Flexible screen fracture line detection method and device, computer equipment and medium

Abstract

Embodiments of the present application disclose a flexible screen fracture line detection method and device, computer equipment and a medium. The method comprises: acquiring a bending area image of a flexible screen collected by an image collector, and converting the bending area image into a binary image; detecting an edge reflection area in the binary image, and determining a region of interest for fracture line detection according to the edge reflection area; and performing fracture line identification on the region of interest to obtain a fracture line detection result. The detection method can accurately and efficiently extract the region of interest for fracture line detection, and thus can accurately and efficiently detect the fracture line of the bending area of the flexible screen, effectively reducing the processing time for identifying defects of the flexible screen and effectively improving the identification rate of defects of the flexible screen.

Description

Technical Field

[0001] This application relates to the field of display technology. More specifically, it relates to a method and apparatus for detecting fracture lines in flexible screens, as well as a computer device and medium. Background Technology

[0002] In the manufacturing process of OLED display panels with flexible screens such as curved screens and foldable screens, tiny cracks may appear when the display layer is bonded to a cover plate such as a curved glass cover or a flexible cover plate. This is called a crack in the display layer, which can cause water and oxygen to enter, damage the display layer, and ultimately render the display panel unusable.

[0003] For fracture line detection in flexible screens, manual inspection methods are costly, inefficient, and often result in missed or over-detected fracture lines due to their difficulty in visual inspection of many minute fracture lines. Currently, several automated detection methods exist, primarily divided into two types: artificial intelligence analysis, which offers high accuracy and wide applicability, but its accuracy relies on learning from a large number of image samples; and machine vision, which typically suffers from slow image processing speeds, and its accuracy and efficiency are heavily influenced by the extraction results of the Region of Interest (ROI) for fracture line detection. This leads to problems such as long inspection times for single images and high rates of missed and over-detected fractures, making it difficult to meet the cycle time and inspection requirements of large-scale production testing scenarios. Summary of the Invention

[0004] The purpose of this application is to provide a method and apparatus, computer equipment and medium for detecting fracture lines in flexible screens, so as to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] The first aspect of this application provides a method for detecting fracture lines in a flexible screen, including:

[0007] The image of the bending area of ​​the flexible screen is acquired by the image acquisition device, and the bending area image is converted into a binarized image;

[0008] The edge reflection regions in the binarized image are detected, and the region of interest for the break line detection is determined based on the edge reflection regions.

[0009] Break lines are identified in the region of interest to obtain break line detection results.

[0010] The inventors discovered that when acquiring images of the bending area of ​​a flexible screen using an image acquisition device, the images of the bending area contain highly reflective edge reflective regions or edge reflective bands. Therefore, the fracture line detection method for flexible screens provided in the first aspect of this application uses edge reflective regions with obvious grayscale characteristics in the binarized image as a basis to accurately and efficiently extract the region of interest for fracture line detection. This enables accurate and efficient detection of fracture lines in the bending area of ​​flexible screens, effectively reducing the processing time for identifying flexible screen defects and significantly improving the defect recognition rate.

[0011] In one possible implementation, determining the region of interest for break line detection based on the edge reflective area includes: selecting a region within a set pixel width range at a set pixel distance on a set side of the edge reflective area as the region of interest for break line detection.

[0012] Given that the image acquisition parameters, shooting angle, shooting distance, and bending angle of the bending area to be detected are determined, the size of the region of interest for fracture line detection and its positional relationship with the edge reflective area are also determined. Based on this, this implementation method ensures the accuracy and efficiency of extracting the region of interest for fracture line detection.

[0013] In one possible implementation, the height of the region of interest for the broken line detection is selected to be the same as the height of the edge reflective region.

[0014] This implementation method can further improve the efficiency of identifying fracture lines in the bending area of ​​flexible screens.

[0015] In one possible implementation, the step of identifying the break line in the region of interest includes: identifying the break line in the region of interest based on grayscale features; if a break line is identified, a judgment is made: based on the fact that the angle deviation between the break line and the bending axis of the bending area is less than a set angle threshold, the detection result is determined to be a defective break line.

