Screen display fault detection method and device, equipment and storage medium

Abstract

The invention discloses a screen display fault detection method and device, equipment and a storage medium. The method comprises the steps that candidate defect positions of a to-be-processed screen image are determined; determining expected distribution of the candidate defect positions through a preset display fault detection model, wherein the preset display fault detection model is an autoregression analysis model established by taking the candidate defect positions in the image as independent variables; and determining a display fault point of the screen displaying the to-be-processed screen image according to the expected distribution. According to the invention, after the candidate defect position is determined, the candidate deadline position is detected according to the preset display fault detection model, the expected distribution of the candidate defect position is obtained, and the display fault point on the screen corresponding to the to-be-processed screen image is positioned according to the expected distribution, so that the detection precision of the screen display fault is improved.

Description

Technical Field

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

[0002] The popularity and spread of smart wearable devices have brought people a new visual experience. Take VR as an example. High-end VR products allow people to experience different artistic styles without leaving home. The screen and lens module of wearable products are the standard for consumers to intuitively measure product quality. If there are defects or bad pixels in the lens module, it will directly affect the user experience and product reputation. Therefore, more stringent and precise requirements are put forward for the defect specifications of VR screens in industrial production. In the process of screen detection, there are differences in the grayscale distribution of the screen between different products of the same model, and even in different positions of the same product, which leads to the variability of defect characteristics. The avoidance measures usually given for these two risks are to divide multiple screens according to different lighting methods, and to divide different areas on the screen and set different detection standards. However, this method has poor robustness and cannot completely avoid risks.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a screen display fault detection method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the detection accuracy of screen faults.

[0005] To achieve the above object, the present invention provides a screen display fault detection method, the screen display fault detection method comprising the following steps:

[0006] determining candidate defect locations of a screen image to be processed;

[0007] Determining the expected distribution of the candidate defect positions by a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables;

[0008] A display failure point of a screen displaying the screen image to be processed is determined according to the expected distribution.

[0009] Optionally, the step of determining candidate defect locations of the screen image to be processed includes:

[0010] Converting the screen image to be processed into a screen image matrix to be processed, and filtering the screen image matrix to be processed according to a preset feature detection algorithm;

[0011] Determine the local extreme value of the screen image matrix to be processed after filtering according to the preset screen image filtering matrix;

[0012] The candidate defect positions of the filtered screen image matrix to be processed are determined according to the local extreme difference values.

[0013] Optionally, before the step of determining the expected distribution of the candidate defect locations by using a preset display fault detection model, the method further includes:

[0014] Centralizing the screen image matrix to be processed, and checking the stability of the screen image matrix to be processed after centralization;

[0015] When the stationarity test passes, determining the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed;

[0016] The preset screen display fault detection model is constructed according to the partial autocorrelation function and the sequence of the centralized screen image matrix to be processed.

[0017] Optionally, the step of determining the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed comprises:

[0018] Determining the autocorrelation function of the screen image matrix to be processed according to the variance and autocovariance of the screen image matrix to be processed;

[0019] The partial autocorrelation function of the screen image matrix to be processed is determined according to the autocovariance and a preset relationship function.

[0020] Optionally, the step of constructing the preset screen display fault detection model according to the sequence of the partial autocorrelation function and the centralized screen image matrix to be processed includes:

[0021] Determining the order of a preset screen display fault detection model according to the partial autocorrelation function;

[0022] The preset screen display fault detection model is constructed according to the residual sequence of the partial autocorrelation function, the order and the sequence of the screen image matrix to be processed after centralization.

[0023] Optionally, the regression coefficient of the preset screen display fault detection model is estimated according to the least squares method.

[0024] Optionally, the step of determining, according to the expected distribution, a display failure point of a screen displaying the screen image to be processed comprises:

[0025] When the expected distribution satisfies the normal distribution, determining the critical failure threshold value according to the probability density function;

[0026] screening out abnormal expected values ​​from the expected distribution according to the critical failure threshold;

[0027] Determine the abnormal pixel points corresponding to the screen image matrix to be processed according to the abnormal expected value;

[0028] A display fault point of a screen displaying the screen image to be processed is determined according to the abnormal pixel point.

[0029] In addition, to achieve the above-mentioned purpose, the present invention also provides a screen display fault detection device, the screen display fault detection device comprising: an area determination module, a data determination module and a fault detection module;

[0030] The region determination module is used to determine the candidate defect locations of the screen image to be processed;

[0031] The data determination module is used to determine the expected distribution of the candidate defect positions by using a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables;

[0032] The fault detection module is used to determine the display fault point of the screen displaying the screen image to be processed according to the expected distribution.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also proposes a screen display fault detection device, which includes a memory, a processor, and a screen display fault detection program stored in the memory and run on the processor, and the screen display fault detection program is configured to implement the screen display fault detection method described above.

