Screen defect detection method, device and equipment and computer readable storage medium

Abstract

The application discloses a screen defect detection method, device and equipment and a computer readable storage medium. The screen defect detection method comprises the following steps: acquiring a detection image of a target screen; performing edge contour searching on the detection image to obtain a first target contour line; extracting a target contour point group on the first target contour line; acquiring position information of a suspected glue overflow defect area according to a mean square deviation of curvatures of each target contour point group; performing scaling and edge contour searching on the detection image to obtain a second target contour line; acquiring an average gray scale of the suspected glue overflow defect area and an average gray scale of a neighborhood area, the neighborhood area being an area between the first target contour line and the second target contour line; calculating a ratio of the average gray scale of the suspected glue overflow defect area to the average gray scale of the neighborhood area as a gray scale contrast; and determining whether the target screen has a glue overflow defect according to the gray scale contrast and a first set value. The glue overflow defect is determined by the detection method, and the detection method has the advantage of high accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical element device testing, and more particularly, to a screen defect detection method and device, an equipment and a computer readable storage medium. BACKGROUND

[0002] The quality of a screen has a great influence on user experience. Especially, for virtual reality (VR) devices, augmented reality (AR) devices and other devices that mainly rely on screens to interact with users, the quality of the screen has a great influence on user experience.

[0003] Taking a virtual reality (VR) device as an example, in order to ensure that the VR product can be widely used and the user experience is good, it is required that the screen of the VR product must be able to achieve a high resolution and cannot have defects such as bad points and dirt. Therefore, many manufacturers will detect various defects such as screen edge detection before the screen is shipped. However, at the present stage, the detection of the screen in the production of the VR product relies on manual detection, such as overflow defect detection by the human eye, which not only has a great influence on the vision of the detection personnel, and the misjudgment and omission rate is high, but the efficiency is low. SUMMARY

[0004] The purpose of the present application is to provide a new technical solution of a screen defect detection method, device, equipment and computer readable storage medium, which can be used to accurately and quickly detect whether the screen of the VR device has an overflow defect.

[0005] In a first aspect, an embodiment of the present application provides a screen defect detection method. The screen defect detection method comprises:

[0006] obtaining a detection image of a target screen;

[0007] performing edge contour search on the detection image to obtain a first target contour line;

[0008] extracting a plurality of target contour point groups on the first target contour line;

[0009] obtaining position information of a suspected overflow defect region according to a mean square deviation of curvatures of the target contour point groups;

[0010] performing scaling and edge contour search on the detection image to obtain a second target contour line;

[0011] obtaining an average gray scale of the suspected overflow defect region and an average gray scale of a neighborhood region, the neighborhood region being a region between the first target contour line and the second target contour line;

[0012] calculate a ratio of the average gray scale of the suspected overflow defect region and the average gray scale of the neighborhood region as a gray scale contrast;

[0013] determine whether the target screen has an edge overflow defect according to the gray scale contrast and a first set value.

[0014] Optionally, the target contour point group includes at least three contour points, and adjacent two of the contour points have a target interval.

[0015] Optionally, the method for obtaining the position information of the suspected overflow defect region according to the mean square deviation of the curvatures of the target contour point groups includes:

[0016] obtain position information of each contour point in the target contour point group; wherein the target contour point group includes a first contour point, a second contour point and a third contour point;

[0017] obtain a distance dis1 between the first contour point and the second contour point, a distance dis2 between the first contour point and the third contour point, and a distance dis3 between the second contour point and the third contour point;

[0018] obtain the curvature of the target contour point group according to the first contour point, the second contour point and the third contour point;

[0019] calculate the mean square deviation of the curvatures of the target contour point groups;

[0020] in a case where the mean square deviation of the curvatures of the target contour point groups is greater than a second set value, determine that a position corresponding to the target contour point group is a suspected overflow defect region.

[0021] Optionally, the method for obtaining the average gray scale of the neighborhood region includes:

[0022] obtain the number of pixel points of non-zero gray scale and the gray scale value of the corresponding image of the neighborhood region;

[0023] calculate a ratio of the number of pixel points of non-zero gray scale and the gray scale value as the average gray scale of the neighborhood region.

