Display fault detection method, device, electronic device and storage medium

Through Fourier transform and wavelet filtering processing technology, the interference of light-transmitting gaps is eliminated and the display screen failure is accurately detected, which solves the problem of distinguishing the impact of display defects and light-transmitting gaps in the prior art, and improves the accuracy and reliability of detection.

CN114429439BActive Publication Date: 2024-11-05合肥欣奕华智能机器股份有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011097901.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-10-14
Publication Date
2024-11-05
Estimated Expiration
2040-10-14

Smart Images

  • Figure CN114429439B_ABST
    Figure CN114429439B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image processing technology, and discloses a display fault detection method, device, electronic device and storage medium. The method of this embodiment includes: determining a target frequency corresponding to an image to be processed containing a target screen and representing the influence of a light-transmitting gap; performing wavelet filtering on the image to be processed after frequency domain processing based on a first filter and a second filter to obtain a first component image representing the influence of light-transmitting gaps in a column direction and a second component image representing the influence of light-transmitting gaps in a row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through; obtaining an image representing the influence of light-transmitting gaps based on the first component image and the second component image; processing the image to be processed based on the image representing the influence of light-transmitting gaps to obtain a target image in which the influence of light-transmitting gaps is eliminated, and accurately performing fault detection on the target screen based on the target image.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a display fault detection method, device, electronic equipment and storage medium. Background Art

[0002] With the development of technology, terminals are becoming more and more popular, and display screens are used in terminals to display interfaces. During the production process of display screens, it is necessary to test the display performance of the display screen to determine whether there are defects such as uneven display.

[0003] In the related art, a camera is usually used to shoot an interface of a single color displayed on a full screen of a display screen, and whether the color displayed on the display screen is uniform is determined based on the shot image.

[0004] However, there are light-transmitting gaps between the display pixels of the display screen. Since it is impossible to ensure that the display pixels correspond to the arrangement of the camera's shooting pixels, the proportion of display pixels and light-transmitting gaps in each shooting pixel is different, resulting in inconsistent colors of different shooting pixels. Therefore, it is impossible to determine whether it is a display defect of the display screen or the influence of the light-transmitting gaps that causes the uneven color of the captured image, making it difficult to accurately detect display failures. Summary of the invention

[0005] The invention provides a display fault detection method, device, electronic equipment and storage medium for accurately detecting display faults.

[0006] In a first aspect, an embodiment of the present invention provides a display fault detection method, the method comprising:

[0007] Determine a target frequency corresponding to the image to be processed including the target screen, which represents the influence of the light-transmitting gap;

[0008] Based on the first filter and the second filter, wavelet filtering is performed on the image to be processed after the frequency domain processing to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0009] Obtaining an image representing the influence of the light-transmitting slit based on the first component image and the second component image;

[0010] The image to be processed is processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and fault detection is performed on the target screen according to the target image.

[0011] In the above scheme, the image to be processed is a spatial domain image, and the color signal value of each pixel in the image to be processed is independent. It is impossible to determine which color signal values ​​are affected by the light-transmitting slits and what the affected values ​​are based on the color signal values ​​of these pixels. However, by converting the spatial domain image into a frequency domain image, the frequencies affected by some specific factors in the frequency domain image can be retained or removed, thereby obtaining an image composed of target frequencies representing the influence of the light-transmitting slits. By determining the target frequency representing the influence of the light-transmitting slits corresponding to the image to be processed containing the target screen, and performing wavelet filtering on the image to be processed after frequency domain processing, a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction can be obtained. Based on the first component image and the second component image, an image representing the influence of the light-transmitting slits is obtained. Then, based on the image representing the influence of the light-transmitting slits, the image to be processed is processed to obtain a target image with the influence of the light-transmitting slits eliminated. Since the light-transmitting slit interference of the target image has been eliminated, the target screen can be accurately detected according to the target image, thereby reducing missed detection and false detection of display faults of the target screen.

[0012] In some optional implementations, determining a target frequency corresponding to an image to be processed including a target screen and representing the influence of a light-transmitting gap includes:

[0013] Performing Fourier transform on the color signal values ​​of multiple target pixels in the image to be processed to obtain the frequencies of the multiple target pixels, wherein the multiple target pixels represent at least one color signal value transformation cycle, and the color signal value is a three primary color (Red Green Blue, RGB for short) value or a grayscale value;

[0014] The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

[0015] The above scheme obtains multiple frequencies of these target pixels by performing Fourier transform on the color signal values ​​of multiple target pixels representing at least one color signal value transformation period in the above image to be processed, wherein the highest frequency is the frequency representing the influence of the light-transmitting gaps in these target pixels; the highest frequency can be directly used as the target frequency, and the target frequency can be obtained conveniently and quickly; or the frequency range containing the above highest frequency in the preset frequency range can be used as the target frequency, and the target frequency can accurately represent the influence of the light-transmitting gaps corresponding to the image to be processed, thereby meeting the needs of different application scenarios.

[0016] In some optional implementations, the image to be processed is processed based on the image representing the influence of the light-transmitting slit to obtain a target image, including:

[0017] The image representing the influence of the light-transmitting slit is removed from the image to be processed to obtain a target image.

[0018] The above scheme removes the image representing the influence of the light-transmitting slit from the image to be processed, thereby removing the interference caused by the influence of the light-transmitting slit from the image to be processed, thereby conveniently and accurately obtaining the target image with the influence of the light-transmitting slit eliminated.

[0019] In some optional implementations, performing fault detection on the target screen according to the target image includes:

[0020] Performing grayscale binarization processing on the target image;

[0021] If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that there is a display failure on the target screen.