[0034] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a screen display fault detection program is stored, and when the screen display fault detection program is executed by a processor, the screen display fault detection method as described above is implemented.

[0035] The present invention discloses a screen display fault detection method, device, equipment and storage medium, the method comprising: determining a candidate defect position of a screen image to be processed; determining an expected distribution of the candidate defect position by a preset display fault detection model, the preset display fault detection model being an autoregressive analysis model established with the candidate defect position in the image as an independent variable; and determining a display fault point of a screen displaying the screen image to be processed according to the expected distribution. After determining the candidate defect position, the present invention detects the candidate defect position according to the preset display fault detection model to obtain the expected distribution of the candidate defect position, and locates the display fault point on the screen corresponding to the screen image to be processed according to the expected distribution, thereby improving the detection accuracy of the screen display fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a structural schematic diagram of a screen display fault detection device in a hardware operating environment involved in an embodiment of the present invention;

[0037] Figure 2 It is a flow chart of the first embodiment of the screen display fault detection method of the present invention;

[0038] Figure 3 It is a flow chart of a second embodiment of the screen display fault detection method of the present invention;

[0039] Figure 4 It is a flow chart of a third embodiment of the screen display fault detection method of the present invention;

[0040] Figure 5 An initial screen image of an embodiment of a screen display fault detection method of the present invention;

[0041] Figure 6 A filter map of candidate defect positions of an embodiment of a screen display fault detection method of the present invention;

[0042] Figure 7 It is a tailing diagram of the autocorrelation function of an embodiment of the screen display fault detection method of the present invention;

[0043] Figure 8 It is a truncated graph of the partial autocorrelation function of an embodiment of the screen display fault detection method of the present invention;

[0044] Fig. 9 It is an expected distribution diagram of an embodiment of a screen display fault detection method of the present invention;

[0045] Fig.10 It is an expected box plot of an embodiment of a screen display fault detection method of the present invention;

[0046] Fig.11 This is a screen defect accurate positioning diagram of an embodiment of a screen display fault detection method of the present invention;

[0047] Fig.12 It is a structural block diagram of the first embodiment of the screen display fault detection device of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] Reference Figure 1 , Figure 1The present invention is a schematic diagram of the structure of a screen display fault detection device in a hardware operating environment according to an embodiment of the present invention.

[0051] like Figure 1 As shown, the screen display fault detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and the user interface 1003 may also include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0052] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the screen display fault detection device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0053] like Figure 1 As shown, the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a screen display fault detection program.

[0054] exist Figure 1 In the screen display fault detection device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the user device; the screen display fault detection device calls the screen display fault detection program stored in the memory 1005 through the processor 1001, and executes the screen display fault detection method provided by the embodiment of the present invention.

[0055] Based on the above hardware structure, an embodiment of the screen display fault detection method of the present invention is proposed.

[0056] Reference Figure 2 , Figure 2The figure is a flow chart of the first embodiment of the screen display fault detection method of the present invention, and provides the first embodiment of the screen display fault detection method of the present invention.

[0057] Step S10: Determine candidate defect locations of the screen image to be processed.

[0058] It should be noted that the executor of this embodiment can be a screen display fault detection device with data processing, network communication and program running functions, such as a smart wearable device controller, etc., or other electronic devices that can achieve the same or similar functions. This embodiment does not impose any restrictions on this.

[0059] It should be noted that the candidate defect location only determines the approximate location where the screen image to be processed has a fault, but it is not accurate. It is necessary to determine the expected distribution of the screen image to be processed based on the autoregressive model, so as to accurately locate the display fault point on the screen based on the expected distribution.

[0060] It can be understood that in this embodiment, the pixel points of the image displayed on the screen are used as the basis for determining the screen fault position, so the candidate defect position can be an image matrix composed of pixel points.

[0061] In a specific implementation, the screen image to be processed is filtered, and the filtering result is returned to the spatial domain. The local range is calculated based on the K×K mask, and the candidate defect position is determined based on the local range. The K value can be less than zero, and can be 2×2 or 5×5. This embodiment is not limited to this.