[0024] Optionally, the method for obtaining the average gray scale of the suspected overflow defect region includes:

[0025] obtain a region formed by the target contour point group corresponding to the suspected overflow defect region; wherein the target contour point group includes a first contour point, a second contour point and a third contour point, and a region formed by the first contour point, the second contour point and the third contour point is a triangular region;

[0026] The average gray scale of any one of the gray scale mean value corresponding to the triangular region inside and the gray scale mean value corresponding to the rectangular region outside the triangular region is calculated as the average gray scale of the suspected overflow defect region.

[0027] Optionally, the screen defect detection method further comprises:

[0028] An area value of the suspected overflow defect region is obtained.

[0029] In a case where the absolute value of the gray scale contrast is less than the first set value and the area value of the suspected overflow defect region is greater than a third set value, it is determined that the target screen has an edge overflow defect.

[0030] Optionally, in a case where the absolute value of the gray scale contrast is less than the first set value, it is determined that the target screen has an edge overflow defect.

[0031] Optionally, the obtaining of the detection image of the target screen comprises:

[0032] An original image of the target screen is obtained.

[0033] Interference information in the original image is removed to obtain the detection image of the target screen.

[0034] In a second aspect, an embodiment of the present application provides a screen defect detection device, which is characterized in application to the screen defect detection method of the first aspect, and the screen defect detection device comprises:

[0035] A first obtaining module is configured to obtain a detection image of a target screen.

[0036] A second obtaining module is configured to perform edge contour searching on the detection image to obtain a first target contour line.

[0037] An extracting module is configured to extract a plurality of target contour point groups on the first target contour line.

[0038] A third obtaining module is configured to obtain position information of a suspected overflow defect region according to a mean square deviation of curvatures of the target contour point groups.

[0039] A fourth obtaining module is configured to perform scaling and edge contour searching on the detection image to obtain a second target contour line.

[0040] A fifth obtaining module is configured to obtain an average gray scale of the suspected overflow defect region and an average gray scale of a neighborhood region, wherein the neighborhood region is a region between the first target contour line and the second target contour line.

[0041] a calculating module configured to calculate a ratio of an average gray scale of the suspected overflow defect region to an average gray scale of the neighborhood region as a gray scale contrast;

[0042] a determining module configured to determine whether the target screen has an edge overflow defect according to the gray scale contrast and a first set value.

[0043] Optionally, the screen defect detection apparatus further comprises:

[0044] a sixth obtaining module configured to obtain an area value of the suspected overflow defect region;

[0045] The determining module is configured to determine that the target screen has an edge overflow defect when an absolute value of the gray scale contrast is less than the first set value and the area value of the suspected overflow defect region is greater than a third set value.

[0046] In a third aspect, an embodiment of the present application provides a screen defect detection device. The screen defect detection device comprises a memory, a processor and a screen defect detection program stored in the memory and executable on the processor; and when the screen defect detection program is executed by the processor, the steps of the screen defect detection method according to the first aspect are implemented.

[0047] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium. The computer readable storage medium stores a screen defect detection program, and when the screen defect detection program is executed by a processor, the steps of the screen defect detection method according to the first aspect are implemented.

[0048] The present application has the following beneficial effects:

[0049] The present application provides a screen defect detection method, which can be used to detect screen edge overflow defects, obtain position information of a suspected overflow defect region through a mean square error of curvature of an edge contour, and then further determine whether a screen to be detected has an overflow defect through a gray scale contrast. The screen defect detection method provided by the present application can not only improve accuracy, but also greatly reduce labor intensity of detection personnel and improve production line detection efficiency.

[0050] Other characteristics and advantages of the present application will become apparent from the following detailed description of exemplary embodiments thereof, with reference made to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0051] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments of the present application and, together with the description, serve to explain the principles of the application.

[0052] Figure 1A schematic flowchart illustrating the screen defect detection method provided in this application embodiment;

[0053] Figure 2 This is the original image of the target screen in the embodiments of this application;

[0054] Figure 3 The binary image is obtained by binarizing the original image of the target screen in this embodiment of the application.