[0022] The above scheme can conveniently and accurately determine whether the target screen has a display fault by performing grayscale binarization processing on the target image and directly determining the pixel points with different grayscale values ​​in the image after the grayscale binarization processing.

[0023] In some optional implementations, the first component image is obtained by:

[0024] Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or

[0025] The second component image is obtained by:

[0026] The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

[0027] In some optional implementations, obtaining an image characterizing the influence of the light-transmitting slit based on the first component image and the second component image includes:

[0028] Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image;

[0029] The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

[0030] In a second aspect, an embodiment of the present invention provides a display fault detection device, comprising:

[0031] A determination module, used to determine a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap;

[0032] A filtering module, configured to perform wavelet filtering on the image to be processed after frequency domain processing based on a first filter and a second filter, to obtain a first component image representing the influence of light-transmitting slits in a column direction and a second component image representing the influence of light-transmitting slits in a row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0033] An acquisition module, configured to obtain an image representing the influence of a light-transmitting slit based on the first component image and the second component image;

[0034] The processing module is used to process the image to be processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and perform fault detection on the target screen according to the target image.

[0035] In some optional implementations, the determination module determines the target frequency corresponding to the image to be processed including the target screen and characterizing the influence of the light-transmitting gap, including:

[0036] Performing Fourier transform on color signal values ​​of a plurality of target pixels in the image to be processed to obtain frequencies of the plurality of target pixels, wherein the plurality of target pixels represent at least one color signal value transformation cycle, and the color signal value is an RGB value or a grayscale value;

[0037] The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

[0038] In some optional implementations, the image to be processed is processed based on the image representing the influence of the light-transmitting slit to obtain a target image, including:

[0039] The image representing the influence of the light-transmitting slit is removed from the image to be processed to obtain a target image.

[0040] In some optional implementations, the processing module performs fault detection on the target screen according to the target image, including:

[0041] Performing grayscale binarization processing on the target image;

[0042] If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that there is a display failure on the target screen.

[0043] In some optional implementations, the filtering module obtains the first component image in the following manner:

[0044] Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or

[0045] The filtering module obtains the second component image in the following manner:

[0046] The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

[0047] In some optional implementations, the obtaining module obtains an image characterizing the influence of the light-transmitting slit based on the first component image and the second component image, including:

[0048] Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image;

[0049] The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

[0050] In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory;

[0051] The memory stores program code, and when the program code is executed by the processor, the processor executes the steps of the method described in the first aspect above.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0053] In addition, the technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by different implementation methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0055] Figure 1A A schematic diagram of a display pixel provided by an embodiment of the present invention;

[0056] Figure 1B A schematic diagram of pixels captured before shooting provided by an embodiment of the present invention;

[0057] Figure 1C A diagram showing the position relationship between display pixels and shooting pixels during shooting provided by an embodiment of the present invention;

[0058] Figure 1D A schematic diagram of pixels captured after shooting provided by an embodiment of the present invention;

[0059] Figure 2A A schematic diagram of a first application scenario provided by an embodiment of the present invention;

[0060] Figure 2B A schematic diagram of a second application scenario provided by an embodiment of the present invention;

[0061] Figure 3 A schematic flow chart of a first display fault detection method provided by an embodiment of the present invention;

[0062] Figure 4 A schematic flow chart of wavelet decomposition provided by an embodiment of the present invention;

[0063] Figure 5 A schematic flow chart of wavelet reconstruction provided by an embodiment of the present invention;

[0064] Figure 6 A schematic flow chart of a second display fault detection method provided by an embodiment of the present invention;

[0065] Figure 7 A schematic diagram of grayscales of partially continuous pixels in the row direction of an image to be processed provided by an embodiment of the present invention;

[0066] Figure 8 A schematic flow chart of a third display fault detection method provided by an embodiment of the present invention;

[0067] Fig. 9 A schematic flow chart of a fourth display fault detection method provided by an embodiment of the present invention;

[0068] Fig. 10A An image after the first grayscale binarization process provided by an embodiment of the present invention;

[0069] Fig. 10B The image after the second grayscale binarization process provided by the embodiment of the present invention;

[0070] Fig.11 A schematic diagram of the structure of a display fault detection device provided by an embodiment of the present invention;

[0071] Fig.12A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0074] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0075] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal connection of two devices. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0076] During the production process of display screens, it is necessary to test the display performance of the display screen to determine whether there are defects such as uneven display. Usually, a camera is used to shoot a single color interface displayed on the full screen of the display screen, and the color displayed on the display screen is determined based on the captured image.

[0077] See also Figure 1A , each display pixel of the display screen displays the same gray value evenly, and there are light-transmitting gaps between the display pixels of the display screen, see Figure 1B , the camera's shooting pixels are different in size and number from the above-mentioned display pixels; since the camera's shooting pixels are different in size and number from the above-mentioned display pixels, when the camera shoots, refer to Figure 1C , the arrangement of display pixels and shooting pixels cannot correspond, and the proportion of display pixels and light-transmitting gaps in each shooting pixel is different, which will lead to Figure 1D As shown, the colors of different captured pixels are inconsistent.

[0078] It can be seen from the above embodiments that it is impossible to determine whether the uneven color of the captured image is caused by a display defect of the display screen or by the influence of the light-transmitting gap. If the display failure of the display screen is determined based on the uneven color of the captured image, it will cause false detection.