[0062] Further, in order to improve the accuracy of screen defect detection, therefore, step S10 in this embodiment may include:

[0063] Converting the screen image to be processed into a screen image matrix to be processed, and filtering the screen image matrix to be processed according to a preset feature detection algorithm;

[0064] Determine the local extreme value of the screen image matrix to be processed after filtering according to the preset screen image filtering matrix;

[0065] The candidate defect positions of the filtered screen image matrix to be processed are determined according to the local extreme difference values.

[0066] It should be noted that the preset feature detection algorithm may be a DOG operator, and the screen image matrix to be processed is filtered according to the DOG operator. An example of filtering by the DOG operator is as follows:

[0067]

[0068] Where σ represents the variance, and x, y represent the coordinates of the screen image matrix to be processed.

[0069] It should be noted that the screen image matrix to be processed is filtered in the frequency domain according to the DOG operator, and the filtered screen image matrix to be processed is returned to the spatial domain.

[0070] It should be noted that the preset screen image filter matrix may be a K×K mask, and the local range of the screen image matrix to be processed is calculated based on the K×K mask.

[0071] It can be understood that the candidate defect positions of the screen image matrix to be processed are determined according to the range values ​​within the K×K mask matrix, and the binarization search for defects using the range instead of the original value can avoid missing detection of tiny defects.

[0072] For ease of understanding, refer to Figure 5 and Figure 6 To explain, Figure 5 for the initial screen image, Figure 6 It is the candidate defect location filter map.

[0073] Step S20: determining the expected distribution of the candidate defect positions by using a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables.

[0074] It should be noted that the preset display fault detection model determines the expected distribution of the candidate defect positions according to the grayscale distribution characteristics of the candidate defect positions, that is, determines the expected distribution of the candidate defect positions according to the actual values ​​and expected values ​​of the candidate defect positions.

[0075] It should be noted that the expected distribution of the candidate defect positions can be the residual distribution of the candidate defect positions. The residual distribution of the expected distribution and the actual distribution of the candidate defect positions is determined according to the preset display fault detection model, and whether the defect area is an abnormal point is determined pixel by pixel based on the residual distribution.

[0076] Step S30: determining a display failure point of the screen displaying the screen image to be processed according to the expected distribution.

[0077] In a specific implementation, a critical failure threshold of an expected distribution is determined according to a probability density function, an abnormal expected value is screened out from the expected distribution according to the critical failure threshold, corresponding pixels are determined according to the abnormal expected value, and display failure points of the screen are determined according to the pixels.

[0078] This embodiment determines the candidate defect positions of the screen image to be processed; determines the expected distribution of the candidate defect positions through a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables; and determines the display fault point of the screen displaying the screen image to be processed according to the expected distribution. After determining the candidate defect positions, this embodiment detects the candidate defect positions according to the preset display fault detection model to obtain the expected distribution of the candidate defect positions, and locates the display fault point on the screen corresponding to the screen image to be processed according to the expected distribution, thereby improving the detection accuracy of the screen display fault.

[0079] Reference Figure 3 , Figure 3 This is a flow chart of a second embodiment of the screen display fault detection method of the present invention. Figure 2 The first embodiment shown here is a second embodiment of the screen display fault detection method of the present invention.

[0080] In the second embodiment, before step S20, the method further includes:

[0081] Step S101: performing centralization processing on the screen image matrix to be processed, and checking the stability of the screen image matrix to be processed after centralization.

[0082] It can be understood that the centralization processing of the screen image matrix to be processed may be to remove the mean of the screen image to be processed.

[0083] It should be noted that testing the stationarity of the screen image matrix to be processed after centering requires that the mean and variance of the screen image matrix to be processed after centering do not change significantly.

[0084] Step S102: when the stationarity test passes, determining the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed.

[0085] It should be noted that the autocorrelation function describes the correlation between the current value and the past value of the sequence. This correlation includes direct and indirect correlation information, such as trend, seasonality, periodicity, and residuals. The partial autocorrelation function describes the relationship between the residual and the next lagged value. Unlike the autocorrelation function, the partial autocorrelation function only has direct correlation.

[0086] Furthermore, in order to improve the accuracy of screen defect detection, step S102 in this embodiment may include:

[0087] Determining the autocorrelation function of the screen image matrix to be processed according to the variance and autocovariance of the screen image matrix to be processed;

[0088] The partial autocorrelation function of the screen image matrix to be processed is determined according to the autocovariance and a preset relationship function.

[0089] It should be noted that the autocorrelation function can be:

[0090]

[0091] In the formula, represents the autocorrelation coefficient of the k-period lag, Cov(x t ,x t-k ) represents the autocovariance, Var(x t ) represents the variance, x t represents a sequence of screen image matrices to be processed, represents the autocovariance of the k-period lag, represents the autocovariance.

