Screen dead pixel detection method and device and storage medium

Abstract

The invention discloses a screen dead pixel detection method, detection equipment and a storage medium, relates to the technical field of screen defect detection, and discloses a screen dead pixel detection method comprising the following steps: obtaining a first detection image collected based on a to-be-detected screen, and determining the diameter size and the number of abnormal points of the first detection image; if the diameter size is smaller than or equal to the preset size and the number is smaller than or equal to the preset number, the shooting angle of the to-be-detected screen is adjusted, and a second detection image of the to-be-detected screen is collected; and if the number of the abnormal points of the first detection image is greater than the number of the abnormal points of the second detection image, determining that the repeated detection points between the first detection image and the second detection image are screen dead pixels. According to the method, two images collected at different shooting angles are analyzed, repeated detection points between the images are selected as screen dead pixels with the number of abnormal points as a reference, analysis is carried out through the number of the abnormal points, misjudgment caused by interference of light reflection, dust and the like is reduced, and the detection accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of screen defect detection, in particular to a screen dead point detection method, a detection device and a storage medium. BACKGROUND

[0002] When detecting a screen, dust, fibers, water vapor and other impurities inevitably exist in the production, storage or use environment of the screen, and foreign matter or dirt is usually attached to the surface of the screen. Therefore, when detecting the screen, it is difficult to distinguish the foreign matter in the detection picture from the actual screen dead point, resulting in low detection accuracy.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a screen dead point detection method, a detection device and a storage medium, which aims to solve the technical problem of low screen dead point detection accuracy.

[0005] To achieve the above purpose, the present application provides a screen dead point detection method, which comprises: acquiring a first detection image based on a screen to be detected, and determining the diameter size and number of abnormal points of the first detection image; if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, adjusting the shooting angle of the screen to be detected, and collecting a second detection image of the screen to be detected; if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determining the repeated detection points between the first detection image and the second detection image as screen dead points.

[0006] In an embodiment, after the step of determining the repeated detection points between the first detection image and the second detection image as screen dead points, the screen dead point detection method further comprises: if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determining the theoretical offset of the abnormal points according to the shooting angle; determining the expected position, actual position and actual offset of the abnormal points of the first detection image in the second detection image; determining the dust points according to the difference between the theoretical offset and the actual offset; screening out the dust points and determining the repeated detection points based on the matching degree between the expected position and the actual position.

[0007] In an embodiment, after the step of determining the expected position, the actual position and the actual offset of the abnormal point of the first detection image in the second detection image, the method for detecting the screen dead point further comprises: determining a repeated point according to the matching degree between the expected position and the actual position, and determining a dust point according to the difference between the theoretical offset and the actual offset based on the repeated point; eliminating the dust point in the repeated point to obtain the repeated detection point between the first detection image and the second detection image.

[0008] In an embodiment, if the diameter size is less than or equal to a preset size, and the number is less than or equal to a preset number, the step of adjusting the shooting angle of the screen to be detected and collecting a second detection image of the screen to be detected comprises: if the diameter size is less than or equal to a preset size, and the number is less than or equal to a preset number, performing a dust blowing action based on the screen to be detected; adjusting the placement position of the screen to be detected or moving the image acquisition device based on a preset angle to collect the second detection image of the screen to be detected.

[0009] In an embodiment, after the step of adjusting the shooting angle of the screen to be detected and collecting a second detection image of the screen to be detected if the diameter size is less than or equal to a preset size, and the number is less than or equal to a preset number, the method for detecting the screen dead point further comprises: if the number of abnormal points of the first detection image is less than or equal to the number of abnormal points of the second detection image, determining non-repeated points between the first detection image and the second detection image; collecting a third detection image of the screen to be detected, wherein the shooting angle of the third detection image is the same as the shooting angle of the first detection image; determining a target detection point corresponding to the non-repeated point in the third detection image, and taking the target detection point and the repeated detection point between the first detection image and the second detection image as the screen dead point.