[0079] The above embodiment is explained by taking the example that the size and number of the camera's shooting pixels are different from those of the above display pixels. It can be understood that even if the camera's shooting pixels are the same as the size and number of the above display pixels, it is difficult to adjust the position of the camera at the pixel level, and it is impossible to ensure that the arrangement of the display pixels and the camera's shooting pixels corresponds. The influence of the light-transmitting gaps still exists, and display failures cannot be accurately detected.

[0080] In addition, the sizes and numbers of display pixels and shooting pixels in the above embodiments are only exemplary. In practical applications, the sizes of display pixels and shooting pixels can be larger or smaller, and the numbers can be more or less.

[0081] In order to accurately detect display faults, the embodiments of the present invention provide a display fault detection method, device, electronic device and storage medium. The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0082] like Figure 2A As shown, it is a schematic diagram of the first application scenario of the embodiment of the present invention. The application scenario diagram includes a display screen ( Figure 2A Target screen 110 is taken as an example) and electronic device 121.

[0083] In this scenario, the target screen 110 displays a single-color interface on the entire screen;

[0084] The electronic device 121 has a shooting function and can capture the image to be processed including the target screen 110;

[0085] It is also possible to determine a target frequency corresponding to the image to be processed that represents the effect of the light-transmitting gap;

[0086] Alternatively, the image to be processed that has undergone frequency domain processing may be subjected to wavelet filtering based on the first filter and the second filter to obtain a first component image representing the influence of light-transmitting slits in the column direction and a second component image representing the influence of light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0087] An image representing the influence of the light-transmitting slit may also be obtained based on the first component image and the second component image;

[0088] The image to be processed may also be processed based on the image representing the influence of the light-transmitting slit to obtain a target image, and fault detection may be performed on the target screen according to the target image.

[0089] like Figure 2B As shown, it is a schematic diagram of a second application scenario of an embodiment of the present invention. The application scenario diagram includes a display screen ( Figure 2A In the figure, the target screen 110 is taken as an example), the electronic device 122 and the image acquisition device 130.

[0090] In this scenario, the target screen 110 displays a single-color interface on the entire screen;

[0091] The image acquisition device 130 may acquire the image to be processed including the target screen 110;

[0092] The image acquisition device 130 and the electronic device 122 can transmit data in a variety of ways. Here, the image acquisition device 130 can be allowed to transmit data with the electronic device 122 via a local area network (LAN), a wireless local area network (WLAN), a data line, etc. For example, the image acquisition device 130 sends the above-mentioned image to be processed to the electronic device 122 via a data line.

[0093] The electronic device 122 may determine a target frequency corresponding to the image to be processed that represents the effect of the light-transmitting gap;

[0094] The image to be processed after the frequency domain processing may also be subjected to wavelet filtering based on the first filter and the second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0095] An image representing the influence of the light-transmitting slit may also be obtained based on the first component image and the second component image;

[0096] The image to be processed may also be processed based on the image representing the influence of the light-transmitting slit to obtain a target image, and fault detection may be performed on the target screen according to the target image.

[0097] In the embodiment of the present invention, the electronic device may be a device with certain computing capabilities, such as a personal computer, a mobile phone, a tablet computer, and a notebook.

[0098] The image acquisition device can be a camera, a mobile phone or other device.

[0099] The target screen may be a display screen of a device such as a television or a mobile phone, for example, a liquid crystal display (LCD) in a television.

[0100] The above application scenarios are only examples of application scenarios for implementing the embodiments of the present invention, and the embodiments of the present invention are not limited to the above application scenarios.

[0101] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0102] Figure 3 A schematic flow chart of a first display fault detection method provided by an embodiment of the present invention is applied to the above electronic device, such as Figure 3 As shown, the method may include:

[0103] Step 301: Determine a target frequency corresponding to an image to be processed including a target screen and representing the influence of a light-transmitting gap.

[0104] In this embodiment, the target screen displays a single color interface in full screen, and the target screen is photographed to obtain an image to be processed including the target screen. Figure 1D As shown in the figure, the image to be processed is composed of multiple pixels. The color signal values ​​(grayscale values ​​or RGB values) displayed by different pixels may be close or very different. Some of the pixels with large differences are caused by light-transmitting gaps. The image to be processed is a spatial domain image. The color signal value of each pixel in the image to be processed is independent. It is impossible to determine which color signal values ​​are affected by the light-transmitting gaps and what the affected values ​​are based on the color signal values ​​of these pixels. It is also impossible to remove the affected values ​​from these color signal values.

[0105] Based on the color signal value (grayscale value or RGB value) of each pixel in the image to be processed, Fourier transform is performed to obtain the image to be processed after frequency domain processing. By converting the spatial domain image into a frequency domain image, the frequency affected by some specific factors in the frequency domain image can be easily obtained or removed without interfering with other frequencies in the frequency domain image.

[0106] The purpose of this embodiment is to obtain an image that characterizes the influence of the light-transmitting slits, and then the above-mentioned image to be processed can be processed based on the image that characterizes the influence of the light-transmitting slits, that is, to obtain an image composed of frequencies affected by some specific factors (target frequencies that characterize the influence of the light-transmitting slits). Based on this, it is necessary to determine the target frequency that characterizes the influence of the light-transmitting slits corresponding to the image to be processed.

[0107] This embodiment does not limit the method for determining the target frequency. For example, the target frequency is determined according to the frequencies of some continuous pixels in the above-mentioned image to be processed.

[0108] Step 302: performing wavelet filtering on the image to be processed after frequency domain processing based on the first filter and the second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction.

[0109] The first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through.