[0092] It should be noted that the partial autocorrelation function can be estimated according to the Yule-Walker equation, which can be:

[0093]

[0094] In the formula, α k represents the partial autocorrelation coefficient of lag k, represents the autocovariance of lag k.

[0095] Step S103: constructing the preset screen display fault detection model according to the partial autocorrelation function and the sequence of the centralized screen image matrix to be processed.

[0096] It should be noted that the order of the preset screen display fault detection model can be determined according to the truncation characteristics of the partial autocorrelation function.

[0097] It should be noted that the partial autocorrelation coefficient and the residual are estimated according to the Yule-Walker equation, and the preset screen display fault detection model is constructed according to the sequence of the screen image matrix to be processed after centralization and the residual sequence.

[0098] Furthermore, in order to improve the accuracy of screen defect detection, step S103 in this embodiment may include:

[0099] Determining the order of a preset screen display fault detection model according to the partial autocorrelation function;

[0100] The preset screen display fault detection model is constructed according to the residual sequence of the partial autocorrelation function, the order and the sequence of the screen image matrix to be processed after centralization.

[0101] It should be noted that the most important role of the partial autocorrelation function is to serve as a basis for determining the order of the preset screen display fault detection model, and it also avoids the risk of multicollinearity in regression analysis.

[0102] It should be noted that the order of the preset screen display fault detection model is determined according to the number of truncation steps of the partial autocorrelation coefficient of the partial autocorrelation function.

[0103] For ease of understanding, refer to Figure 7 and Figure 8 To explain, Figure 7 This is the tail plot of the autocorrelation function. Figure 8 is the partial autocorrelation function truncated diagram, from Figure 7 and Figure 8 It can be seen that the autocorrelation function has a tailing feature, and the partial autocorrelation function has a truncation feature. Figure 7 The horizontal axis represents the delay order, and the vertical axis represents the autocorrelation coefficient. Figure 8 The horizontal axis represents the delay order, and the vertical axis represents the partial autocorrelation coefficient.

[0104] It should be noted that the preset screen display fault detection model can be:

[0105]

[0106] In the formula, α p represents the regression coefficient, p represents the order of the preset screen display fault detection model, x t represents the sequence of screen image matrices to be processed after centralization, ε t represents the residual sequence, and t represents the sequence length.

[0107] It can be understood that the regression coefficient of the preset screen display fault detection model can be estimated according to the least square method, which can be:

[0108]

[0109] This embodiment performs centralization processing on the screen image matrix to be processed, and checks the stability of the screen image matrix to be processed after centralization; when the stability test passes, the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed are determined; and the preset screen display fault detection model is constructed according to the sequence of the partial autocorrelation function and the screen image matrix to be processed after centralization. This embodiment uses the screen image matrix to be processed as an independent variable, and constructs a preset screen display fault detection model according to the autocorrelation function and the partial autocorrelation function, so as to determine the screen display fault point according to the preset screen display fault detection model, thereby improving the robustness of screen defect detection.

[0110] Reference Figure 4, Figure 4 This is a flow chart of a third embodiment of the screen display fault detection method of the present invention. Figure 2 The first embodiment shown here is a third embodiment of the screen display fault detection method of the present invention.

[0111] In the third embodiment, the step S30 further includes:

[0112] Step S301: when the expected distribution satisfies the normal distribution, determining a critical failure threshold according to a probability density function.

[0113] It should be noted that the probability density function can be:

[0114]

[0115] In the formula, σ represents variance, μ represents expected value, and x represents independent variable.

[0116] Step S302: Filter out abnormal expected values ​​from the expected distribution according to the critical failure threshold.

[0117] It can be understood that the critical failure threshold is calculated according to the probability density function. For example, the critical failure threshold may be 3σ. Then, expected values ​​outside 3σ may be screened out from the expected distribution and these expected values ​​may be taken as abnormal expected values.

[0118] For ease of understanding, refer to Fig. 9 and Fig.10 To explain, Fig. 9 is the expected distribution diagram, Fig.10 is the expected box plot, from Fig. 9 It can be seen that the expected distribution satisfies the normal distribution. The ordinate represents the residual value, and the abscissa represents the value of the model independent variable. Fig.10 Values ​​outside the upper and lower bounds are values ​​outside 3σ, that is, abnormal expected values. There are upper and lower bounds above and below the rectangle in the figure, and the vertical axis represents the variance value. If it exceeds 3σ, that is, exceeds the upper and lower bounds, it is marked as an abnormal expected value.