[0010] In an embodiment, after the step of obtaining a first detection image collected based on a screen to be detected and determining the diameter size and the number of abnormal points of the first detection image, the method for detecting the screen dead point further comprises: if the diameter size is greater than a preset size and / or the number is greater than a preset number, determining the abnormal point of the first detection image as a screen dead point.

[0011] In an embodiment, after the step of adjusting the shooting angle of the screen to be detected and collecting the second detection image of the screen to be detected if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, the screen dead point detection method further comprises: determining a grid point position of the abnormal point in a virtual grid of the first detection image; determining a repeated detection point between the first detection image and the second detection image according to the grid point position and an adjustment value of the shooting angle.

[0012] In an embodiment, after the step of determining the repeated detection point between the first detection image and the second detection image as a screen dead point if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, the screen dead point detection method further comprises: determining a non-repeated detection point between the first detection image and the second detection image as a dust point.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a detection device, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the screen dead point detection method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the screen dead point detection method as described above.

[0015] The one or more technical solutions proposed in the present application have at least the following technical effects: First, the first detection image of the screen to be detected is obtained and the diameter size and the number of abnormal points are determined, and when the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, the shooting angle is adjusted and the second detection image is collected, and then the repeated detection points of the first detection image and the second detection image with more abnormal points are determined as screen dead points by comparing the number of abnormal points of the first detection image and the second detection image. Based on this, when the number of abnormal points of the first detection image is more, it means that the probability of mixing non-dead points is higher, and the second detection image has filtered part of the non-dead points due to the change of the angle. At this time, only the repeated detection points are retained, which is equivalent to verifying the abnormal points of the first image with the filtering result of the second image, so as to further eliminate the non-screen dead points that still exist after the angle change, reduce the situation of misjudging non-dead points as dead points, and improve the accuracy of screen dead point detection. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, those skilled in the art can obtain other drawings from these drawings without any creative effort.

[0018] Figure 1 A flowchart provided for the first embodiment of the screen dead point detection method of the present application; Figure 2 A flowchart provided for the second embodiment of the screen dead point detection method of the present application; Figure 3 A flowchart provided for the fourth embodiment of the screen dead point detection method of the present application; Figure 4 A brief flowchart of the screen dead point detection method provided for the fourth embodiment of the present application; Figure 5 A device structure diagram of the hardware running environment involved in the screen dead point detection method in the embodiments of the present application.

[0019] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0021] The main solution of the embodiments of the present application is: acquiring a first detection image based on a to-be-detected screen, and determining the diameter size and number of abnormal points of the first detection image; If the diameter size is less than or equal to a preset size, and the number is less than or equal to a preset number, adjusting the shooting angle of the to-be-detected screen, and acquiring a second detection image of the to-be-detected screen; If the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determining the repeated detection points between the first detection image and the second detection image as screen dead points.

[0022] In the present embodiment, for the convenience of description, the following describes the detection device of the screen dead points as the execution subject.

[0023] When the screen is detected, due to the environmental problems of the screen itself, foreign matters or impurities usually exist on the surface of the screen. Therefore, when the screen is detected, it is difficult to distinguish the foreign matters in the detection picture from the actual screen bad points, resulting in low detection accuracy.

[0024] The present application provides a solution, by collecting detection images of the screen to be detected at different shooting angles, and then analyzing the number of abnormal points of the detection images. When the number of abnormal points of the first detection image is large, it means that the probability of mixing non-bad points is higher. The second detection image has filtered part of the non-bad points due to the change of angle. At this time, only the repeated detection points between the two images are retained, which is equivalent to verifying the abnormal points of the first image with the filtering results of the second image. Therefore, the non-screen bad points still existing after the change of angle are further eliminated, the situation of misjudging non-bad points as bad points is reduced, and the accuracy of screen bad point detection is improved.

[0025] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a screen bad point detection device, etc. The present embodiment and the following embodiments will be described below taking the screen bad point detection device as an example.

