CN114255232B - LED display screen display defect detection method, electronic equipment and device - Google Patents
LED display screen display defect detection method, electronic equipment and device Download PDFInfo
- Publication number
- CN114255232B CN114255232B CN202210188796.2A CN202210188796A CN114255232B CN 114255232 B CN114255232 B CN 114255232B CN 202210188796 A CN202210188796 A CN 202210188796A CN 114255232 B CN114255232 B CN 114255232B
- Authority
- CN
- China
- Prior art keywords
- image
- defective
- display screen
- led display
- module
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Control Of Indicators Other Than Cathode Ray Tubes (AREA)
Abstract
The invention discloses a method, electronic equipment and a device for detecting display defects of an LED display screen, belonging to the field of quality inspection of the LED display screen, wherein the method comprises the steps of obtaining a picture when the LED display screen displays pure colors; identifying a frame of the LED display screen in the image, and selecting the image in the frame as a second image; dividing the second image into a plurality of third images according to the arrangement mode of the splicing modules in the LED display screen; screening out the defective third image, and recording a defective splicing module corresponding to the defective third image; the method reduces the identification and settlement of the non-defective splicing module and conveniently and quickly finds the defective position, the resolution ratio of the splicing module is much lower than that of the whole LED display screen, the defective splicing module is identified first, then the defect of the splicing module is separately positioned, the operation complexity can be reduced, and the detection speed is improved.
Description
Technical Field
The invention relates to a method, electronic equipment and a device for detecting display defects of an LED display screen, and belongs to the field of quality inspection of the LED display screen.
Background
The method used for detecting the defects of the LED display screen at present generally comprises the steps of enabling the display screen to display a specific pattern, shooting a displayed picture by a camera, analyzing the shot image, detecting whether the display screen has the defects or not through all pixel points. The method ignores the characteristics of the LED display screen, and directly takes the whole display screen as a detection object. In fact, a complete LED display screen is usually formed by splicing a plurality of display modules (mostly boxes) with resolution of 240X180 or 320X240, and the detection method in the prior art ignores the modularity of the LED display screen, has low detection efficiency, and is difficult to locate after detecting defects.
Disclosure of Invention
Aiming at the modularity of the LED display screen, the unit module where the defect is located is identified, and then the defect of the unit module is independently positioned.
In a first aspect, the present application provides a method for detecting display defects of an LED display screen, including the following steps:
obtaining a picture when the LED display screen displays a pure color to obtain a first image;
identifying a frame of the LED display screen in the first image, and selecting an image in the frame as a second image;
dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen;
screening out a defective third image, and recording a defective splicing module corresponding to the defective third image;
and judging the defect type of the defective third image, and positioning the defect position of the defective splicing module.
According to the LED display screen display defect detection method, the defective splicing module is found out firstly, then the defect type of the defective module is judged, the position of the defect is located, the identification and settlement of the non-defective splicing module are reduced, and the detection efficiency can be improved.
Further, the step of obtaining the picture of the LED display screen displaying the pure color to obtain the first image includes:
acquiring pictures of the LED display screen displaying red, green and blue to obtain three first images;
the step of identifying the frame of the LED display screen in the first image and selecting the image in the frame as the second image comprises the following steps:
identifying frames of the LED display screen in the three first images to obtain three first frame information;
combining the three first frame information to obtain second frame information;
and selecting a local image in the three first images according to the second frame information to generate three second images.
Each pixel of the LED display screen is composed of red, green and blue sub-pixels, and the detection is performed once when the display screen displays the three colors, so that whether the LED display screen has a display defect can be accurately judged.
Further, the step of obtaining the picture of the LED display screen displaying the pure color to obtain the first image includes:
acquiring pictures of the LED display screen displaying white, red, green and blue to obtain four first images;
the step of identifying the frame of the LED display screen in the first image and selecting the image in the frame as the second image comprises the following steps:
identifying the frames of the LED display screen in the four first images to obtain four first frame information;
combining the four pieces of first frame information to obtain second frame information;
and selecting local images in the four first images according to the second frame information to generate four second images.
Further, the screening out the defective third image and the recording of the defective stitching module corresponding to the defective third image comprises:
numbering the third images according to the arrangement mode of the splicing modules in the LED display screen;
detecting each third image to detect a defective third image;
the number of the defective third image is recorded.
The defect position generated finally is formed by the serial number of the splicing module and the pixel position of the splicing module, so that the defect position can be conveniently and quickly found out when the defect is repaired.