[0119] Step S303: determining the abnormal pixel points corresponding to the screen image matrix to be processed according to the abnormal expected value.

[0120] It should be noted that all pixels of the screen image to be processed have corresponding expected values, and after the abnormal pixels are determined, their corresponding abnormal pixels can be determined.

[0121] Step S304: determining the display fault point of the screen displaying the screen image to be processed according to the abnormal pixel point.

[0122] It is understandable that each pixel in the screen image matrix to be processed has its corresponding coordinates. Therefore, the abnormal coordinates in the screen image matrix to be processed can be determined based on the abnormal pixels, and the position of the screen defect can be located based on the abnormal coordinates.

[0123] For ease of understanding, refer to Fig.11 To explain, Fig.11 To accurately locate screen defects, Fig.11 and Figure 6 In comparison, it can be seen that the positioning accuracy of the screen defect position is higher.

[0124] In this embodiment, when the expected distribution satisfies the normal distribution, a critical failure threshold is determined according to a probability density function; an abnormal expected value is screened out from the expected distribution according to the critical failure threshold; abnormal pixel points corresponding to the matrix of the screen image to be processed are determined according to the abnormal expected value; and a display failure point of the screen displaying the screen image to be processed is determined according to the abnormal pixel points. In this embodiment, a critical failure threshold is determined according to a probability density function, an abnormal expected value is screened out from the expected distribution according to the critical failure threshold, corresponding abnormal pixel points are determined according to the abnormal expected value, and the place where the screen fails is located according to the abnormal pixel points, thereby locating screen defects according to the distributed method, which not only reduces the development cycle but also improves the efficiency of screen defect detection.

[0125] In addition, an embodiment of the present invention further provides a storage medium, on which a screen display fault detection program is stored. When the screen display fault detection program is executed by a processor, the screen display fault detection method as described above is implemented.

[0126] In addition, refer to Fig.12 , the embodiment of the present invention also provides a screen display fault detection device, the screen display fault detection device comprises: an area determination module 10, a data determination module 20 and a fault detection module 30;

[0127] The region determination module 10 is used to determine the candidate defect locations of the screen image to be processed;

[0128] The data determination module 20 is used to determine the expected distribution of the candidate defect positions by using a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables;

[0129] The fault detection module 30 is used to determine the display fault point of the screen displaying the screen image to be processed according to the expected distribution.

[0130] This embodiment determines the candidate defect positions of the screen image to be processed; determines the expected distribution of the candidate defect positions through a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables; and determines the display fault point of the screen displaying the screen image to be processed according to the expected distribution. After determining the candidate defect positions, this embodiment detects the candidate defect positions according to the preset display fault detection model to obtain the expected distribution of the candidate defect positions, and locates the display fault point on the screen corresponding to the screen image to be processed according to the expected distribution, thereby improving the detection accuracy of the screen display fault.

[0131] Based on the above-mentioned first embodiment of the screen display fault detection device of the present invention, a second embodiment of the screen display fault detection device of the present invention is proposed.

[0132] In this embodiment, the region determination module 10 is used to convert the screen image to be processed into a screen image matrix to be processed, and filter the screen image matrix to be processed according to a preset feature detection algorithm.

[0133] Furthermore, the region determination module 10 is also used to determine the local extreme difference value of the screen image matrix to be processed after filtering according to a preset screen image filtering matrix.

[0134] Furthermore, the region determination module 10 is also used to determine the candidate defect positions of the filtered screen image matrix to be processed according to the local extreme difference value.

[0135] Furthermore, the data determination module 20 is also used to perform centralization processing on the screen image matrix to be processed, and to check the stability of the screen image matrix to be processed after centralization.

[0136] Furthermore, the data determination module 20 is also used to determine the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed when the stationarity test passes.

[0137] Furthermore, the data determination module 20 is also used to construct the preset screen display fault detection model according to the partial autocorrelation function and the sequence of the centralized screen image matrix to be processed.

[0138] Furthermore, the data determination module 20 is further configured to determine the autocorrelation function of the screen image matrix to be processed according to the variance and autocovariance of the screen image matrix to be processed.

[0139] Furthermore, the data determination module 20 is also used to determine the partial autocorrelation function of the screen image matrix to be processed according to the autocovariance and a preset relationship function.

[0140] Furthermore, the data determination module 20 is also used to determine the order of a preset screen display fault detection model according to the partial autocorrelation function.