[0110] As described above, the purpose of this embodiment is to obtain an image that characterizes the influence of the light-transmitting slit, that is, to obtain an image composed of frequencies affected by some specific factors (target frequencies that characterize the influence of the light-transmitting slit). The above-mentioned image to be processed is a two-dimensional image, and the column features and row features are independent of each other. For example, the gradient of a pixel point in the column is not the same as the gradient of the pixel point in the row. Therefore, it is necessary to filter the image to be processed in the row direction and the column direction respectively, and obtain a first component image that characterizes the influence of the light-transmitting slit in the column direction, which is composed of the target frequency in the column direction, and a second component image that characterizes the influence of the light-transmitting slit in the row direction, which is composed of the target frequency in the row direction.

[0111] In some specific embodiments, the first component image is obtained by:

[0112] Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or

[0113] The second component image is obtained by:

[0114] The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

[0115] See also Figure 4 As shown, through wavelet decomposition, the image to be processed (represented by image A in the figure) that has been processed in the frequency domain is subjected to row sampling through a first filter, and all frequencies except the target frequency in the row direction are allowed to pass through, so as to obtain a first image in which the target frequency representing the influence of the light-transmitting slit in the row direction is removed; the first image is subjected to column sampling through a first filter, and all frequencies except the target frequency in the column direction are allowed to pass through, so as to obtain a third component image in which the target frequency representing the influence of the light-transmitting slit in the row and column directions is removed;

[0116] The first image is subjected to column sampling by a second filter, and the target frequency in the column direction is allowed to pass through, so as to obtain a first component image representing the influence of the light-transmitting slit only in the column direction;

[0117] The A image is subjected to row sampling through the second filter, and the target frequency in the row direction is allowed to pass through, so as to obtain a second image representing the influence of the light-transmitting slit in the row direction; the second image is subjected to column sampling through the first filter, and all frequencies except the target frequency in the column direction are allowed to pass through, so as to obtain a second component image representing the influence of the light-transmitting slit only in the row direction;

[0118] The second image is subjected to column sampling through a second filter, and the target frequency in the column direction is allowed to pass through, thereby obtaining a fourth component image characterized by the influence of the light-transmitting slits in both the row and column directions.

[0119] Figure 4 It is only an exemplary explanation to obtain the component image characterizing the influence of the light-transmitting gap. This embodiment does not limit the order of row sampling and column sampling. The image to be processed (A image) after frequency domain processing can also be firstly subjected to column sampling by the first filter / second filter and then row sampling, which will not be repeated here.

[0120] Step 303: Obtain an image representing the influence of the light-transmitting slit based on the first component image and the second component image.

[0121] In this embodiment, an image representing the influence of the light-transmitting slit can be obtained based on the component image influenced by the light-transmitting slit. Figure 4 The third component image obtained in the embodiment removes the target frequency characterizing the influence of the light-transmitting slits in the row and column directions, which is not in compliance; although the above-mentioned fourth component image is a component image characterizing the influence of the light-transmitting slits in both row and column directions, that is, both the rows and columns of this image are composed of the target frequency, this image may not characterize the influence of the light-transmitting slits. If this image is also used as a component image characterizing the influence of the light-transmitting slits, the image obtained based on this component image cannot accurately characterize the influence of the light-transmitting slits, affecting the subsequent processing of the image to be processed. Therefore, only the first component image characterizing the influence of the light-transmitting slits in the column direction and the second component image characterizing the influence of the light-transmitting slits in the row direction need to be considered.

[0122] In this embodiment, after obtaining the first component image characterizing the influence of the light-transmitting slits in the column direction and the second component image characterizing the influence of the light-transmitting slits in the row direction, it is necessary to obtain a complete image characterizing the influence of the light-transmitting slits based on the first component image and the second component image, so that the interference caused by the influence of the light-transmitting slits can be removed from the image to be processed based on the complete image characterizing the influence of the light-transmitting slits.

[0123] In addition, the image to be processed that has been processed in the frequency domain is decomposed by wavelet decomposition, and the pixels of the first component image and the second component image are compressed. Therefore, it is also necessary to perform inverse filtering processing on the first component image and the second component image through the inverse filter of the first filter and the inverse filter of the second filter.

[0124] In some specific embodiments, obtaining an image representing the influence of the light-transmitting slit based on the first component image and the second component image may be achieved in the following manner:

[0125] Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image;

[0126] The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

[0127] See also Figure 5 As shown, by wavelet reconstruction, the first component image is upsampled by columns through the inverse filter of the second filter to obtain a third image, and the third image is upsampled by rows through the inverse filter of the first filter to obtain an inverse filtered first component image;

[0128] Performing column upsampling on the second component image through an inverse filter of the first filter to obtain a fourth image, and performing row upsampling on the fourth image through an inverse filter of the second filter to obtain an inverse filtered second component image;

[0129] Superimposing the frequencies of the same row / column of the inverse filtered first component image and the inverse filtered second component image to obtain a composite image;

[0130] The above-mentioned image to be processed is a spatial domain image. If an image that characterizes the influence of the light-transmitting slit is required to process the image to be processed, it is also necessary to convert the composite image and the image to be processed into images of the same type. In some embodiments, the composite image is processed in the spatial domain through an inverse Fourier transform to obtain the above-mentioned image that characterizes the influence of the light-transmitting slit.

[0131] Figure 5 This is only an exemplary description of the method for obtaining the above-mentioned composite image. This embodiment does not limit the order of row upsampling and column upsampling. The order of row upsampling and column upsampling for the first component image and the second component image may be the same or different, which will not be repeated here.

[0132] Step 304: Process the image to be processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and perform fault detection on the target screen according to the target image.