[0026] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0027] Based on this, the present embodiment provides a screen bad point detection method, referring to Figure 1 , Figure 1 The flowchart of the first embodiment of the screen bad point detection method of the present application.

[0028] In the present embodiment, the screen bad point detection method comprises steps S10-S40: Step S10, acquiring a first detection image collected based on a screen to be detected, and determining the diameter size and number of abnormal points of the first detection image.

[0029] The first detection image is an image of a screen to be detected, such as an OLED (Organic Light-Emitting Diode) mobile phone screen, captured by an image acquisition device, such as an industrial camera, at an initial angle, and contains the screen display content and possible defects such as dead pixels, reflections and dust, which are represented as abnormal points in the image that deviate from the surrounding normal pixel area in brightness, color or shape. The initial angle is 0°, and the first detection image is a front view detection image. The diameter size is the diameter of the circumscribed circle of the abnormal point, usually in pixels, which is converted to the actual millimeter value through the pixel-physical size mapping relationship; the number is the total number of abnormal points in the image.

[0030] In this embodiment, the screen to be detected is first controlled to display a pure white screen, and the detection device is placed in a dark environment to eliminate background interference. Then, a 1200-megapixel industrial camera is controlled to capture the screen in a certain range at a 0° front view angle and an exposure time of 10 ms, to obtain the first detection image. After obtaining the first detection image, the abnormal points in the image are first marked, and then the contours of the abnormal points are extracted and the circumscribed circle diameter is calculated through a preset algorithm such as an edge detection algorithm, while the total number of abnormal points is counted, and finally the diameter size and number of abnormal points are obtained. It can be understood that the identification process of the abnormal points is a prior art, and the present application does not limit this.

[0031] Alternatively, the screen to be detected can also display other colors such as pure black during the screen detection process, and the entire screen area of the screen to be detected can also be directly captured, which is not limited by the present application.

[0032] In another optional embodiment, the screen to be detected can be controlled to display black, white and red color pictures in turn, and the camera can be controlled to continuously capture 3 images at the same angle, and then the images can be input into a pre-trained YOLOv5 abnormal detection model, and then the position coordinates and confidence of each abnormal point can be output by the model, and based on the abnormal points identified by the model, the actual diameter can be calculated through the pixel coordinates, and the number of abnormal points can be counted.

[0033] The present embodiment records the diameter size and number of abnormal points, so that when the diameter size and / or number of abnormal points do not meet the requirements, these abnormal points are directly determined as screen dead points.

[0034] In step S20, if the diameter size is less than or equal to a preset size, and the number is less than or equal to a preset number, the shooting angle of the screen to be detected is adjusted, and a second detection image of the screen to be detected is acquired.

[0035] In the embodiment, the preset size is an abnormal point diameter threshold value, and exceeding the threshold value indicates that the screen has a serious dead point defect, and thus the abnormal point is directly determined as a screen dead point without secondary verification. Similarly, the preset number is a maximum number of abnormal points allowed to be subjected to secondary detection, and when the number is too large, the screen needs to be scrapped without further detection. The adjusted shooting angle refers to an angle between the camera when shooting the first detection image and the second detection image.

[0036] As an optional implementation, when the size parameter and the number parameter of the abnormal points in the first detection image meet the preset size and the preset number, an angle adjustment instruction is triggered to move the camera to change the shooting angle or to move the screen to be detected to change the shooting angle. For example, a mechanical arm carrying the camera is controlled to rotate 45° around the center axis of the screen, and the camera focal length is adjusted to clear imaging. Then, the display screen of the screen to be detected is kept, and the camera is controlled to shoot the second detection image with the same exposure parameter, where the formats of the two images are the same.

[0037] In another optional implementation, when the size parameter and the number parameter of the abnormal points in the first detection image meet the preset size and the preset number, a dust blowing action needs to be performed based on the screen to be detected to blow off the dust in the screen to be detected, and then the placement position of the screen to be detected is adjusted or the image acquisition device is moved based on a preset angle, and finally the second detection image of the screen to be detected is acquired. The ion blowing process can be performed by an ion blower. Therefore, the second detection image is acquired after the dust blowing process is performed on the screen to be detected, the interference of the dust is excluded based on a physical means, the number of non-dead points in the second detection image is reduced, and the detection accuracy is improved.

