-transitory computer readable storage medium having stored thereon a computer program, which is executed by a processor, to implement the method for determining a contamination defect of a display screen as described above.
Compared with the prior art, the invention has the beneficial effects that: firstly, acquiring a segmentation threshold of a defect image; carrying out mean value filtering on the defect image to obtain a mean value filtering image; determining the light and dark properties of the defect; acquiring defect characteristic parameters; and judging whether the defect belongs to dirt or not according to the defect characteristic parameters. The result of the processing method is reliable, and the method is suitable for judging the dirt defects of similar display screens.
The embodiment of the invention also provides electronic equipment corresponding to the method for judging the pollution defect of the display screen, which is provided by the embodiment, so as to execute the method for judging the pollution defect of the upper display screen. The embodiments of the present invention are not limited.
Referring to fig. 4, a schematic diagram of an electronic device according to some embodiments of the invention is shown. As shown in fig. 4, the electronic device 20 includes: the system comprises a processor 200, a memory 201, a bus 202 and a communication interface 203, wherein the processor 200, the communication interface 203 and the memory 201 are connected through the bus 202; the memory 201 stores a computer program that can be executed on the processor 200, and the processor 200 executes the method for determining the dirty defect of the display screen according to any of the foregoing embodiments when executing the computer program.
The Memory 201 may include a high-speed Random Access Memory (RAM) and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The processor 200 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 200. The Processor 200 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the method in combination with the hardware thereof.
The electronic equipment provided by the embodiment of the invention and the method for judging the dirtiness defect of the display screen provided by the embodiment of the invention have the same inventive concept and have the same beneficial effects as the method adopted, operated or realized by the electronic equipment.
The embodiment of the present invention further provides a computer readable storage medium corresponding to the method for determining a dirty defect of a display screen provided in the foregoing embodiment, please refer to fig. 5, which illustrates the computer readable storage medium being an optical disc 30, on which a computer program (i.e., a program product) is stored, and when the computer program is executed by a processor, the computer program will execute the method for determining a dirty defect of a display screen provided in any of the foregoing embodiments.
It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, or other optical and magnetic storage media, which are not described in detail herein.
The computer-readable storage medium provided by the above embodiment of the present invention and the method for determining the smudgy defect of the display screen provided by the embodiment of the present invention have the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by the application program stored in the computer-readable storage medium.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Claims (7)
1. A method for judging the dirt defect of a display screen is characterized by comprising the following steps:
acquiring a segmentation threshold of a defect image;
obtaining a mean value filtering image of the defect image;
calculating the gray average value difference of the bright and dark regions, and determining the bright and dark properties of the defects, wherein the process is as follows:
A) presetting a defect image into a bright area and a dark area; if the length and the width of the defect image are both larger than 30 pixels, the horizontal starting position of the bright area is 1/6 of the width of the defect image, the vertical starting position is 1/6 of the height of the defect image, the horizontal ending position is 5/6 of the width of the defect image, the vertical ending position is 5/6 of the height of the defect image, and the rest areas are dark areas; if at least one of the length and the width of the defect image is less than or equal to 30 pixels, the horizontal starting position of the bright area is 1/4 of the width of the defect image, the vertical starting position is 1/4 of the height of the defect image, the horizontal ending position is 3/4 of the width of the defect image, the vertical ending position is 3/4 of the height of the defect image, and the rest are dark areas;
B) respectively calculating the gray average values of the bright area and the dark area, if the gray average value of the bright area is greater than that of the dark area, determining that the defect is a bright defect, otherwise, determining that the defect is a dark defect;