[0133] In this embodiment, after obtaining the image representing the influence of the light-transmitting gap, the image to be processed needs to be processed to eliminate or reduce the interference caused by the influence of the light-transmitting gap and obtain the target image. Only based on the target image can the target screen be accurately detected for faults.

[0134] In the above scheme, the image to be processed is a spatial domain image, and the color signal value of each pixel in the image to be processed is independent. It is impossible to determine which color signal values ​​are affected by the light-transmitting slits and what the affected values ​​are based on the color signal values ​​of these pixels. However, by converting the spatial domain image into a frequency domain image, the frequencies affected by some specific factors in the frequency domain image can be retained or removed, thereby obtaining an image composed of target frequencies representing the influence of the light-transmitting slits. By determining the target frequency representing the influence of the light-transmitting slits corresponding to the image to be processed containing the target screen, and performing wavelet filtering on the image to be processed after frequency domain processing, a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction can be obtained. Based on the first component image and the second component image, an image representing the influence of the light-transmitting slits is obtained. Then, based on the image representing the influence of the light-transmitting slits, the image to be processed is processed to obtain a target image with the influence of the light-transmitting slits eliminated. Since the light-transmitting slit interference of the target image has been eliminated, the target screen can be accurately detected according to the target image, thereby reducing missed detection and false detection of display faults of the target screen.

[0135] Figure 6 A schematic flow chart of a second display fault detection method provided by an embodiment of the present invention is applied to the above electronic device, such as Figure 6 As shown, the method may include:

[0136] Step 601: Perform Fourier transform on the color signal values ​​of multiple target pixels in the image to be processed to obtain the frequencies of the multiple target pixels.

[0137] The plurality of target pixel points represent at least one color signal value transformation cycle, and the color signal value is an RGB value or a grayscale value.

[0138] In this embodiment, although the proportions of display pixels and light-transmitting gaps in each captured pixel are different, the distribution of display pixels in the target screen is uniform, the distribution of captured pixels is also uniform, and the color signal values ​​of the pixels in the row direction or column direction of the image to be processed show periodic changes. Figure 7 As shown, taking the grayscale value of the pixel points in the row direction as an example, every four pixel points represent a color signal value transformation cycle. By selecting multiple target pixel points representing one or more color signal value transformation cycles and performing Fourier transform, the frequencies of the multiple target pixel points can be obtained. The frequencies of the multiple target pixel points can reflect the frequency characteristics of the image to be processed.

[0139] If only four pixels representing one color signal value change cycle are selected, it is difficult to analyze the frequency characteristics of the image to be processed; if multiple pixels representing more color signal value change cycles are selected, the amount of calculation will increase. In some specific embodiments, the above multiple target pixels represent two color signal value change cycles.

[0140] The grayscale value distribution and color signal value transformation period of the above-mentioned pixel points in the row direction are merely examples. The present embodiment can also select multiple target pixel points representing at least one color signal value transformation period according to the grayscale value distribution of the pixel points in the column direction. The implementation method is similar to the above-mentioned embodiment and will not be repeated here.

[0141] Step 602: taking the highest frequency among the frequencies of the plurality of target pixels as the target frequency; or taking a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixels as the target frequency.

[0142] In this embodiment, for the scenario of display fault detection, the image to be processed includes a target screen that displays an interface of a single color throughout the screen. The color signal values ​​of most pixels in the image to be processed have high similarity. Color signal values ​​with high similarity will produce lower frequencies, and color signal values ​​with low similarity will produce higher frequencies. Therefore, the low frequencies in the frequency of the target pixel points represent that they are not affected by the light-transmitting gaps, and conversely, the high frequencies represent that they are affected by the light-transmitting gaps.

[0143] In some embodiments, the highest frequency among the frequencies of the above-mentioned multiple target pixel points can be directly used as the target frequency. For example:

[0144] The frequencies of the multiple target pixel points include: 1 Hz, 3 Hz, 5 Hz and 7 Hz, and 7 Hz is used as the target frequency.

[0145] In some other embodiments, a frequency range having the highest frequency among the frequencies of the target pixels in a preset frequency range may be used as the target frequency.

[0146] The above-mentioned highest frequency is the frequency that characterizes the influence of the light-transmitting gaps in these target pixels. For the pixels that represent the transformation period of different color signal values ​​in the image to be processed, the frequency that is affected by the light-transmitting gaps will fluctuate. By using the frequency range that includes the above-mentioned highest frequency in the preset frequency range as the target frequency, the target frequency can accurately characterize the influence of the light-transmitting gaps corresponding to the image to be processed. This embodiment can obtain the preset frequency range by, but not limited to, the following methods:

[0147] 1) Through deep learning, the frequency range corresponding to the frequencies of multiple target pixels is obtained, for example:

[0148] The frequency distribution of a certain number of sample pixels and the corresponding frequency spectrum range are taken as input and the prediction results are taken as output. The initial neural network model is trained to obtain a trained neural network model. The frequencies of multiple target pixels are input into the trained neural network model to obtain the corresponding frequency range.

[0149] 2) Divide the frequencies between the lowest frequency and the highest frequency of the multiple target pixel points into N frequency segments evenly, and these frequencies constitute the above-mentioned preset frequency range.

[0150] Still taking the frequency of the above-mentioned multiple target pixel points including: 1Hz, 3Hz, 5Hz and 7Hz as an example, if the preset frequency range is 1-2Hz, 2-4Hz, 5-6Hz and 7-8Hz, 7-8Hz includes 7Hz, 7-8Hz is used as the target frequency.