Further, the screening out the defective third image and the recording the defective stitching module corresponding to the defective third image comprises:
detecting each third image to detect a defective third image;
determining a location of the defective third image in the second image;
recording a defective stitching module corresponding to the defective third image.
Further, said detecting each of said third images, the step of detecting a defective third image comprising:
acquiring the brightness, the chroma and the saturation of each pixel of the third image;
calculating the mean square error of brightness, the mean square error of chroma and the mean square error of saturation of each third image;
selecting the third image with the mean square error of luminance, the mean square error of chrominance and the mean square error of saturation larger than the first value as a defective third image.
Further, the step of judging the type of the defect of the defective third image and locating the position of the defect of the defective splicing module includes:
identifying a defect contour and an internal feature distribution in the defective third image using a machine learning algorithm;
intersecting and comparing the defect contour and the internal feature distribution with an optimal feature set, and calculating matching probability;
and generating a defect type, a matching probability corresponding to the defect type and a position parameter corresponding to the defect type.
Further, before obtaining the first image from the picture when the pure color is displayed on the LED display screen, the method further includes the steps of:
acquiring a black image when the LED display screen is not lightened under uniform illumination in a dark field;
identifying a film defect in the black image.
In order to increase the contrast of the LED display screen, a black film is usually disposed in the LED display screen, and if the black film is locally oxidized and discolored, even if all pixels of the LED display screen are normal, a display defect is still detected, so that the problem of abnormal black film of the LED display screen is preferably eliminated.
In a second aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, perform the steps of the method according to any one of the first aspect.
In a third aspect, the present application provides an LED display screen display defect detecting apparatus, including:
the first acquisition module is used for acquiring a picture of the LED display screen displaying pure color to obtain a first image;
the frame identification module is used for identifying the frame of the LED display screen in the first image and selecting the image in the frame as a second image;
the first dividing module is used for dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen;
the screening module is used for screening out the defective third image and recording the defective splicing module corresponding to the defective third image;
and the judging and positioning module is used for judging the defect type of the defective third image and positioning the defect position of the defective splicing module.
The invention has the beneficial effects that: according to the method, pure color images displayed by the LED display screen are divided according to the arrangement mode of the splicing modules in the LED display screen, the defective splicing modules are firstly identified, then the defect types of the defective modules are judged, the defect positions are positioned, the identification settlement of the non-defective splicing modules is reduced, the detection efficiency can be improved, the defect positions can be conveniently and quickly found when the defects are repaired subsequently, the resolution ratio of the splicing modules is much lower than that of the whole LED display screen, the defective splicing modules are firstly identified, then the defects of the splicing modules are independently positioned, the operation complexity can be reduced, and the detection speed is improved.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
Fig. 1 is a flowchart of a method for detecting a display defect of an LED display screen according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a display defect detection apparatus for an LED display screen according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 4 is a schematic effect diagram of a second image provided in an embodiment of the present application.
Fig. 5 is a schematic effect diagram of a third image provided in an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
The following disclosure provides many different embodiments or examples for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples, such repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed.
According to the LED display screen display defect detection method in the prior art, the LED display screen is regarded as a whole, with the technical progress, the resolution ratio of the LED display screen on the market is higher and higher, and the LED display screen is regarded as a whole, whether the display defect exists is detected by using a machine learning algorithm, so that the calculation amount is large, the complexity is high, and the detection efficiency is low.
Referring to fig. 1, the application provides a method for detecting display defects of an LED display screen, comprising the following steps:
s1: and obtaining a picture when the LED display screen displays a pure color to obtain a first image.
Specifically, a high-precision camera which is overlooked and faces the production line is arranged on the quality inspection production line and is used for shooting a picture when an LED display screen displays a pure color (for example, white) and outputting a first image.
S2: and identifying a frame of the LED display screen in the first image, and selecting the image in the frame as a second image.
The first image includes the LED display screen and the quality inspection pipeline as a background, and step S2 is equivalent to cropping the first image, removing the background portion of the first image, and leaving only the portion of the LED display screen that emits light.
S3: and dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen.
The arrangement mode of the splicing modules comprises two acquisition methods, namely, the module types selected by the same batch of display screens are the same, and the splicing modes are the same, so that the arrangement mode of the splicing modules of the batch of display screens can be input in advance; and secondly, the display screen is made to emit light and needs to be electrified, and the arrangement mode of the splicing modules of the display screen can be known through the line signal feedback of the display screen.