[0038] Optionally, if the diameter size is greater than the preset size and / or the number is greater than the preset number, the abnormal points in the first detection image are determined as screen dead points without secondary shooting and subsequent verification.

[0039] The embodiment adjusts the shooting angle, performs secondary verification based on the angle sensitivity of non-dead points such as dust, and thus improves the detection accuracy of subsequent real dead points.

[0040] It should be noted that the camera can be moved by a calibration transformation matrix of the camera so that the abnormal point is located in the camera optical axis.

[0041] In step S30, if the number of abnormal points in the first detection image is greater than the number of abnormal points in the second detection image, the repeated detection points between the first detection image and the second detection image are determined as screen dead points.

[0042] In the embodiment, the screen bad point is a physical defect of the screen itself, and its position is completely fixed on the screen panel and is irrelevant to the shooting angle. The screen bad point will keep a stable relative position in the image no matter the screen is shot from the front or the side. The real bad point will definitely appear in both the first and second detection images and become a repeated detection point.

[0043] The existence of the non-bad point in the first detection image depends on the initial shooting angle. After the shooting angle is adjusted, the relative position of the light source and the lens changes, and the reflection condition is destroyed. Such a point will disappear, for example, the dust is a small foreign matter on the screen surface. The change of the shooting angle can cause the reflection intensity of the dust to decrease sharply or be covered by the screen background, so that the dust is no longer identified as an abnormal point in the second detection image. At this time, the number of abnormal points in the first detection image is greater than that in the second detection image. Similarly, new non-bad points can appear in the second detection image due to the change of the shooting angle. Therefore, directly taking the repeated detection points between the first detection image and the second detection image as the screen bad points and taking the repeatedly appearing points as the screen bad points can effectively filter out the non-bad points under the normal shooting angle and the new non-bad points generated after the adjustment of the shooting angle, so as to improve the detection accuracy.

[0044] It can be understood that the dust blowing process only removes the larger movable dust, and the dust with a higher adhesion degree to the screen cannot be removed. Therefore, even after the dust blowing process, the number of abnormal points in the first detection image can be greater than that in the second detection image.

[0045] Optionally, the non-repeated detection points between the first detection image and the second detection image can also be determined as dust points.

[0046] The embodiment provides a detection method of a screen bad point. When the first detection image is acquired and the size and number of abnormal points of the first image meet the secondary detection requirement, a second detection image is acquired based on different shooting angles. When the number of abnormal points of the first detection image is greater, the repeated detection points between the two detection images are taken as the screen bad points. In this way, the non-bad points under the normal shooting angle and the new non-bad points generated after the adjustment of the shooting angle are filtered out. Therefore, the accuracy of the detection of the screen bad point is improved through the position stability of the real bad point and the angle sensitivity of the non-bad point.

[0047] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those of the first embodiment can be referred to the foregoing description, and will not be described in detail. On this basis, please refer to Figure 2 , before step S30, the detection method of the screen bad point further includes steps S40-S70: In step S40, if the number of abnormal points of the first detection image is greater than that of the second detection image, the theoretical offset of the abnormal point is determined according to the shooting angle.

[0048] In the embodiment, when the number of abnormal points in the first detection image is greater than the number of abnormal points in the second detection image, the theoretical displacement of the abnormal points can be calculated by the shooting angle. Wherein, the theoretical displacement of the abnormal points in the two images can be calculated by a geometric formula based on the relative position of the screen and the camera and the shooting angle θ. For example, the vertical distance L between the camera and the screen is measured to be 30 cm, which is the vertical distance when the first image is shot, and the angle adjustment parameter θ is 15°, and then the theoretical displacement ΔLtheo=Lxtanθ (tan15°≈0.2679) is calculated according to the geometric relationship, which is ΔLtheo≈30x0.2679=8.037 cm; then the pixel displacement is converted, and it is known that the physical width of the screen 15 cm corresponds to the image width 1080 pixels, 1 cm=72 pixels, so the theoretical pixel displacement is 8.037x72≈578 pixels.