[0055] Figure 4 This is a drawn outline image of the target screen in the embodiments of this application;

[0056] Figure 5 A curvature histogram of multiple groups of target contour points provided in an embodiment of this application;

[0057] Figure 6 According to Figure 5 A schematic diagram of the mean square error of the calculated curvature;

[0058] Figure 7 This is a scaled-down image of the detection image of the target screen in this embodiment of the application;

[0059] Figure 8 The image of the neighborhood region between the first target contour line and the second target contour line;

[0060] Figure 9 This is a functional block diagram of the screen defect detection device provided in the embodiments of this application.

[0061] Explanation of reference numerals in the attached figures:

[0062] 10. Screen defect detection device; 11. First acquisition module; 12. Second acquisition module; 13. Third acquisition module; 14. Fourth acquisition module; 15. Fifth acquisition module; 16. Calculation module; 17. Determination module; 18. Extraction module; 20. First target contour line. Detailed Implementation

[0063] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0064] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.

[0065] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0066] In all of the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments can have different values.

[0067] It should be noted that like reference numerals and letters refer to like items throughout the attached drawings, and therefore once an item is defined in one drawing, it is not necessary to discuss it further in subsequent drawings.

[0068] The screen defect detection method, device, equipment and computer readable storage medium provided by the embodiments of the present application are described in detail below in conjunction with the drawings.

[0069] In the existing related art, taking a VR device as an example, for an assembled VR all-in-one machine, a quality inspector checks whether it has defects by using the human eye to check through a lens. One common way is to use different color cards to light up the screen of the VR, and then the human eye checks whether there are defects under different cards through the lens. Common defects include green screen dark spots, green screen bright spots, red screen bright spots, red screen dark spots, black screen bright spots, white screen dark spots, scratches, edge overflow glue, and transparency defects, etc. However, at the present stage, for the edge overflow glue defect of the screen, due to the small area of the defect and the problem of adhesion with the background, accurate identification and detection cannot be performed at present.

[0070] The embodiments of the present application provide a fast and accurate identification and detection method for the edge overflow glue defect of the VR screen. The method uses the mean square deviation of the curvature of the edge contour point for coarse positioning, and then uses the set gray scale contrast for accurate positioning after coarse positioning. The method combines coarse positioning and accurate positioning to accurately identify the edge overflow glue defect of the screen.

[0071] According to one embodiment of the present application, a screen defect detection method is provided, as shown in Figure 1 The screen defect detection method may, for example, include the following steps S1-S8.

[0072] Step S1, acquire a detection image of a target screen.

[0073] In the above step S1, the target screen is a screen to be measured.

[0074] In the embodiments provided by the present application, the target screen is, for example, the screen of a VR product. The technical solutions provided by the embodiments of the present application can be used to accurately and quickly identify and detect the edge overflow glue defect of the screen of the VR product.

[0075] Of course, the target screen includes but is not limited to the screen of the VR product described above, and can also be the screen of other terminal devices. In this application, only the screen of the VR product is taken as an example for description.

[0076] The screen defect detection method provided in the embodiments of this application is also applicable to the edge overflow defect identification detection of the screen of other terminal devices, and the applicable scenarios of the screen in the embodiments of this application are not limited.

[0077] In the process of acquiring the detection image of the target screen, for example, an image acquisition device such as a camera can be used to capture the target screen to acquire the image of the target screen.

[0078] It should be noted that the original image of the target screen can be acquired by using a camera. See Figure 2 ; and then the effective area of the original image is extracted, which aims to exclude interference information, and the final acquired image is the detection image of the target screen. The detection image of the target screen can be used for subsequent identification and detection. The reason why the original image of the target screen is not directly used in the technical solution of this application is that the interference information existing in the original image will affect the accuracy of the subsequent detection result.

[0079] After the above step S1 is completed, step S2 can be entered:

[0080] In step S2, the edge contour of the detection image is searched to acquire the first target contour line 20. See Figure 4 .

[0081] Since the screen defect detection method provided in the embodiments of this application is used to detect the edge overflow defect of the screen, the edge contour of the target screen (i.e., the screen to be detected) is needed, that is, the first target contour line mentioned in step S2, so as to detect the contour.