S4: and screening out the defective third image, and recording the defective splicing module corresponding to the defective third image.
S5: and judging the defect type of the defective third image, and positioning the defect position of the defective splicing module.
In step S4, the defective mosaic module is already recorded, and only the pixel position of the mosaic module relative to the mosaic module, not the pixel position of the whole display screen, may be recorded when the defective mosaic module is located in step S5. Usually the resolution ratio of single concatenation module only is 240 pixel X180 pixel or 320 pixel X240 pixel, the pixel of whole display screen often reaches 4K, 8K, even the pixel position of whole display screen has been recorded, it is also very difficult according to the pixel position backtracking defect pixel of whole display screen when restoreing defect position, this application can indicate the defect at which concatenation module earlier, indicate what pixel position at this concatenation module again, make the maintenance personal find the pixel point that needs the restoration more easily.
The embodiment of the application divides the pure color image that the LED display screen shows according to the arrangement of concatenation module in the LED display screen, discern defective concatenation module earlier, carry out defect type judgement to defective module again, fix a position defective position, reduce the discernment settlement to nondefective concatenation module, can improve detection efficiency, the resolution ratio of concatenation module is much lower than the resolution ratio of whole LED display screen, discern defective concatenation module earlier, fix a position the defect of concatenation module alone again, can reduce the operation complexity, promote detection speed.
Each pixel of the LED display screen is composed of red, green and blue sub-pixels. When the LED display screen is made to display white, according to the above method, it is tested that if a single pixel of the LED display screen is defective, only one of the sub-pixels of the pixel may be defective, and the remaining two sub-pixels are normal, so a preferred embodiment is provided.
Step S1 becomes: and acquiring pictures of the LED display screen displaying red, green and blue to obtain three first images. This enables detection of each sub-pixel of the LED display screen. This also adds the added benefit of making it more accurate to identify the border of the LED display screen in the first image. Accordingly, step S2 specifically includes step S21: identifying frames of the LED display screen in the three first images to obtain three first frame information; s22: combining the three first frame information to obtain second frame information; s23: and selecting a local image from the three first images according to the second frame information to generate three second images. The color of the quality inspection assembly line is as simple as possible, the identification frame is prevented from being influenced, some parts of the quality inspection assembly line inevitably have colors influencing the identification frame, for example, metal parts can reflect light, a conveyor belt is usually green or black, the frame extracted by the display only through pure color luminescence is possibly not accurate enough, the frame of the display screen is extracted through a color separation clustering algorithm under red, green and blue display colors, the display screen is identified through a target identification algorithm and the frame of the display screen is extracted, the identification display screen regions are combined according to certain confidence coefficient, and the image displayed by the display screen can be extracted more accurately, namely the more accurate second image.
Some LED display screens are provided with a black film to reduce the minimum brightness of the LED display screen, thereby increasing the contrast of the LED display screen. If the black film is locally abnormal, even if all pixel points of the LED display screen to be detected can normally emit light, the defect of the display of the LED display screen can still be detected according to the detection method, and therefore two preferred embodiments are provided for the LED display screen pasted with the black film.
Firstly, the step of obtaining a picture of the LED display screen when displaying a pure color to obtain a first image comprises the following steps: and acquiring pictures of the LED display screen displaying white, red, green and blue to obtain four first images.
The method comprises the following steps of identifying a frame of the LED display screen in a first image, and selecting an image in the frame as a second image, wherein the steps comprise:
s21': and identifying the frames of the LED display screen in the four first images to obtain four first frame information.
S22': and combining the four pieces of first frame information to obtain second frame information.
S23': and selecting local images in the four first images according to the second frame information to generate four second images.
When the four colors are displayed and the defects are detected at the same pixel position of the same splicing module, the defect of the black film is roughly considered to exist at the position, for example, the black film is oxidized, the black film has scratches, the surface has stains and the like; it is of course also possible that all three sub-pixels are defective at this location.
Secondly, before step S1, the method further comprises the steps of:
s01: and acquiring a black image when the LED display screen is not lightened under uniform illumination in a dark field.
S02: film defects in the black image are identified.