[0049] Step S50, determining the expected position, actual position and actual displacement of the abnormal point in the first detection image in the second detection image.

[0050] In the embodiment, the expected position is the position where the abnormal point in the first detection image should appear in the second detection image based on the theoretical displacement, the actual position is the position where the abnormal point is detected in the second detection image, and the actual displacement is the distance between the current position and the actual position.

[0051] The pixel coordinates of the abnormal point P1 on the first detection image can be extracted first, then the expected position is calculated according to the theoretical displacement, then the abnormal points within 100 pixels around the coordinates where P1 is located in the second image are searched to obtain the actual position P2, and then the actual displacement ΔP is calculated based on the distance between the actual position P2 and the current position P1.

[0052] Step S60, determining the dust point according to the difference between the theoretical displacement and the actual displacement.

[0053] In the embodiment, the dust point is an abnormal point whose displacement difference exceeds a preset threshold, and the actual displacement of the abnormal point deviates significantly from the theoretical value due to the displacement of the surface dust which is not constrained by the internal geometry of the screen. Therefore, when determining the dust point, the difference between the theoretical displacement and the actual displacement is calculated, and when the difference is greater than the preset threshold, it is determined to be a dust point.

[0054] Alternatively, the theoretical displacement and the actual displacement can also be input into a machine classification learning model, and the confidence of the dust point is output based on the learning model, and whether it is a dust point is determined based on the confidence.

[0055] Step S70, screening out the dust point and determining the repeatedly detected point based on the matching degree between the expected position and the actual position.

[0056] In the embodiment, the screening of the dust point can be marking the abnormal point as a dust point, or directly deleting the abnormal point in the image. After the dust point is screened, the repeated detection point is determined directly by the matching degree between the expected position and the actual position, for example, the distance between the expected position and the actual position is less than a preset distance, and the detection point is determined as a repeated detection point.

[0057] Based on this, step S30 includes step S31 of determining the repeated detection point as a screen bad point.

[0058] The embodiment provides a detection method of a screen bad point. When the number of abnormal points of a first detection image is greater than that of a second detection image, a theoretical offset of the abnormal points is calculated based on a shooting angle, and then the actual position of the abnormal point in the first detection image is matched with a theoretical position in the second detection image derived based on the offset, that is, the actual offset of each abnormal point is compared with the theoretical offset. If the difference between the actual offset and the theoretical offset of a certain abnormal point is within a preset threshold, and the point has a corresponding position of the abnormal point in the second detection image, the point is determined as a repeated detection point. Otherwise, if the actual offset significantly deviates from the theoretical offset, the point is determined as a non-bad point that disappears or shifts due to the change of the angle. Finally, the repeated detection point that meets the offset matching condition is determined as a screen bad point. In this way, the non-bad points are further filtered by the geometric constraint of the shooting angle and the offset, and the identification accuracy of the real bad points is improved.

[0059] Based on the second embodiment of the application, in the third embodiment of the application, the same or similar contents as the above second embodiment can be referred to the above description, and will not be described in detail. On this basis, after step S50, the dust points are screened first in the process of determining the repeated detection points. The offset difference of each abnormal point in the first and second detection images needs to be calculated, including the offset of a large number of non-repeated points existing only in a single image. However, these non-repeated points are not bad points with a high probability, but consume additional calculation resources.

[0060] Therefore, in another optional embodiment, after step S50, in addition to screening the dust points and then determining the repeated points, the repeated points can also be determined according to the matching degree between the expected position and the actual position first, and then the dust points are determined based on the difference between the theoretical offset and the actual offset based on the repeated points, and finally the dust points in the repeated points are screened, so as to obtain the repeated detection points between the first detection image and the second detection image.