[0151] The frequencies of the above-mentioned multiple target pixel points and the preset frequency range are merely exemplary descriptions, and the present embodiment is not limited thereto.

[0152] Step 603: performing wavelet filtering on the image to be processed after frequency domain processing based on the first filter and the second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction.

[0153] The first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through.

[0154] Step 604: Obtain an image representing the influence of the light-transmitting gap based on the first component image and the second component image.

[0155] Step 605: Process the image to be processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and perform fault detection on the target screen according to the target image.

[0156] The implementation of steps 603-605 is the same as that of steps 302-304, and will not be repeated here.

[0157] The above scheme obtains multiple frequencies of these target pixels by performing Fourier transform on the color signal values ​​of multiple target pixels representing at least one color signal value transformation period in the above image to be processed, wherein the highest frequency is the frequency representing the influence of the light-transmitting gaps in these target pixels; the highest frequency can be directly used as the target frequency, and the target frequency can be obtained conveniently and quickly; or the frequency range containing the above highest frequency in the preset frequency range can be used as the target frequency, and the target frequency can accurately represent the influence of the light-transmitting gaps corresponding to the image to be processed, thereby meeting the needs of different application scenarios.

[0158] Figure 8 A schematic flow chart of a third display fault detection method provided by an embodiment of the present invention is applied to the above electronic device, such as Figure 8 As shown, the method may include:

[0159] Step 801: Determine a target frequency corresponding to an image to be processed including a target screen and representing the influence of a light-transmitting gap.

[0160] Step 802: performing wavelet filtering on the image to be processed after frequency domain processing based on the first filter and the second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction.

[0161] The first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through.

[0162] Step 803: Obtain an image characterizing the influence of the light-transmitting gap based on the first component image and the second component image.

[0163] The implementation of steps 801-803 is the same as that of the above steps 301-303, and will not be repeated here.

[0164] Step 804: remove the image representing the influence of the light-transmitting gap from the image to be processed to obtain a target image.

[0165] As described above, after obtaining the image representing the influence of the light-transmitting slits, the image to be processed needs to be processed to eliminate or reduce the interference caused by the influence of the light-transmitting slits. By removing the image representing the influence of the light-transmitting slits from the image to be processed, the interference caused by the influence of the light-transmitting slits can be directly eliminated or reduced.

[0166] In this embodiment, the image representing the influence of the light-transmitting gap can be removed from the image to be processed by, but not limited to, the following methods:

[0167] 1) If the image to be processed and the image representing the influence of the light-transmitting slit are RGB images, the target Red component is obtained by subtracting the Red component of the corresponding pixel in the image representing the influence of the light-transmitting slit from the Red component of the pixel in the image to be processed; the target Green component is obtained by subtracting the Green component of the corresponding pixel in the image representing the influence of the light-transmitting slit; the target Blue component is obtained by subtracting the Blue component of the corresponding pixel in the image representing the influence of the light-transmitting slit from the Blue component. The target Red component, the target Green component and the target Blue component constitute the target RGB value of the pixel, and the target RGB values ​​of all pixels in the image to be processed constitute the target image.

[0168] 2) If the image to be processed and the image representing the influence of the light-transmitting slits are grayscale images, the target grayscale value of the pixel is obtained by subtracting the grayscale value of the corresponding pixel in the image representing the influence of the light-transmitting slits from the grayscale value of the pixel in the image to be processed; the target grayscale values ​​of all pixels in the image to be processed constitute the target image.

[0169] The above two removal methods are only exemplary descriptions, and this embodiment may also use other methods to remove the image representing the influence of the light-transmitting gap.

[0170] Step 805: Perform fault detection on the target screen according to the target image.

[0171] The implementation method of step 805 may refer to the implementation method of step 304 above, which will not be described in detail here.

[0172] The above scheme removes the image representing the influence of the light-transmitting slit from the image to be processed, thereby removing the interference caused by the influence of the light-transmitting slit from the image to be processed, thereby conveniently and accurately obtaining the target image with the influence of the light-transmitting slit eliminated.

[0173] Fig. 9 A schematic flow chart of a fourth display fault detection method provided by an embodiment of the present invention is applied to the above electronic device, such as Fig. 9 As shown, the method may include:

[0174] Step 901: Determine a target frequency corresponding to an image to be processed including a target screen and representing the influence of a light-transmitting gap.

[0175] Step 902: performing wavelet filtering on the image to be processed after frequency domain processing based on the first filter and the second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction.

[0176] The first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through.

[0177] Step 903: Obtain an image representing the influence of the light-transmitting gap based on the first component image and the second component image.

[0178] Step 904: Process the image to be processed based on the image characterizing the influence of the light-transmitting slit to obtain a target image.

[0179] The implementation of steps 901-903 is the same as that of the above steps 301-303. The implementation of step 904 can refer to the implementation of step 304, which will not be repeated here.

[0180] Step 905: performing grayscale binarization processing on the target image.

[0181] The target image contains many pixels. The diagnosis process is relatively complicated if the fault diagnosis is performed directly based on the target image. By performing grayscale binarization processing on the target image, the amount of data in the target image is greatly reduced, thereby highlighting the faulty pixels.

[0182] In this embodiment, the target image may be an RGB image or a grayscale image. If the target image is an RGB image, it needs to be grayscaled first and then grayscale binarized.