The method comprises the steps of obtaining images under a dark field through uniform illumination and a high-precision camera when a screen is not lightened, judging whether a surface layer film is in a problem or not through a machine learning algorithm, and analyzing a black image to quickly find out the film defects according to the fact that the place with the film defects has different appearances from other positions even if the place with the film defects does not emit light. The defect detection method eliminates the defect display defect of retesting the display screen due to the abnormal black film, is favorable for quickly finding out the defect reason, and specifically repairs the defect.
From the comparison above, the second method can identify the film defects more accurately, but needs to make the quality inspection assembly line in dark field, while the first method is simpler without adding new steps.
There are two ways to indicate the defective stitching module (i.e. to screen out the defective third image and record the defective stitching module corresponding to the defective third image).
First, step S4 includes:
s41': detecting each third image to detect a defective third image;
s42': determining a location of a defective third image in the second image;
s43': and recording a defective splicing module corresponding to the defective third image.
The output of step S43' may be in the form of marking the problematic locations in the second image, printing the marked second image, and the service person finding the defective pixels based on the printed image and the pixel locations suggested in step S5.
Second, step S4 includes:
s41: and numbering the third images according to the arrangement mode of the splicing modules in the LED display screen.
S42: each third image is detected, and a defective third image is detected.
S43: the number of the defective third image is recorded.
The second image shown in fig. 4 shows that the display screen is composed of 4 × 4 tiled modules, step S41 shows nos. 1-16, and after the above steps S41 to S43 are performed, the defective third image is recorded as module No. 2, module No. 7, and module No. 10. And the maintenance personnel find the defective pixel according to the module corresponding to the recorded serial number and the pixel position prompted in the step S5.
Wherein each third image is detected, the step of detecting a defective third image comprising:
s421: acquiring the brightness, the chroma and the saturation of each pixel of a third image;
s422: calculating the mean square error of brightness, the mean square error of chroma and the mean square error of saturation of each third image;
s423: selecting the third image with the mean square error of the luminance, the mean square error of the chrominance or the mean square error of the saturation larger than the first value as a defective third image. In particular, the first value is equal to 1.
And if any one of the brightness mean square error, the chroma mean square error or the saturation mean square error is larger than the first value, the splicing module corresponding to the third image is considered to be defective. That is, a complex machine learning model is not required to be used when the defective third image is screened, and the mean square error is simply calculated, the embodiment of the present application only needs to apply different machine learning models in the steps S2 and S5, and the step S5 only aims at the defective third image, so that the calculation range is greatly reduced compared with the full-screen detection in the prior art, and the improvement of the detection efficiency is facilitated.
Wherein step S5 includes:
s51: and identifying the defect contour and the internal feature distribution in the defective third image by using a machine learning algorithm.
S52: and intersecting and comparing the defect outline and the internal feature distribution with the optimal feature set, and calculating the matching probability.
S53: and generating a defect type, a matching probability corresponding to the defect type and a position parameter corresponding to the defect type.
The location parameter may be in the form of a plane coordinate system constructed for a center point or a corner of the defective third image, and the defect location is recorded by coordinates.
In the training stage of the machine learning model, a level set algorithm is used for extracting defect contour and pixel mean square error information (namely internal feature distribution including, for example, luminance mean square error, chrominance mean square error and saturation mean square error), contour features of the same category and target mean square error information are merged, and then the merged feature equation is used as a learning result parameter to be stored until the last image is obtained. And finally, verifying in a verification set to obtain the maximum recognition rate.
In the identification stage of the machine learning model, a level set algorithm is used for extracting defect outline and pixel mean square error information, then the defect outline and pixel mean square error information are intersected and compared with an optimal characteristic set, the matching probability is calculated, finally, the matching probability and defect types (such as dark spots, dead spots and bright spots) are displayed and stored, and defect position parameters are output, so that the repair is facilitated.