[0061] Optionally, the repeated detection points between the detection images can also be determined in the form of grid division. Therefore, the grid point position of the abnormal point in the virtual grid of the first detection image can be determined first, and then the repeated detection points between the first detection image and the second detection image are determined according to the grid point position and the adjustment value of the shooting angle.

[0062] Specifically, the first detection image can be divided into a virtual grid according to a preset size, such as 10*10 pixels for a grid unit, or in proportion to the physical size h of the screen, to ensure that the grid covers the entire screen area, while giving each grid a unique coordinate. Then traverse the abnormal points in the first detection image, calculate the grid unit it falls into through the pixel coordinate, and record the grid point position (i1, j1). Then, according to the adjustment value of the shooting angle, such as the rotation angle θ and the distance change Δd of the camera and the screen, the theoretical grid position (i2, j2) of the grid point (i1, j1) in the first detection image in the virtual grid of the second detection image is calculated by using the geometric transformation formula. Finally, traverse the abnormal points of the second detection image and determine their grid positions, and determine the abnormal points consistent with the theoretical grid position (i2, j2) as repeated detection points. Based on this, the structured positioning of the grid simplifies the matching calculation of the abnormal points in the cross-angle image, and improves the efficiency and accuracy of the determination of repeated detection points.

[0063] The embodiment locks the repeated points first, and then filters the dust points among them. At this time, the offset calculation is only for the candidate set that may be bad points, so as to accurately identify the difference between the dust in the "stable" state and the real screen bad points, reduce the false rejection of real bad points, and reduce the system calculation complexity. At the same time, the repeated detection points are screened based on the network point detection method, which improves the accuracy of repeated detection point screening.

[0064] Based on the first embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as the above first embodiment can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 3 , after step S20, the screen bad point detection method further includes steps S80-S100: Step S80, if the number of abnormal points of the first detection image is less than or equal to the number of abnormal points of the second detection image, determine the non-repeated points between the first detection image and the second detection image.

[0065] In the present embodiment, before shooting the second detection image, the screen to be detected completes the blowing process, and the blowing action introduces new dust covering onto the screen. At this time, the bad points covered by the dust are shown in the second image, and the blowing operation introduces new dust, generating new pseudo abnormal points. Therefore, when the number of abnormal points of the first detection image is small, the abnormal points that exist only in the second detection image and do not appear in the first detection image, i.e. non-repeated points, need to be extracted, so as to lock the newly added abnormal points in the second detection image, and determine which of the non-repeated points belong to the covered bad points and which belong to the dust points introduced by blowing.

[0066] Step S90, collect the third detection image of the screen to be detected.

[0067] In this embodiment, the shooting angle of the third detection image is the same as that of the first detection image. The third detection image is captured at the same shooting angle as the first detection image, so that the dust points among the non-repeated points are filtered out by the angle tilt manner. Therefore, the camera can be controlled to be turned back to the shooting angle of the first detection image by the mechanical arm, and then the third detection image is captured based on the same focal length, exposure time, etc. Alternatively, the screen to be detected is controlled to rotate, so that the angle between the camera and the screen to be detected is equivalent to the angle when the first detection image is shot. Before the third detection image is captured, the blowing operation is not performed, so as to avoid introducing new dust again.

[0068] In step S100, the corresponding target detection point of the non-repeated point in the third detection image is determined, and the target detection point and the repeated detection point between the first detection image and the second detection image are taken as the screen dead point.

[0069] In this embodiment, the target detection point is the point of the non-repeated point that repeatedly appears in the third detection image, which is identified as the screen dead point. The target detection point can be determined by using the same comparison manner, which is not described herein.