[0082] Optionally, after the original image of the target screen is acquired, a global threshold function can be used to perform binaryzation processing on the original image to acquire a binary image. See Figure 3 .

[0083] After the binary image of the original image of the target screen is acquired, the edge contour of the target screen is found, that is, the first target contour line 20 is acquired, for example, by using a contour search method. See the white line shown in Figure 4 .

[0084] After the above step S2 is completed, step S3 can be entered:

[0085] In step S3, a plurality of target contour point groups on the first target contour line 20 are extracted.

[0086] Due to the unique nature of adhesive overflow defects in screens, these defects are concentrated in the edge areas of the screen. Therefore, when judging these defects, it is necessary to extract the contour points on the edge contour.

[0087] It should be noted that the first target contour line 20 may contain a number of consecutive contour points, and each contour point has its own coordinates (x, y).

[0088] In one example, the target contour point group may include at least three contour points, with a target interval between any two adjacent contour points.

[0089] In a preferred embodiment of this application, three consecutive contour points can be grouped into a target contour point group. The three contour points can form a circle, that is, form a reference shape.

[0090] Of course, each target contour point group can also include more than three contour points, which can be flexibly adjusted according to actual needs. This application embodiment does not impose any restrictions on this. The more contour points each target contour point includes, the higher the accuracy of the test results, but it may also lead to a large amount of computation and affect efficiency. Overall, a design in which each target contour point group includes three contour points is more preferred.

[0091] Furthermore, the selection method for three consecutive contour points is as follows: for example, there can be a one-pixel interval between two adjacent contour points. Optionally, in the embodiments of this application, the selected step size is 3, 5, or 10. The step size can be set according to the actual image size, and this application does not impose any restrictions on it.

[0092] After completing step S3 above, you can proceed to step S4:

[0093] Step S4: Obtain the location information of the suspected glue overflow defect area based on the mean square error of the curvature of each target contour point group.

[0094] In step S3 above, several target contour point groups can be extracted on the first target contour line 20. Since each target contour point group is designed to include three or more contour points, these contour points can form an arc, and the corresponding target contour point group has a certain curvature.

[0095] In step S4, the curvature of the arc formed by multiple consecutive contour points in the target contour point group is calculated, and the mean square error of the curvature corresponding to each target contour point group on the first target contour line 20 is then calculated. Subsequently, by comparing the mean square error of the curvature of each target contour point group with a set value (the second set value described below), it is possible to preliminarily determine whether there is a suspected adhesive overflow defect at the edge of the target screen and the location information of the suspected adhesive overflow defect area. In other words, step S4 can preliminarily locate the suspected adhesive overflow defect area of ​​the target screen.

[0096] After completing step S4 above, you can proceed to step S5:

[0097] Step S5: Scale and perform edge contour search on the detected image to obtain the second target contour line.

[0098] In one example, the detected image of the target screen is scaled, for example, by a scaling factor of 1.01. The edge contour of the scaled image is then obtained, which is the second target contour line mentioned above. See [link to relevant documentation]. Figure 7 This is equivalent to scaling the first target outline 20 inward.

[0099] After step S5, a region is formed between the first target contour line 20 and the second target contour line. This region is referred to as the neighborhood region in the following steps. See [link to relevant documentation]. Figure 8 .

[0100] After completing step S5 above, you can proceed to steps S6 and S7:

[0101] Step S6: Obtain the average gray level of the suspected adhesive overflow defect area and the average gray level of the neighboring area. The neighboring area is the region between the first target contour line 20 and the second target contour line. See [link to relevant documentation]. Figure 8 ;as well as,

[0102] Step S7: Calculate the ratio of the average gray level of the suspected glue overflow defect area to the average gray level of the neighboring area as the gray level contrast.

[0103] In one example, when the target contour point group corresponding to the suspected glue overflow defect area includes three contour points, the area formed by the three contour points is, for example, a triangular area.

[0104] Understandably, in this application, the suspected glue overflow defect area (or suspected glue overflow defect point) can be obtained by calculating the mean square error of the curvature of the target contour point. In order to more accurately determine whether the suspected glue overflow defect area actually has an edge glue overflow defect, it is also necessary to calculate the gray level gray_min of the suspected glue overflow defect area and calculate the gray level of the neighboring area for comparison. This is to ensure the robustness of the detection results.