The machine learning model for calculating the pixel mean square error information belongs to a simpler model, and the display defects of the LED display screen can be accurately detected by using the simpler model in the embodiment of the application. For the whole screen test in the prior art, the simpler model is difficult to apply, a 4K screen is taken as an example, the statistical cardinality is very large, and if other pixels are normal, the brightness of a single pixel point is low, and the mean square error of the whole brightness is still very small. Therefore, if the specified mean square error is larger, the test is inaccurate; if the specified mean square error is smaller, the model is too sensitive, and the display screen which is qualified in the prior art is also determined as failing, because the process limitation does not exist identical LED chips, the LED display screen is manufactured by selecting the same batch of LED chips with similar performance at present, the brightness of the LED display screen after unit correction is not really uniform, the adjacent splicing modules are adjusted and calibrated to be in continuous brightness transition, the LED display screen is relatively uniform in human vision, the spliced modules can be found to be not completely uniform through the human vision as long as the positions of the splicing modules are changed, the brightness mean square error calculated by a machine is not limited by the human vision, when the specified mean square error is smaller, a large number of display screens are determined as the defect, and therefore, the prior art can realize the whole-screen detection by using a more complex algorithm. According to the embodiment of the application, the 4K screen display frame is divided into the plurality of third images according to the arrangement mode of the splicing modules, the resolution ratio of each third image is far lower than that of the 4K screen, the statistical cardinality is greatly reduced, and therefore a simple machine learning model can be used.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the present application provides an electronic device, including: the processor 301 and the memory 302, the processor 301 and the memory 302 being interconnected and communicating with each other via a communication bus 303 and/or other form of connection mechanism (not shown), the memory 302 storing a computer program executable by the processor 301, the computer program being executable by the processor 301 when the computing device is running to perform the method in any of the alternative implementations of the above embodiments when the processor 301 executes the computer program to perform the following functions: obtaining a picture when the LED display screen displays a pure color to obtain a first image; identifying a frame of the LED display screen in the first image, and selecting an image in the frame as a second image; dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen; screening out the defective third image, and recording a defective splicing module corresponding to the defective third image; and judging the defect type of the defective third image, and positioning the defect position of the defective splicing module.
Referring to fig. 2, fig. 2 is a device for detecting display defects of an LED display screen according to some embodiments of the present disclosure, including:
the first obtaining module 201 is configured to obtain a picture of the LED display screen displaying a pure color to obtain a first image;
the frame identification module 202 is used for identifying a frame of the LED display screen in the first image and selecting an image in the frame as a second image;
the first dividing module 203 is used for dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen;
the screening module 204 is used for screening out the defective third image and recording the defective splicing module corresponding to the defective third image;
and the judging and positioning module 205 is configured to perform defect type judgment on the defective third image, and perform defect position positioning on the defective splicing module.
The device can divide the pure color image that the LED display screen shows according to the arrangement of concatenation module in the LED display screen, discern defective concatenation module earlier, carry out the defect type to defective module again and judge, fix a position defective position, reduce the discernment settlement to nondefective concatenation module, can improve detection efficiency, and conveniently find defective position fast when restoreing the defect in the follow-up, the resolution ratio of concatenation module is much lower than the resolution ratio of whole LED display screen, discern defective concatenation module earlier, fix a position the defect of concatenation module again alone, can reduce the operation complexity, promote detection speed.
In some preferred embodiments, the apparatus further comprises a second acquisition module for acquiring a black image when the LED display screen is not lit under uniform illumination in a dark field, and a second recognition module for recognizing a film defect in the black image.
In the description of the present specification, reference to the description of the terms "one embodiment," "certain embodiments," "illustrative embodiments," "example," "specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (6)
1. A method for detecting display defects of an LED display screen is characterized by comprising the following steps:
acquiring a black image when the LED display screen is not lightened under uniform illumination in a dark field;
identifying film defects in the black image;
obtaining a picture when the LED display screen displays a pure color to obtain a first image;
identifying a frame of the LED display screen in the first image, and selecting an image in the frame as a second image;
dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen;
screening out a defective third image, and recording a defective splicing module corresponding to the defective third image;
judging the defect type of the defective third image, and positioning the defect position of the defective splicing module;
the screening out the defective third image and the recording the defective splicing module corresponding to the defective third image comprises:
acquiring the brightness, the chroma and the saturation of each pixel of the third image;
calculating the mean square error of brightness, the mean square error of chroma and the mean square error of saturation of each third image;
selecting said third image having a mean square error of luminance, a mean square error of chrominance, and a mean square error of saturation greater than a first value as said defective third image;
determining a location of the defective third image in the second image;
recording a defective stitching module corresponding to the defective third image.
2. The method for detecting the display defects of the LED display screen according to claim 1, wherein the step of obtaining the first image from the picture of the LED display screen displaying the pure color comprises:
acquiring pictures of an LED display screen displaying red, green and blue to obtain three first images;
the step of identifying the frame of the LED display screen in the first image and selecting the image in the frame as the second image comprises the following steps:
identifying the frames of the LED display screen in the three first images to obtain three first frame information;
combining the three pieces of first frame information to obtain second frame information;
and selecting a local image in the three first images according to the second frame information to generate three second images.