[0070] For the purpose of facilitating the understanding of the implementation process of the screen dead point detection method of this embodiment, please refer to Figure 2 , Figure 2 A brief flowchart of a screen dead point detection method is provided. Specifically, the acquisition device is an RMT test camera (wireless remote Bluetooth camera), the screen to be detected has lens foreign matter (small impurities attached to the lens or inside or surface of the screen protection layer) and Oled dead point (failed pixel point that cannot normally display color on the display screen), h is the height of the display screen, and the RMT test camera is shot from the vertical direction when the first detection image is shot. At this time, the lens foreign matter and the Oled dead point overlap in the vertical direction, and an abnormal point is presented in the image. Then, the angle of the RMT test camera is adjusted to 45°, or the position of the screen to be detected is adjusted so that the included angle and the RMT test camera are 45°. Then, the second detection image is shot from the inclined direction. At this time, the relative positions of the lens foreign matter and the Oled dead point change, and the two do not overlap. However, there are two abnormal points in the captured image. Then, the third detection image is captured. Finally, the images under different angles are compared to distinguish the actual Oled dead point and the lens foreign matter, so as to complete the detection of the screen dead point.

[0071] It should be noted that the above parameters are only used for explanation and do not limit the present application.

[0072] The embodiment provides a screen bad point detection method. When the number of abnormal points in the second detection image is large, non-repeated points are found from the two detection images, and a third detection image is collected by adjusting a shooting angle. Subsequently, secondary analysis and judgment are performed based on the third detection image, and screen bad points are found from the non-repeated points. Then, the target detection points and the repeated detection points between the first detection image and the second detection image are taken as the screen bad points, so that the screen bad points covered by dust are found after the blowing process, and the new dust point interference caused by the blowing process is filtered, and the detection accuracy is improved.

[0073] The application provides a detection device, comprising: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the screen bad point detection method in the first embodiment.

[0074] Reference is made below to Figure 5 which shows a structural schematic diagram of a detection device suitable for implementing the embodiments of the application. Figure 5 The detection device shown is merely an example, and should not impose any limitation on the functions and use range of the embodiments of the application.

[0075] As shown in Figure 5 , the detection device can comprise a processing apparatus 1001 (for example, a central processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage apparatus 1003 to a random access memory (RAM) 1004. In the random access memory 1004, various programs and data required for operation of the detection device are also stored. The processing apparatus 1001, the read-only memory 1002 and the random access memory 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the input / output interface 1006: an input apparatus 1007 comprising, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output apparatus 1008 comprising, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage apparatus 1003 comprising, for example, a magnetic tape, a hard disk, etc.; and a communication apparatus 1009. The communication apparatus 1009 can allow the detection device to perform wireless or wired communication with other devices to exchange data. Although the detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be alternatively implemented or provided.

[0076] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0077] The detection device provided by the present application adopts the screen dead point detection method in the above-mentioned embodiments, and can solve the technical problem of low accuracy of screen dead point detection. Compared with the prior art, the detection device provided by the present application has the same beneficial effects as the screen dead point detection method provided by the above-mentioned embodiments, and other technical features in the detection device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0078] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0079] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0080] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the screen dead point detection method in the above-mentioned embodiments.

[0081] The computer readable storage medium provided in the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, a radio frequency (RF), etc., or any suitable combination of the above.

[0082] The computer readable storage medium described above may be contained in the detection device, or may exist separately without being assembled into the detection device.

[0083] The computer readable storage medium described above carries one or more programs, which, when executed by the detection device, cause the detection device to: acquire a first detection image based on a to-be-detected screen, and determine a diameter size and a number of abnormal points of the first detection image; if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, adjust a shooting angle of the to-be-detected screen, and acquire a second detection image of the to-be-detected screen; if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determine a repeated detection point between the first detection image and the second detection image as a screen dead point.

[0084] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0085] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0086] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0087] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer programs) for executing the above-mentioned screen dead point detection method, and can solve the technical problem of low screen dead point detection accuracy. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the screen dead point detection method provided by the above-mentioned embodiments, which will not be described here.

[0088] The above merely describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or the like, which is made based on the technical concept of the present application and the content of the specification and drawings, is included in the patent protection scope of the present application.