[0105] Specifically, after steps S6 and S7, the average gray level gray_all of the pixels in the image corresponding to the neighborhood region between the two contour lines (the first target contour line and the second target contour line) can be obtained. Then, the mean gray level gray_mean_var corresponding to the triangular region formed by the three contour points in the target contour point group is calculated; and then the gray level contrast contrast is calculated.

[0106] After completing step S7 above, you can proceed to step S8:

[0107] Step S8: Determine whether the target screen has edge adhesive overflow defects based on the grayscale contrast and the first set value.

[0108] In one example, after obtaining the grayscale contrast in step S7, if the absolute value of the grayscale contrast is less than a first preset value, it is determined that the suspected adhesive overflow defect area has an edge adhesive overflow defect. Otherwise, it is considered a non-adhesive overflow defect. This method of determining edge adhesive overflow defects in the screen is not only highly accurate but also significantly reduces the workload of inspection personnel and improves production line inspection efficiency.

[0109] This application provides a screen defect detection method that can be used to detect glue overflow defects at the edge of the screen. The method obtains the location information of the suspected glue overflow defect area by using the mean square error of the curvature of the edge contour, and then uses grayscale contrast to further determine whether there is a glue overflow defect in the screen under test. The screen defect detection method provided by this application not only has high accuracy, but also greatly reduces the labor intensity of the inspection personnel and improves the inspection efficiency of the production line.

[0110] In some examples of this application, the method for obtaining the location information of suspected adhesive overflow defect areas based on the mean square error of the curvature of each target contour point group includes the following steps 01 to 05:

[0111] Step 01: Obtain the position information of each contour point in the target contour point group; wherein, the target contour point group includes a first contour point, a second contour point, and a third contour point;

[0112] Step 02: Obtain the distance dis1 between the first contour point and the second contour point, the distance dis2 between the first contour point and the third contour point, and the distance dis3 between the second contour point and the third contour point;

[0113] Step 03: Obtain the curvature of the target contour point group based on the first contour point, the second contour point, and the third contour point;

[0114] Step 04: Calculate the root mean square error of the curvature of each target contour point group;

[0115] Step 05: If the root mean square error of the curvature of the target contour point group is greater than the second set value, determine that the position corresponding to the target contour point group is a suspected glue overflow defect area.

[0116] In the above example of this application, the target contour point group includes, for example, the three consecutive contour points mentioned above, namely the first contour point, the second contour point, and the third contour point. The curvature corresponding to these three contour points can be calculated using the following formula:

[0117] curvature j =1 / radius j Where j = 1, 2, 3, ..., n;

[0118] Then, the mean squared variance of the curvature is calculated. j When the mean squared variance of the curvature of a certain target contour point set j If the value is greater than the second set value (a certain threshold), then there is a suspected glue overflow defect at the position corresponding to the target contour point group.

[0119] Specifically, the position (i.e., coordinate position) of the first contour point is:

[0120] Point i-1 .x=InnerProfile_src[i-3].x;

[0121] Point i-1 .y=InnerProfile_src[i-3].y.

[0122] The position (i.e., coordinate position) of the second contour point is:

[0123] Point i .x = InnerProfile_src[i].x;

[0124] Point i .y = InnerProfile_src[i].y.

[0125] The position (i.e., coordinate position) of the third contour point is:

[0126] Point i+1 .x=InnerProfile_src[i+3].x;

[0127] Point i+1 .y=InnerProfile_src[i+3].y.

[0128] Calculate the distance dis1 between the first contour point and the second contour point, where dis1 = sqrt

[0129] (Point i-1 .x-Point i .x)*(Point i-1 .y-Point i .y);

[0130] Calculate the distance dis2 between the first contour point and the third contour point, where dis2 = sqrt

[0131] (Point i-1 .x-Point i+1 .x)*(Point i-1 .y-Point i+1 .y);

[0132] Calculate the distance dis3 between the second and third contour points, where dis3 = sqrt

[0133] (Point i .x-Point i+1 .x)*(Point i .y-Point i+1 .y).