acquiring defect characteristic parameters according to the brightness attributes of the defects, wherein the method comprises the following steps:
A) if the gray level average value difference of the bright area and the dark area is more than 3 and the defect is a bright defect, the threshold value of the defect image binaryzation is 3 more than the segmentation threshold value T obtained by adopting the maximum inter-class variance method, otherwise, the threshold value of the defect image binaryzation is 3 less than the segmentation threshold value T obtained by adopting the maximum inter-class variance method;
B) binarizing the defect image according to the binarized threshold value of the defect image, searching the position of a seed point from the binary image until a pixel point with any gray scale of 255 is found, and recording the coordinate of the pixel point at the moment;
C) acquiring a defect connected image; taking pixel points at the same positions as the pixel points in the mean filtering image as seed points, adopting an eight-neighborhood region growing method, namely, eight pixel points which are nearest to the seed points are searched according to a set gray scale difference threshold value, searching the pixel points of which the gray scale difference with the seed points is within a gray scale difference threshold value range, obtaining the position coordinates of the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range, taking the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range as new seed points to be searched next time, and repeating the steps until no pixel point meets the gray scale difference threshold value, and stopping searching; setting initial gray values of all pixel points of the defect communicated image to be 0, acquiring all points with gray-scale differences smaller than a gray-scale difference threshold value from the seed points, then marking the gray values of all the points with gray-scale differences smaller than the gray-scale difference threshold value from the seed points in the defect communicated image as 255, and setting the gray values of the rest pixel points to be 0, and finally acquiring the defect communicated image;
D) extracting a skeleton of the defect connected image;
E) acquiring the average line width of the defects; counting the number of all pixel points with the gray value of 255 in the defect connected image, wherein the pixel points are the defect area; the average line width of the defect is represented by the ratio F1 of the defect area to the skeleton length;
F) the ratio F2 of the skeleton length to the average line width F1 is used for indicating whether the defect belongs to a long defect or a short defect;
G) acquiring the bending degree of the defect image; in the defect connected image, in all pixel point coordinates with the gray value of 255, the difference between the maximum value and the minimum value of the transverse coordinate is the length of the defect circumscribed rectangle, and the difference between the maximum value and the minimum value of the longitudinal coordinate is the width of the defect circumscribed rectangle; acquiring the larger length and the larger width of the defect circumscribed rectangle, and representing the bending degree of the defect by using the ratio F3 of the absolute value of the difference between the length of the framework and the larger length and the width of the defect to the length of the framework;
and judging whether the defect belongs to dirt or not.
2. The method for determining the smudging defect of the display screen according to claim 1, wherein:
the process of obtaining the segmentation threshold of the defect image is as follows:
and acquiring a segmentation threshold of the defect image in real time by adopting a maximum inter-class variance method.
3. The method for determining the contamination defect of the display screen according to claim 1, wherein:
the process of obtaining the mean value filtering image of the defect image is as follows:
and (4) adopting a 3X3 mean filter to the defect image to obtain a mean filter image of the defect image.
4. The method for determining the smudging defect of the display screen according to claim 1, wherein:
the method for judging whether the defect belongs to the dirt is as follows:
and when the F2 and the F3 are simultaneously larger than the set judgment threshold value, judging the defect to be dirty, otherwise, judging the defect not to be dirty.
5. A system for determining a smudging defect of a display screen, comprising:
the acquisition segmentation threshold module is used for acquiring a segmentation threshold of the defect image;
the mean value filtering image obtaining module is used for obtaining a mean value filtering preprocessing image;
and the module for determining the bright and dark attributes of the defect is used for calculating the gray average value difference of the bright and dark areas and determining the bright and dark attributes of the defect, and the process is as follows:
A) presetting a defect image into a bright area and a dark area; if the length and the width of the defect image are both larger than 30 pixels, the horizontal starting position of the bright area is 1/6 of the width of the defect image, the vertical starting position is 1/6 of the height of the defect image, the horizontal ending position is 5/6 of the width of the defect image, the vertical ending position is 5/6 of the height of the defect image, and the rest areas are dark areas; if at least one of the length and the width of the defect image is less than or equal to 30 pixels, the horizontal starting position of the bright area is 1/4 of the width of the defect image, the vertical starting position is 1/4 of the height of the defect image, the horizontal ending position is 3/4 of the width of the defect image, the vertical ending position is 3/4 of the height of the defect image, and the rest are dark areas;
B) respectively calculating the gray average values of the bright area and the dark area, if the gray average value of the bright area is greater than that of the dark area, the defect is a bright defect, otherwise, the defect is a dark defect;
the module for obtaining the defect characteristic parameters is used for obtaining the defect characteristic parameters, and the method comprises the following steps:
A) if the gray level average value difference of the bright area and the dark area is more than 3 and the defect is a bright defect, the threshold value of the defect image binaryzation is 3 more than the segmentation threshold value T obtained by adopting the maximum inter-class variance method, otherwise, the threshold value of the defect image binaryzation is 3 less than the segmentation threshold value T obtained by adopting the maximum inter-class variance method;
B) binarizing the defect image according to the binarized threshold value of the defect image, searching the position of a seed point from the binary image until a pixel point with any gray scale of 255 is found, and recording the coordinate of the pixel point at the moment;
C) acquiring a defect connected image; taking pixel points at the same positions as the pixel points in the mean filtering image as seed points, adopting an eight-neighborhood region growing method, namely, eight pixel points which are nearest to the seed points are searched according to a set gray scale difference threshold value, searching the pixel points of which the gray scale difference with the seed points is within a gray scale difference threshold value range, obtaining the position coordinates of the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range, taking the pixel points of which the gray scale difference with the seed points is within the gray scale difference threshold value range as new seed points to be searched next time, and repeating the steps until no pixel point meets the gray scale difference threshold value, and stopping searching; setting initial gray values of all pixel points of the defect connected image to be 0, acquiring all points with gray-scale difference smaller than a gray-scale difference threshold value from the seed points, marking the gray values of all the points with gray-scale difference smaller than the gray-scale difference threshold value from the seed points to be 255 in the defect connected image, and setting the gray values of the rest pixel points to be 0, and finally acquiring the defect connected image;
D) extracting a skeleton of the defect connected image;
E) acquiring the average line width of the defects; counting the number of all pixel points with the gray value of 255 in the defect connected image, wherein the pixel points are the defect area; the average line width of the defect is represented by the ratio F1 of the defect area to the skeleton length;
F) the ratio F2 of the skeleton length to the average line width F1 is used for indicating whether the defect belongs to a long defect or a short defect;
G) acquiring the bending degree of the defect image; in the defect connected image, in all pixel point coordinates with the gray value of 255, the difference between the maximum value and the minimum value of the transverse coordinate is the length of the defect circumscribed rectangle, and the difference between the maximum value and the minimum value of the longitudinal coordinate is the width of the defect circumscribed rectangle; acquiring the larger length and width of the circumscribed rectangle of the defect, and expressing the bending degree of the defect by using the ratio F3 of the absolute value of the difference between the length of the framework and the larger length and width of the defect and the length of the framework;
and the defect judging module is used for judging whether the defect belongs to dirt.
6. An electronic device comprising a memory, a processor and a computer program stored on and executable on the memory, the processor executing the program to implement the method of determining a display screen smudge defect of any of claims 1-4.
7. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method for determining a display screen smudge defect of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210413304.5A CN114519714B (en) | 2022-04-20 | 2022-04-20 | Method and system for judging smudgy defect of display screen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210413304.5A CN114519714B (en) | 2022-04-20 | 2022-04-20 | Method and system for judging smudgy defect of display screen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114519714A CN114519714A (en) | 2022-05-20 |
| CN114519714B true CN114519714B (en) | 2022-07-26 |
Family
ID=81600460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210413304.5A Active CN114519714B (en) | 2022-04-20 | 2022-04-20 | Method and system for judging smudgy defect of display screen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114519714B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405661B (en) * | 2023-04-28 | 2023-09-29 | 可诺特软件(深圳)有限公司 | Smart television development performance testing method and device |
| CN116503382B (en) * | 2023-05-25 | 2023-10-13 | 中导光电设备股份有限公司 | Method and system for detecting scratch defects of display screen |
| CN117437232B (en) * | 2023-12-21 | 2024-03-26 | 山东心传矿山机电设备有限公司 | Water pump impeller appearance defect detection method and system based on image processing |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4974261A (en) * | 1988-11-15 | 1990-11-27 | Matsushita Electric Works, Ltd. | Optical surface inspection method |
| JPH07122193A (en) * | 1993-10-27 | 1995-05-12 | Toshiba Eng Co Ltd | Method and device for detecting defect |
| JPH10282063A (en) * | 1997-04-08 | 1998-10-23 | Nippon Steel Corp | Automatic inspection apparatus for surface flaw |
| JP2005181040A (en) * | 2003-12-18 | 2005-07-07 | Seiko Epson Corp | Defect detection method for display panel, its detection device, and manufacturing method for the display panel |
| JP2006047078A (en) * | 2004-08-04 | 2006-02-16 | Central Glass Co Ltd | Method for inspecting printing defect and/or printing contamination of transparent plate body |
| JP2008014842A (en) * | 2006-07-06 | 2008-01-24 | Seiko Epson Corp | Method and apparatus for detecting stain defects |
| JP2008170325A (en) * | 2007-01-12 | 2008-07-24 | Seiko Epson Corp | Stain flaw detection method and stain flaw detection device |
| JP2011008482A (en) * | 2009-06-25 | 2011-01-13 | Seiko Epson Corp | Defect detection method, defect detection device and defect detection program |
| KR20150014717A (en) * | 2013-07-30 | 2015-02-09 | (주)탑중앙연구소 | Image stain detection method for camera module defect determination |
| CN107643295A (en) * | 2017-08-24 | 2018-01-30 | 中国地质大学（武汉） | A kind of method and system of the cloth defect on-line checking based on machine vision |
| CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
| CN108709893A (en) * | 2018-03-30 | 2018-10-26 | 苏州佳智彩光电科技有限公司 | A kind of online defect inspection method of an AMOLED display screens point ball of string |
| CN109613023A (en) * | 2019-01-28 | 2019-04-12 | 西南大学 | A kind of fruit surface defect rapid detection method of regional luminance adaptively correcting |
| CN109752394A (en) * | 2019-01-28 | 2019-05-14 | 凌云光技术集团有限责任公司 | A kind of display screen defect high-precision detecting method and system |
| CN109949725A (en) * | 2019-03-06 | 2019-06-28 | 武汉精立电子技术有限公司 | A kind of AOI system image grayscale standardized method and system |
| CN110208269A (en) * | 2019-05-17 | 2019-09-06 | 惠州高视科技有限公司 | The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished |
| CN112630222A (en) * | 2020-11-24 | 2021-04-09 | 河海大学常州校区 | Mobile phone cover plate glass defect detection method based on machine vision |
| KR20210105185A (en) * | 2020-02-18 | 2021-08-26 | 동우 화인켐 주식회사 | Method for inspecting smudged defect |
| CN113390611A (en) * | 2021-05-27 | 2021-09-14 | 北京兆维科技开发有限公司 | Screen defect detection method |
| CN113888539A (en) * | 2021-12-06 | 2022-01-04 | 蓝思科技股份有限公司 | Defect classification method, device, equipment and storage medium |
| WO2022012240A1 (en) * | 2020-07-16 | 2022-01-20 | 京东方科技集团股份有限公司 | Method and device for detecting defect of display panel |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108683907B (en) * | 2018-05-31 | 2020-10-09 | 歌尔股份有限公司 | Optical module pixel defect detection method, device and equipment |
| CN109613004A (en) * | 2018-12-13 | 2019-04-12 | 武汉精立电子技术有限公司 | Defect display methods in a kind of inspection of backlight |
| CN111476758B (en) * | 2020-03-12 | 2023-04-25 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Defect detection method and device for AMOLED display screen, computer equipment and storage medium |
| CN111612781B (en) * | 2020-05-27 | 2023-07-14 | 歌尔光学科技有限公司 | Screen defect detection method and device and head-mounted display equipment |
-
2022
- 2022-04-20 CN CN202210413304.5A patent/CN114519714B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4974261A (en) * | 1988-11-15 | 1990-11-27 | Matsushita Electric Works, Ltd. | Optical surface inspection method |
| JPH07122193A (en) * | 1993-10-27 | 1995-05-12 | Toshiba Eng Co Ltd | Method and device for detecting defect |