3. The method for detecting the display defects of the LED display screen according to claim 1, wherein the step of obtaining the picture of the LED display screen displaying the pure color to obtain the first image comprises:
acquiring pictures of the LED display screen displaying white, red, green and blue to obtain four first images;
the step of identifying the frame of the LED display screen in the first image and selecting the image in the frame as the second image comprises the following steps:
identifying the frames of the LED display screens in the four first images to obtain four first frame information;
combining the four first frame information to obtain second frame information;
and selecting local images in the four first images according to the second frame information to generate four second images.
4. The method for detecting the display defects of the LED display screen according to claim 1, wherein the step of judging the type of the defects of the defective third image and locating the positions of the defects of the defective splicing module comprises the following steps:
identifying a defect contour and an internal feature distribution in the defective third image using a machine learning algorithm;
intersecting and comparing the defect contour and the internal feature distribution with an optimal feature set, and calculating matching probability;
and generating a defect type, a matching probability corresponding to the defect type and a position parameter corresponding to the defect type.
5. An electronic device comprising a processor and a memory, the memory storing computer readable instructions which, when executed by the processor, perform the steps of the method of any one of claims 1-4.
6. The utility model provides a LED display screen shows defect detecting device which characterized in that includes:
the second acquisition module is used for acquiring a black image when the LED display screen is not lightened under uniform illumination in a dark field;
the second identification module is used for identifying the film defects in the black image;
the first acquisition module is used for acquiring a picture of the LED display screen displaying pure color to obtain a first image;
the frame identification module is used for identifying the frame of the LED display screen in the first image and selecting the image in the frame as a second image;
the first dividing module is used for dividing the second image into a plurality of third images corresponding to the splicing modules according to the arrangement mode of the splicing modules in the LED display screen;
the screening module is used for screening out the defective third image and recording the defective splicing module corresponding to the defective third image; acquiring the brightness, the chroma and the saturation of each pixel of the third image; calculating the mean square error of brightness, the mean square error of chroma and the mean square error of saturation of each third image; selecting said third image having a mean square error of luminance, a mean square error of chrominance, and a mean square error of saturation greater than a first value as said defective third image; determining a location of the defective third image in the second image; recording a defective stitching module corresponding to the defective third image;
and the judging and positioning module is used for judging the defect type of the defective third image and positioning the defect position of the defective splicing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210188796.2A CN114255232B (en) | 2022-02-28 | 2022-02-28 | LED display screen display defect detection method, electronic equipment and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210188796.2A CN114255232B (en) | 2022-02-28 | 2022-02-28 | LED display screen display defect detection method, electronic equipment and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114255232A CN114255232A (en) | 2022-03-29 |
| CN114255232B true CN114255232B (en) | 2022-06-17 |
Family
ID=80800081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210188796.2A Active CN114255232B (en) | 2022-02-28 | 2022-02-28 | LED display screen display defect detection method, electronic equipment and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255232B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115855970B (en) * | 2023-02-21 | 2023-05-12 | 攀枝花大宇包装印刷有限公司 | Automatic detection equipment for printing steel mesh |
| CN116381974B (en) * | 2023-06-06 | 2023-08-11 | 深圳市瀚达美电子有限公司 | MiniLED pixel detection method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113419909A (en) * | 2021-06-11 | 2021-09-21 | 苏州华兴源创科技股份有限公司 | Display uniformity detection method and computer equipment |
| CN113466292A (en) * | 2021-07-22 | 2021-10-01 | 苏州华兴源创科技股份有限公司 | Defect detection method and device for display module |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013160629A (en) * | 2012-02-06 | 2013-08-19 | Hitachi High-Technologies Corp | Defect inspection method, defect inspection apparatus, program, and output unit |