[0134] Calculate the angles between the edges of the first contour point and the second contour point using the law of cosines:

[0135] cosA=(dis2*dis2+dis3*dis3-dis1*dis1) / 2*dis2*dis3;

[0136] sinA = sqrt(1 - cosA * cosA);

[0137] radius j =dis1 / (2*sinA).

[0138] Then obtain curvature j =1 / radius jWhere j = 1, 2, 3, ..., n.

[0139] The mean squared variance of curvature is calculated using the following formula. j :

[0140]

[0141] When the mean squared variance of the curvature of a certain target contour point set j If the value is greater than the second set value (a certain threshold), then there is a suspected glue overflow defect at the position corresponding to the target contour point group.

[0142] Based on the example above in this application, see Figure 5 4159 target contour point groups were extracted from the first target contour line 20. Figure 5 The shown histogram of curvature values ​​indicates that different groups of target contour points have different curvatures.

[0143] See Figure 6 ,according to Figure 5 The curvature of all target contour point groups shown. Figure 6 The mean square error of the curvature of each target contour point group is shown. From Figure 6 It can be seen that the root mean square error of some target contour point groups is relatively large, for example, exceeding 0.02. The root mean square error of the curvature of some target contour point groups is even larger. These target contour points correspond to suspected glue overflow defect areas.

[0144] It should be noted that the second setting value in the above example of this application can be set as needed, and its specific value is not limited in the embodiments of this application.

[0145] In some examples of this application, the method for obtaining the average gray level of the neighborhood region includes:

[0146] Obtain the number of non-zero grayscale pixels (pixel_num) and grayscale value (gray_all) of the image corresponding to the neighborhood region;

[0147] The ratio of the number of non-zero grayscale pixels (pixel_num) to the grayscale value (gray_all) is calculated as the average grayscale value (gray_mean) of the neighborhood region, i.e., gray_mean = gray_all / pixel_num.

[0148] The neighboring region can be seen in the following: Figure 8 The area shown.

[0149] In some examples of this application, the method for obtaining the average gray level of the suspected adhesive overflow defect area includes:

[0150] Obtain the region formed by the target contour point group corresponding to the suspected glue overflow defect area; wherein, the target contour point group includes a first contour point, a second contour point and a third contour point, and the region formed by the first contour point, the second contour point and the third contour point is a triangular region.

[0151] The average gray level of the suspected glue overflow defect area is calculated by taking either the mean gray level inside the triangular region or the mean gray level inside the bounding rectangle of the triangular region.

[0152] To obtain the average grayscale value of a suspected glue overflow defect area, it is necessary to find the region formed by the corresponding target contour points. When this region is triangular, the average grayscale value inside the triangular region can be calculated and directly used as the average grayscale value of the suspected glue overflow defect area. Alternatively, the average grayscale value inside the bounding rectangle of the triangular region can also be calculated and used as the grayscale value of the suspected glue overflow defect area.

[0153] In some examples of this application, the screen defect detection method further includes the following steps:

[0154] Obtain the area value (area) of the suspected glue overflow defect region;

[0155] If the absolute value of the grayscale contrast is less than the first set value, and the area value of the suspected adhesive overflow defect region is greater than the third set value, it is determined that the target screen has an edge adhesive overflow defect.

[0156] In other words, in the step of further accurately determining whether there is adhesive overflow defect at the edge of the screen, an evaluation parameter has been added, namely the area value of the suspected adhesive overflow defect area.

[0157] Based on this, when the absolute value of the calculated grayscale contrast is less than the first preset value, and the area of ​​the suspected glue overflow defect area (triangular area) is greater than the third preset value, it can be determined very accurately that the target screen has an edge glue overflow defect.

[0158] This method is highly accurate in determining edge adhesive defects on screens, and it can greatly reduce the workload of inspection personnel and improve production line inspection efficiency.

[0159] In some examples of this application, when the absolute value of the grayscale contrast is less than the first set value, it is determined that the target screen has an edge adhesive overflow defect.