Claims

1. A method for detecting a bad pixel of a screen, the method comprising: The method for detecting the screen bad points comprises: acquiring a first detection image collected based on a to-be-detected screen, and determining a diameter size and a number of abnormal points of the first detection image; if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, adjusting a shooting angle of the to-be-detected screen, and collecting a second detection image of the to-be-detected screen; if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determining a repeated detection point between the first detection image and the second detection image as a screen bad point.

2. The screen defect detection method as described in claim 1, characterized in that, After the step of determining the repeated detection point between the first detection image and the second detection image as a screen bad point, the method for detecting the screen bad points further comprises: if the number of abnormal points of the first detection image is greater than the number of abnormal points of the second detection image, determining a theoretical offset of the abnormal point according to the shooting angle; determining an expected position, an actual position and an actual offset of the abnormal point of the first detection image in the second detection image; determining a dust point according to a difference between the theoretical offset and the actual offset; screening out the dust point and determining the repeated detection point based on a matching degree between the expected position and the actual position.

3. The screen defect detection method as described in claim 2, characterized in that, After the step of determining the expected position, the actual position and the actual offset of the abnormal point of the first detection image in the second detection image, the method for detecting the screen bad points further comprises: determining a repeated point according to a matching degree between the expected position and the actual position, and determining a dust point according to a difference between the theoretical offset and the actual offset based on the repeated point; screening out the dust point in the repeated point to obtain the repeated detection point between the first detection image and the second detection image.

4. The screen defect detection method as described in claim 1, characterized in that, The step of adjusting the shooting angle of the to-be-detected screen and collecting the second detection image of the to-be-detected screen if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number comprises: if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, performing a dust blowing action based on the to-be-detected screen; adjusting a placement position of the to-be-detected screen or moving an image collection device based on a preset angle to collect the second detection image of the to-be-detected screen.

5. The method of claim 4, wherein the step of determining the number of defective pixels is performed by the steps of: determining the number of defective pixels in the screen by using a predetermined algorithm. After the step of adjusting the shooting angle of the to-be-detected screen and collecting the second detection image of the to-be-detected screen if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, the method for detecting the screen bad points further comprises: if the number of abnormal points of the first detection image is less than or equal to the number of abnormal points of the second detection image, determining a non-repeated point between the first detection image and the second detection image; collecting a third detection image of the to-be-detected screen, wherein a shooting angle of the third detection image is the same as a shooting angle of the first detection image; Determine a target detection point corresponding to the non-repeated point in the third detection image, and take the target detection point and repeated detection points between the first detection image and the second detection image as the screen defect point.

6. The method of claim 1, wherein the step of detecting the defective pixel comprises the steps of: determining a pixel value of the pixel; and determining whether the pixel value is less than a predetermined value. After the step of determining the diameter size and the number of the abnormal points of the first detection image based on the first detection image collected from the screen to be detected, the screen defect point detection method further comprises: If the diameter size is greater than a preset size and / or the number is greater than a preset number, determine the abnormal points of the first detection image as the screen defect point.

7. The method of claim 1, wherein the step of detecting the defective pixel comprises the steps of: determining a pixel value of the pixel; and determining whether the pixel value is less than a predetermined value. After the step of adjusting the shooting angle of the screen to be detected and collecting a second detection image of the screen to be detected if the diameter size is less than or equal to a preset size and the number is less than or equal to a preset number, the screen defect point detection method further comprises: Determine the grid point position of the abnormal point in the virtual grid of the first detection image; Determine the repeated detection points between the first detection image and the second detection image according to the grid point position and the adjustment value of the shooting angle.

8. The screen defect detection method as described in claim 1, characterized in that, After the step of determining the repeated detection points between the first detection image and the second detection image as the screen defect point if the number of the abnormal points of the first detection image is greater than the number of the abnormal points of the second detection image, the screen defect point detection method further comprises: Determine the non-repeated detection points between the first detection image and the second detection image as the dust point.

9. A detection device, characterized by The detection device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the screen defect point detection method according to any one of claims 1 to 8.

10. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the screen defect point detection method according to any one of claims 1 to 8.

Images