| JPH10282063A (en) * | 1997-04-08 | 1998-10-23 | Nippon Steel Corp | Automatic inspection apparatus for surface flaw |
| JP2005181040A (en) * | 2003-12-18 | 2005-07-07 | Seiko Epson Corp | Defect detection method for display panel, its detection device, and manufacturing method for the display panel |
| JP2006047078A (en) * | 2004-08-04 | 2006-02-16 | Central Glass Co Ltd | Method for inspecting printing defect and/or printing contamination of transparent plate body |
| JP2008014842A (en) * | 2006-07-06 | 2008-01-24 | Seiko Epson Corp | Method and apparatus for detecting stain defects |
| JP2008170325A (en) * | 2007-01-12 | 2008-07-24 | Seiko Epson Corp | Stain flaw detection method and stain flaw detection device |
| JP2011008482A (en) * | 2009-06-25 | 2011-01-13 | Seiko Epson Corp | Defect detection method, defect detection device and defect detection program |
| KR20150014717A (en) * | 2013-07-30 | 2015-02-09 | (주)탑중앙연구소 | Image stain detection method for camera module defect determination |
| CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
| CN107643295A (en) * | 2017-08-24 | 2018-01-30 | 中国地质大学（武汉） | A kind of method and system of the cloth defect on-line checking based on machine vision |
| CN108709893A (en) * | 2018-03-30 | 2018-10-26 | 苏州佳智彩光电科技有限公司 | A kind of online defect inspection method of an AMOLED display screens point ball of string |
| CN109613023A (en) * | 2019-01-28 | 2019-04-12 | 西南大学 | A kind of fruit surface defect rapid detection method of regional luminance adaptively correcting |
| CN109752394A (en) * | 2019-01-28 | 2019-05-14 | 凌云光技术集团有限责任公司 | A kind of display screen defect high-precision detecting method and system |
| CN109949725A (en) * | 2019-03-06 | 2019-06-28 | 武汉精立电子技术有限公司 | A kind of AOI system image grayscale standardized method and system |
| CN110208269A (en) * | 2019-05-17 | 2019-09-06 | 惠州高视科技有限公司 | The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished |
| KR20210105185A (en) * | 2020-02-18 | 2021-08-26 | 동우 화인켐 주식회사 | Method for inspecting smudged defect |
| WO2022012240A1 (en) * | 2020-07-16 | 2022-01-20 | 京东方科技集团股份有限公司 | Method and device for detecting defect of display panel |
| CN112630222A (en) * | 2020-11-24 | 2021-04-09 | 河海大学常州校区 | Mobile phone cover plate glass defect detection method based on machine vision |
| CN113390611A (en) * | 2021-05-27 | 2021-09-14 | 北京兆维科技开发有限公司 | Screen defect detection method |
| CN113888539A (en) * | 2021-12-06 | 2022-01-04 | 蓝思科技股份有限公司 | Defect classification method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114519714A (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114519714B (en) | Method and system for judging smudgy defect of display screen | |
| CN108629775B (en) | Thermal state high-speed wire rod surface image processing method | |
| CN108896278B (en) | Optical filter silk-screen defect detection method and device and terminal equipment | |
| CN111612781A (en) | Screen defect detection method and device and head-mounted display equipment | |
| CN112577969B (en) | Defect detection method and defect detection system based on machine vision | |
| CN110334760B (en) | Optical component damage detection method and system based on RESUnet | |
| CN113160161B (en) | Method and device for detecting defects at edge of target | |
| CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
| CN114723677A (en) | Image defect detection method, image defect detection device, image defect detection equipment and storage medium | |
| CN110276759B (en) | Mobile phone screen bad line defect diagnosis method based on machine vision | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN112102253A (en) | Non-woven fabric surface defect automatic detection method and system based on machine vision | |
| CN116485764A (en) | Structural surface defect identification method, system, terminal and medium | |
| CN114677348A (en) | IC chip defect detection method and system based on vision and storage medium | |
| CN116309583B (en) | Method and system for detecting display screen dent defect | |
| CN116542963A (en) | Float glass defect detection system and detection method based on machine learning | |
| CN113902742B (en) | TFT-LCD detection-based defect true and false judgment method and system | |
| CN113888539B (en) | Defect classification method, device, equipment and storage medium | |
| CN115631190A (en) | Glass substrate defect identification warning method and system, electronic device and storage medium | |
| CN114445405B (en) | Method and system for detecting uniformity of circular hole | |
| CN111678673A (en) | Lens detection method, lens detection device and readable storage medium | |
| CN116503382B (en) | Method and system for detecting scratch defects of display screen | |
| CN113870754B (en) | Method and system for judging defects of panel detection electronic signals | |
| CN116500042B (en) | Defect detection method, device, system and storage medium | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision |
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 |