[0160] It should be noted that when using only grayscale contrast as an evaluation parameter for whether the target screen has edge glue overflow defects, as described in the example above, if the absolute value of the grayscale contrast is less than the first set value, the target screen is determined to have edge glue overflow defects. Conversely, if the absolute value is greater than the set value, the target screen is not considered to have edge glue overflow defects. This evaluation method is relatively simple and has good accuracy.

[0161] In some examples of this application, acquiring the detected image of the target screen includes:

[0162] Obtain the original image of the target screen;

[0163] The interference information in the original image is removed to obtain the detection image of the target screen.

[0164] According to another aspect of the embodiments of this application, a screen defect detection device is also proposed, which is applied to the screen defect detection method described above.

[0165] See Figure 9 The screen defect detection device 10 includes:

[0166] The first acquisition module 11 is used to acquire the detection image of the target screen;

[0167] The second acquisition module 12 performs edge contour search on the detected image to obtain the first target contour line 20;

[0168] Extraction module 18 is used to extract a plurality of target contour point groups on the first target contour line 20;

[0169] The third acquisition module 13 acquires the location information of the suspected glue overflow defect area based on the mean square error of the curvature of the target contour point group.

[0170] The fourth acquisition module 14 scales and searches the edge contours of the detected image to obtain the second target contour line;

[0171] The fifth acquisition module 15 is used to acquire the average gray level of the target region formed by the target contour point group and the average gray level of the neighboring region; wherein, the neighboring region is the region between the first target contour line 20 and the second target contour line;

[0172] Calculation module 16 is used to calculate the ratio of the average gray level of the target region to the average gray level of the neighboring regions as the gray level contrast; and

[0173] The determination module 17 is used to determine whether the target screen has an adhesive overflow defect based on the grayscale contrast and the first set value.

[0174] Optionally, the screen defect detection device further includes a sixth acquisition module, which is used to acquire the area value of the suspected glue overflow defect area; based on this, the determination module 17 is used to determine the glue overflow defect at the edge of the target screen when the absolute value of the grayscale contrast is less than the first set value and the area value of the suspected glue overflow defect area is greater than the third set value.

[0175] This application provides a screen defect detection device that can be used to detect glue overflow defects at the edge of a screen. The location information of the suspected glue overflow defect area is obtained by using the mean square error of the curvature of the edge contour. Then, the grayscale contrast is used to further determine whether there is a glue overflow defect in the screen under test. The screen defect detection device provided in this application not only has high accuracy in determining glue overflow defects, but also greatly reduces the labor intensity of inspection personnel and improves the inspection efficiency of the production line.

[0176] The specific implementation of the screen defect detection device in this application can refer to the embodiments of the screen defect detection method described above. Therefore, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, and will not be described in detail here.

[0177] According to another aspect of the embodiments of this application, a screen defect detection device is proposed, the screen defect detection device comprising: a memory, a processor, and a screen defect detection program stored in the memory and executable on the processor; wherein, when the screen defect detection program is executed by the processor, it implements the steps of the screen defect detection method as described above.

[0178] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a screen defect detection program, which, when executed by a processor, implements the steps of the screen defect detection method described above.

[0179] The above embodiments mainly describe the differences between the various embodiments. As long as the different optimization features between the various embodiments are not contradictory, they can be combined to form a better embodiment. For the sake of brevity, they will not be elaborated here.

[0180] While specific embodiments of this application have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this application. The scope of this application is defined by the appended claims.

Claims

1. A method for detecting screen defects, characterized in that, include: Acquire the detection image of the target screen; The detected image is subjected to edge contour search to obtain the first target contour line; Extract several target contour point groups from the first target contour line; Based on the mean square error of the curvature of each target contour point group, the location information of the suspected glue overflow defect area is obtained; The detected image is scaled and its edge contour is searched to obtain the second target contour line; The average gray level of the suspected glue overflow defect area and the average gray level of the neighboring area are obtained, wherein the neighboring area is the area between the first target contour line and the second target contour line; The ratio of the average gray level of the suspected glue overflow defect area to the average gray level of the neighboring area is calculated as the gray level contrast. Based on the grayscale contrast and the first set value, it is determined whether the target screen has edge adhesive overflow defects.

2. The screen defect detection method according to claim 1, characterized in that, The target contour point group includes at least three contour points, and there is a target interval between two adjacent contour points.