| CN103559862B (en) * | 2013-11-11 | 2016-08-17 | 西安诺瓦电子科技有限公司 | The Subarea calibration method of LED display |
| CN104900178B (en) * | 2015-06-18 | 2017-10-13 | 西安诺瓦电子科技有限公司 | Brightness abnormal image detection method and LED display uniformity correcting method |
| CN105094740B (en) * | 2015-07-07 | 2018-03-27 | 西安诺瓦电子科技有限公司 | A kind of location positioning method applied to LED display |
| CN107065247A (en) * | 2017-06-07 | 2017-08-18 | 惠科股份有限公司 | A kind of display panel testing method, apparatus and system |
| CN109119009A (en) * | 2017-06-26 | 2019-01-01 | 深圳回收宝科技有限公司 | Screen defect inspection method, detection device, system and storage medium |
| CN108460757B (en) * | 2018-02-11 | 2020-04-14 | 深圳市鑫信腾科技有限公司 | Mobile phone TFT-LCD screen Mura defect online automatic detection method |
| CN108630142A (en) * | 2018-05-13 | 2018-10-09 | 上海诣阔软件有限公司 | A kind of correction LED display piece method |
| CN109062531B (en) * | 2018-08-15 | 2021-08-27 | 京东方科技集团股份有限公司 | Spliced screen, display method of spliced screen and display control device |
| CN110942726A (en) * | 2018-09-21 | 2020-03-31 | 深圳光峰科技股份有限公司 | LED display screen |
| CN109490313B (en) * | 2018-11-09 | 2022-08-23 | 中国科学院光电技术研究所 | Automatic detection device and method for surface defects of large-caliber curved surface optical element |
| CN110233977A (en) * | 2019-06-04 | 2019-09-13 | 深圳市摩西尔电子有限公司 | A kind of method and device of LED screen image mosaic and display |
| CN110648626A (en) * | 2019-09-30 | 2020-01-03 | 深圳市奥拓电子股份有限公司 | Method and system for correcting bright and dark lines of LED display screen and storage medium thereof |
| US11494886B2 (en) * | 2020-05-29 | 2022-11-08 | Adobe Inc. | Hierarchical multiclass exposure defects classification in images |
| CN112988096A (en) * | 2021-03-26 | 2021-06-18 | 北京集创北方科技股份有限公司 | Display unit positioning method, device, equipment, storage medium and display device |
| CN113866182A (en) * | 2021-09-09 | 2021-12-31 | 安徽亿普拉斯科技有限公司 | Detection method and system for detecting defects of display module |
| CN114046880A (en) * | 2021-11-19 | 2022-02-15 | 武汉华上科技有限公司 | Color difference correction method for LED spliced display screen |
-
2022
- 2022-02-28 CN CN202210188796.2A patent/CN114255232B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113419909A (en) * | 2021-06-11 | 2021-09-21 | 苏州华兴源创科技股份有限公司 | Display uniformity detection method and computer equipment |
| CN113466292A (en) * | 2021-07-22 | 2021-10-01 | 苏州华兴源创科技股份有限公司 | Defect detection method and device for display module |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114255232A (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114255232B (en) | LED display screen display defect detection method, electronic equipment and device | |
| CN102279189B (en) | Defect detecting device, defect restoring device and defect detecting method | |
| KR20140076963A (en) | Apparatus and Method for Mura Defect Detection of Display Device | |
| KR101113910B1 (en) | Led pixel diagnosis apparatus for led display board | |
| KR100910593B1 (en) | Faulty pixel detecting method and faulty pixel detecting system for led electric sign board | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN109978864A (en) | Display panel detection system, method, apparatus and storage medium | |
| CN116256908B (en) | Calibration method based on miniLED backlight module | |
| CN114299070A (en) | Method and related device for detecting mura defects of display screen | |
| KR100763019B1 (en) | System and its method for inspection of FPD | |
| KR101876908B1 (en) | Enhancement method for location accuracy of display panel defect | |
| CN109712115A (en) | A kind of pcb board automatic testing method and system | |
| KR101068356B1 (en) | Method for inspecting defect of the Pixels in display panel device by image | |
| CN108663371B (en) | Method and system for detecting dust and foreign matters on display panel | |
| CN110891173B (en) | Dynamic image detection method and system | |
| JP2006251561A (en) | Defective pixel repairing method | |
| CN115546140A (en) | Display panel detection method and system and electronic device | |
| CN111292300B (en) | Method and apparatus for detecting bright spot defect of display panel, and readable storage medium | |
| CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
| CN110672631B (en) | Panel defect photographing method and panel defect photographing device | |
| US7330580B2 (en) | System and method for inspecting an LCD panel | |
| KR20120074702A (en) | Diagonal scan method for fast edge detection | |
| JP2790037B2 (en) | Appearance inspection method and appearance inspection apparatus | |
| KR100643248B1 (en) | Method and apparatus for inspecting display panel | |
| JP2007024616A (en) | Lighting image plane inspecting technique of plasma display panel |
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 |