[0183] If the target image is an RGB image, grayscale processing can be performed by multiplying the RGB components of each pixel of the target image by the preset weight coefficient corresponding to each component to obtain the grayscale value of the pixel. For example:

[0184] The preset weight coefficients corresponding to the RGB components are a, b, and c respectively. The grayscale value of the pixel at the (x,y) coordinate is g(x,y)=R(x,y)*a+G(x,y)*b+B(x,y)*c, where R(x,y) is the Red component of the pixel at the (x,y) coordinate, G(x,y) is the Green component of the pixel at the (x,y) coordinate, and B(x,y) is the Blue component of the pixel at the (x,y) coordinate.

[0185] Determine whether the grayscale value of each pixel in the target image of grayscale processing reaches the preset grayscale threshold. If it reaches it, the grayscale of the pixel is considered to be 255 (it is considered to be white); if it does not reach it, the grayscale of the pixel is considered to be 0 (it is considered to be black).

[0186] The above-mentioned grayscale processing and grayscale binarization processing are exemplary descriptions, and specific parameters can be set according to actual applications.

[0187] Step 906: If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that the target screen has a display failure.

[0188] The grayscale binarization of the target image classifies similar pixels in the target image into one grayscale and amplifies the differences between non-similar pixels. Based on whether the pixels in the target image after the grayscale binarization are the same, display faults can be detected simply and conveniently.

[0189] See also Fig. 10A As shown in the figure, the target image after grayscale binarization processing contains pixels with grayscale of 0, which means that the target image is relatively uniform, and the color displayed on the target screen is determined to be uniform, and it is determined that the target screen has no display fault;

[0190] See also Fig. 10B As shown, in addition to the pixel with grayscale 0, there is also a pixel with grayscale 255 in the target image after grayscale binarization processing, which indicates that the target image is uneven. It is determined that the color displayed on the target screen is uneven, and it is determined that the target screen has a display fault.

[0191] In some specific embodiments, after determining that the target screen has a display fault, a fault reminder message may be sent in a preset notification manner, for example:

[0192] The electronic device has a display function, and the fault reminder information is displayed on the screen of the electronic device;

[0193] Or the above electronic device sends the fault reminder information to the user equipment.

[0194] The preset notification method can be set according to the actual application scenario, and this embodiment is not limited to the above two methods.

[0195] like Fig.11 As shown, based on the same inventive concept, an embodiment of the present invention provides a display fault detection device 1100, comprising:

[0196] A determination module 1101 is used to determine a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap;

[0197] A filtering module 1102 is used to perform wavelet filtering on the image to be processed after the frequency domain processing based on a first filter and a second filter to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0198] An obtaining module 1103 is configured to obtain an image representing the influence of a light-transmitting gap based on the first component image and the second component image;

[0199] The processing module 1104 is used to process the image to be processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and perform fault detection on the target screen according to the target image.

[0200] The determination module 1101 determines a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap, including:

[0201] Performing Fourier transform on color signal values ​​of a plurality of target pixels in the image to be processed to obtain frequencies of the plurality of target pixels, wherein the plurality of target pixels represent at least one color signal value transformation cycle, and the color signal value is an RGB value or a grayscale value;

[0202] The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

[0203] In some optional implementations, the processing module 1104 processes the image to be processed based on the image representing the influence of the light-transmitting slit to obtain a target image, including:

[0204] The image representing the influence of the light-transmitting slit is removed from the image to be processed to obtain a target image.

[0205] In some optional implementations, the processing module 1104 performs fault detection on the target screen according to the target image, including:

[0206] Performing grayscale binarization processing on the target image;

[0207] If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that there is a display failure on the target screen.

[0208] In some optional implementations, the filtering module 1102 obtains the first component image in the following manner:

[0209] Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or

[0210] The filtering module obtains the second component image in the following manner:

[0211] The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

[0212] In some optional implementations, the obtaining module 1103 obtains an image representing the influence of the light-transmitting gap based on the first component image and the second component image, including:

[0213] Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image;

[0214] The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

[0215] Since the device is the device in the method in the embodiment of the present invention, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0216] like Fig.12 As shown, based on the same inventive concept, an embodiment of the present invention provides an electronic device 1200, including: a processor 1201 and a memory 1202;

[0217] Memory 1202 is used to store computer programs executed by processor 1201. Memory 1202 can be a volatile memory, such as random-access memory (RAM); Memory 1202 can also be a non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD) or solid-state drive (SSD), or memory 1202 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. Memory 1202 can be a combination of the above memories.

[0218] The processor 1201 may include one or more central processing units (CPU), graphics processing units (GPU) or digital processing units, etc.

[0219] The specific connection medium between the memory 1202 and the processor 1201 is not limited in the embodiment of the present invention. Fig.12 In the embodiment, the memory 1202 and the processor 1201 are connected via a bus 1203. The bus 1203 is connected to the processor 1201 via a bus 1203. Fig.12 The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 1203 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.12 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0220] The memory stores program codes, and when the program codes are executed by the processor, the processor 1201 performs the following process:

[0221] Determine a target frequency corresponding to the image to be processed including the target screen, which represents the influence of the light-transmitting gap;

[0222] Based on the first filter and the second filter, wavelet filtering is performed on the image to be processed after the frequency domain processing to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through;

[0223] Obtaining an image representing the influence of the light-transmitting slit based on the first component image and the second component image;

[0224] The image to be processed is processed based on the image representing the influence of the light-transmitting gap to obtain a target image, and fault detection is performed on the target screen according to the target image.

[0225] In some optional implementations, the processor 1201 specifically performs:

[0226] Performing Fourier transform on color signal values ​​of a plurality of target pixels in the image to be processed to obtain frequencies of the plurality of target pixels, wherein the plurality of target pixels represent at least one color signal value transformation cycle, and the color signal value is an RGB value or a grayscale value;

[0227] The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

[0228] In some optional implementations, the processor 1201 specifically performs:

[0229] The image representing the influence of the light-transmitting slit is removed from the image to be processed to obtain a target image.