[0141] Furthermore, the data determination module 20 is also used to construct the preset screen display fault detection model according to the residual sequence of the partial autocorrelation function, the order and the sequence of the screen image matrix to be processed after centralization.

[0142] Furthermore, the fault detection module 30 is further configured to determine a critical fault threshold according to a probability density function when the expected distribution satisfies a normal distribution.

[0143] Furthermore, the fault detection module 30 is further configured to filter out abnormal expected values ​​from the expected distribution according to the critical fault threshold.

[0144] Furthermore, the fault detection module 30 is also used to determine the abnormal pixel points corresponding to the screen image matrix to be processed according to the abnormal expected value.

[0145] Furthermore, the fault detection module 30 is further configured to determine a display fault point of the screen displaying the screen image to be processed according to the abnormal pixel point.

[0146] Other embodiments or specific implementations of the screen display fault detection device of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0147] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0148] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0149] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0150] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A screen display fault detection method, characterized in that: The screen display fault detection method comprises the following steps: determining candidate defect locations of a screen image to be processed; Determining the expected distribution of the candidate defect positions by a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables; A display failure point of a screen displaying the screen image to be processed is determined according to the expected distribution.

2. The screen display fault detection method according to claim 1, characterized in that: The step of determining the candidate defect positions of the screen image to be processed comprises: Converting the screen image to be processed into a screen image matrix to be processed, and filtering the screen image matrix to be processed according to a preset feature detection algorithm; Determine the local extreme value of the screen image matrix to be processed after filtering according to the preset screen image filtering matrix; The candidate defect positions of the filtered screen image matrix to be processed are determined according to the local extreme difference values.

3. The screen display fault detection method according to claim 2, characterized in that: Before the step of determining the expected distribution of the candidate defect locations by presetting the display fault detection model, the method further includes: Centralizing the screen image matrix to be processed, and checking the stability of the screen image matrix to be processed after centralization; When the stationarity test passes, determining the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed; The preset screen display fault detection model is constructed according to the partial autocorrelation function and the sequence of the centralized screen image matrix to be processed.

4. The screen display fault detection method according to claim 3, characterized in that: The step of determining the autocorrelation function of the screen image matrix to be processed and the partial autocorrelation function of the screen image matrix to be processed comprises: Determining the autocorrelation function of the screen image matrix to be processed according to the variance and autocovariance of the screen image matrix to be processed; The partial autocorrelation function of the screen image matrix to be processed is determined according to the autocovariance and a preset relationship function.

5. The screen display fault detection method according to claim 3, characterized in that: The step of constructing the preset screen display fault detection model according to the sequence of the partial autocorrelation function and the centralized screen image matrix to be processed comprises: Determining the order of a preset screen display fault detection model according to the partial autocorrelation function; The preset screen display fault detection model is constructed according to the residual sequence of the partial autocorrelation function, the order and the sequence of the screen image matrix to be processed after centralization.

6. The screen display fault detection method according to claim 5, characterized in that: The regression coefficients of the preset screen display fault detection model are estimated according to the least squares method.

7. The screen display fault detection method according to any one of claims 1 to 6, characterized in that: The step of determining the display failure point of the screen displaying the screen image to be processed according to the expected distribution comprises: When the expected distribution satisfies the normal distribution, determining the critical failure threshold value according to the probability density function; screening out abnormal expected values ​​from the expected distribution according to the critical failure threshold; Determine the abnormal pixel points corresponding to the screen image matrix to be processed according to the abnormal expected value; A display fault point of a screen displaying the screen image to be processed is determined according to the abnormal pixel point.

8. A screen display fault detection device, characterized in that: The screen display fault detection device comprises: an area determination module, a data determination module and a fault detection module; The region determination module is used to determine the candidate defect locations of the screen image to be processed; The data determination module is used to determine the expected distribution of the candidate defect positions by using a preset display fault detection model, wherein the preset display fault detection model is an autoregressive analysis model established with the candidate defect positions in the image as independent variables; The fault detection module is used to determine the display fault point of the screen displaying the screen image to be processed according to the expected distribution.

9. A screen display fault detection device, characterized in that: The screen display fault detection device comprises: a memory, a processor and a screen display fault detection program stored in the memory and executable on the processor. When the screen display fault detection program is executed by the processor, the steps of the screen display fault detection method according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a screen display fault detection program, and when the screen display fault detection program is executed by the processor, the steps of the screen display fault detection method according to any one of claims 1 to 7 are implemented.

Images