3. The screen defect detection method according to claim 1, characterized in that, The method for obtaining the location information of suspected adhesive overflow defect areas based on the mean square error of the curvature of each of the target contour point groups includes: Obtain the position information of each contour point in the target contour point group; wherein, the target contour point group includes a first contour point, a second contour point, and a third contour point; Obtain the distance dis1 between the first contour point and the second contour point, the distance dis2 between the first contour point and the third contour point, and the distance dis3 between the second contour point and the third contour point; The curvature of the target contour point group is obtained based on the first contour point, the second contour point, and the third contour point. Calculate the root mean square error of the curvature of each target contour point group; If the root mean square error of the curvature of the target contour point group is greater than a second set value, the position corresponding to the target contour point group is determined to be a suspected glue overflow defect area.

4. The screen defect detection method according to claim 1, characterized in that, The method for obtaining the average gray level of the neighborhood region includes: Obtain the number of non-zero grayscale pixels and their grayscale values ​​in the image corresponding to the neighborhood region; The ratio of the number of pixels with non-zero gray levels to the gray level value is used as the average gray level of the neighborhood region.

5. The screen defect detection method according to claim 1, characterized in that, The method for obtaining the average gray level of the suspected glue overflow defect area includes: Obtain the region formed by the target contour point group corresponding to the suspected glue overflow defect area; wherein, the target contour point group includes a first contour point, a second contour point and a third contour point, and the region formed by the first contour point, the second contour point and the third contour point is a triangular region. The average gray level of the suspected glue overflow defect area is calculated by taking either the mean gray level inside the triangular region or the mean gray level inside the bounding rectangle of the triangular region.

6. The screen defect detection method according to any one of claims 1-5, characterized in that, The screen defect detection method further includes: Obtain the area value of the suspected glue overflow defect region; If the absolute value of the grayscale contrast is less than the first set value, and the area value of the suspected adhesive overflow defect region is greater than the third set value, it is determined that the target screen has an edge adhesive overflow defect.

7. The screen defect detection method according to any one of claims 1-5, characterized in that, If the absolute value of the grayscale contrast is less than the first set value, it is determined that the target screen has an edge adhesive overflow defect.

8. The screen defect detection method according to claim 1, characterized in that, The acquisition of the detection image of the target screen includes: Obtain the original image of the target screen; The interference information in the original image is removed to obtain the detection image of the target screen.

9. A screen defect detection device, characterized in that, The screen defect detection device, applied to the screen defect detection method as described in any one of claims 1-8, comprises: The first acquisition module is used to acquire the detection image of the target screen; The second acquisition module performs edge contour search on the detected image to obtain the first target contour line; The extraction module is used to extract a group of target contour points on the first target contour line; The third acquisition module is used to acquire the location information of the suspected glue overflow defect area based on the mean square error of the curvature of each target contour point group. The fourth acquisition module scales and searches the edge contours of the detected image to obtain the second target contour line; The fifth acquisition module is used to acquire the average gray level of the suspected glue overflow defect area and the average gray level of the neighboring area; wherein, the neighboring area is the area between the first target contour line and the second target contour line; The calculation module is used to calculate the ratio of the average gray level of the suspected glue overflow defect area to the average gray level of the neighboring area as the gray level contrast. The determination module is used to determine whether the target screen has edge adhesive overflow defects based on the grayscale contrast and the first set value.

10. The screen defect detection device according to claim 9, characterized in that, The screen defect detection device also includes: The sixth acquisition module is used to acquire the area value of the suspected glue overflow defect area; The determining module is used to determine the adhesive overflow defect at the edge of the target screen when the absolute value of the grayscale contrast is less than the first set value and the area value of the suspected adhesive overflow defect area is greater than the third set value.

11. A screen defect detection device, characterized in that, The screen defect detection device includes: a memory, a processor, and a screen defect detection program stored in the memory and executable on the processor; wherein, when the screen defect detection program is executed by the processor, it implements the steps of the screen defect detection method as described in any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a screen defect detection program, which, when executed by a processor, implements the steps of the screen defect detection method as described in any one of claims 1 to 8.

Images