[0230] In some optional implementations, the processor 1201 specifically performs:

[0231] Performing grayscale binarization processing on the target image;

[0232] If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that there is a display failure on the target screen.

[0233] In some optional implementations, the processor 1201 specifically performs:

[0234] Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or

[0235] The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

[0236] In some optional implementations, the processor 1201 specifically performs:

[0237] Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image;

[0238] The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

[0239] Since the electronic device is an electronic device that executes the method in the embodiment of the present invention, and the principle of solving the problem by the electronic device is similar to that of the method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0240] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the display fault detection method described above are implemented. The readable storage medium may be a non-volatile readable storage medium.

[0241] The present application is described above with reference to block diagrams and / or flow charts illustrating methods, devices (systems) and / or computer program products according to embodiments of the present invention. It should be understood that a block of a block diagram and / or flow chart diagram and a combination of blocks of a block diagram and / or flow chart diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer and / or other programmable display fault detection device to produce a machine so that instructions executed via a computer processor and / or other programmable display fault detection device create a method for implementing the functions / actions specified in the block diagram and / or flow chart block.

[0242] Accordingly, the present application may also be implemented with hardware and / or software (including firmware, resident software, microcode, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium, which has a computer-usable or computer-readable program code implemented in the medium, for use by an instruction execution system or in conjunction with an instruction execution system. In the context of the present application, a computer-usable or computer-readable medium may be any medium that may contain, store, communicate, transmit, or convey a program for use by an instruction execution system, device, or apparatus, or in conjunction with an instruction execution system, device, or apparatus.

[0243] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0244] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A display fault detection method, characterized in that: The method comprises: Determine a target frequency corresponding to the image to be processed including the target screen, which represents the influence of the light-transmitting gap; Based on the first filter and the second filter, wavelet filtering is performed on the image to be processed after the frequency domain processing to obtain a first component image representing the influence of the light-transmitting slits in the column direction and a second component image representing the influence of the light-transmitting slits in the row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through; Obtaining an image representing the influence of the light-transmitting slit based on the first component image and the second component image; Processing the image to be processed based on the image representing the influence of the light-transmitting slit to obtain a target image, and performing fault detection on the target screen according to the target image; The first component image is obtained by: Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or The second component image is obtained by: The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

2. The method according to claim 1, characterized in that Determining a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap includes: Performing Fourier transform on color signal values ​​of a plurality of target pixels in the image to be processed to obtain frequencies of the plurality of target pixels, wherein the plurality of target pixels represent at least one color signal value transformation cycle, and the color signal value is a three primary color RGB value or a grayscale value; The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

3. The method according to claim 1, characterized in that The image to be processed is processed based on the image representing the influence of the light-transmitting slit to obtain a target image, including: The image representing the influence of the light-transmitting slit is removed from the image to be processed to obtain a target image.

4. The method according to claim 1, characterized in that: Performing fault detection on the target screen according to the target image includes: Performing grayscale binarization processing on the target image; If there are pixels with different grayscale values ​​in the image after the grayscale binarization processing, it is determined that there is a display failure on the target screen.

5. The method according to any one of claims 1 to 4, characterized in that: Obtaining an image characterizing the influence of the light-transmitting slit based on the first component image and the second component image includes: Perform inverse filtering on the first component image and the second component image to synthesize the first component image and the second component image to obtain a synthesized image; The composite image is processed in the spatial domain to obtain the image representing the influence of the light-transmitting slit.

6. A display fault determination device, characterized in that: The device includes: A determination module, used to determine a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap; A filtering module, configured to perform wavelet filtering on the image to be processed after frequency domain processing based on a first filter and a second filter, to obtain a first component image representing the influence of light-transmitting slits in a column direction and a second component image representing the influence of light-transmitting slits in a row direction, wherein the first filter allows frequencies other than the target frequency to pass through, and the second filter allows the target frequency to pass through; An acquisition module, configured to obtain an image representing the influence of a light-transmitting slit based on the first component image and the second component image; A processing module, used for processing the image to be processed based on the image representing the influence of the light-transmitting slit to obtain a target image, and performing fault detection on the target screen according to the target image; The filtering module is used to obtain the first component image in the following manner: Inputting the image to be processed after frequency domain processing into the first filter for row sampling to obtain a first image; inputting the first image into the second filter for column sampling to obtain the first component image; and / or Used to obtain the second component image by the following method: The image to be processed that has undergone frequency domain processing is input into the second filter for row sampling to obtain a second image; and the second image is input into the first filter for column sampling to obtain the second component image.

7. The device according to claim 6, characterized in that The determination module determines a target frequency corresponding to the image to be processed including the target screen and representing the influence of the light-transmitting gap, including: Performing Fourier transform on color signal values ​​of a plurality of target pixels in the image to be processed to obtain frequencies of the plurality of target pixels, wherein the plurality of target pixels represent at least one color signal value transformation cycle, and the color signal value is an RGB value or a grayscale value; The highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency; or a frequency range in a preset frequency range that includes the highest frequency among the frequencies of the plurality of target pixel points is used as the target frequency.

8. An electronic device, characterized in that: comprising one or more processors, and a memory for storing instructions executable by said processors; The processor is configured to execute the instruction to implement the display fault detection method according to any one of claims 1 to 5.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the display fault detection method according to any one of claims 1 to 5 is implemented.