[0016] The break line in the bending area is usually roughly parallel to the bending axis of the bending area. Based on this, this implementation can further determine whether the identified break line is indeed a defective break line in the display layer or a false defect caused by factors such as stains or defects in the curved glass cover of a curved screen or the flexible cover of a foldable screen by judging whether the angular deviation between the identified break line and the bending axis is less than a set angle threshold. This further improves the accuracy of identifying the break line in the bending area of ​​the flexible screen.

[0017] In one possible implementation, before making a judgment if a break line is identified, the method further includes: merging the break lines identified in the region of interest based on the Hough transform.

[0018] Break lines are typically long, and the grayscale features at the less severe locations of the break are not obvious, potentially leading to incorrect identification. Therefore, this implementation avoids the situation where a single break line is identified as multiple discontinuous break lines.

[0019] In one possible implementation, after determining the region of interest for break line detection based on the edge reflective area and before performing break line identification on the region of interest, the method further includes: performing image enhancement on the region of interest.

[0020] In one possible implementation, the image enhancement includes at least one of gamma transformation, noise point removal, and edge sharpening.

[0021] This implementation method can further improve the accuracy of identifying the break lines in the bending area of ​​flexible screens.

[0022] In one possible implementation, acquiring the bending area image of the flexible screen acquired by the image acquisition device includes: acquiring multiple bending area images of the flexible screen acquired by multiple image acquisition devices with different acquisition angles.

[0023] This implementation method improves the accuracy of identifying fracture lines in the bending area of ​​flexible screens by performing fracture line identification on images of the bending area acquired from multiple angles, and avoids missed detections due to factors such as the narrow acquisition range of the image acquisition device.

[0024] A second aspect of this application provides a fracture line detection device for a flexible screen, comprising:

[0025] The preprocessing module is configured to acquire the bending area image of the flexible screen acquired by the image acquisition device, and convert the bending area image into a binarized image;

[0026] The region of interest (ROI) determination module is configured to detect edge reflection regions in the binarized image and determine the ROI for breakline detection based on the edge reflection regions; and

[0027] The identification module is configured to identify break lines in the region of interest and obtain break line detection results.

[0028] In one possible implementation, the region of interest determination module is configured to determine the region of interest for break line detection based on the edge reflective region by selecting a region within a preset pixel width range at a preset pixel distance on a preset side of the edge reflective region as the region of interest for break line detection.

[0029] In one possible implementation, the identification module is configured to identify break lines in the region of interest and obtain break line detection results by: identifying break lines in the region of interest based on grayscale features and determining that: if a break line exists and the angular deviation between the break line and the bending axis of the bending area is less than a preset angle threshold, then the detection result is determined to be a defective break line.

[0030] In one possible implementation, the device further includes the image acquisition unit for acquiring images of the bending area of ​​the flexible screen.

[0031] In one possible implementation, the image acquisition device includes multiple image acquisition devices with different acquisition angles.

[0032] In one possible implementation, the image acquisition device includes a CCD camera and a point light source.

[0033] This implementation method, by setting up multiple sets of image acquisition devices, including CCD cameras and point light sources respectively, can acquire images of the bending area from multiple angles without interference between the point light sources, thereby further improving the accuracy of identifying the fracture line of the bending area of ​​the flexible screen.

[0034] A third aspect of this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method provided in the first aspect of this application.

[0035] The fourth aspect of this application provides a computer non-transient readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of this application. Attached Figure Description

[0036] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0037] Figure 1 This document illustrates a flowchart of a method for detecting fracture lines in a flexible screen according to an embodiment of this application. Figure 1 .

[0038] Figure 2 A schematic diagram showing the positional relationship between the three image acquisition devices and the curved screen is shown.

[0039] Figure 3 This diagram illustrates the binarized image and the extracted region of interest to be identified.

[0040] Figure 4 This document illustrates a flowchart of a method for detecting fracture lines in a flexible screen according to an embodiment of this application. Figure 2 .

[0041] Figure 5 This is a schematic diagram of the structure of the fracture line detection device for flexible screen provided in an embodiment of this application.

[0042] Figure 6 A schematic diagram of the structure of a computer system that implements the detection apparatus provided in the embodiments of this application is shown. Detailed Implementation

[0043] To more clearly illustrate this application, the following description, in conjunction with embodiments and accompanying drawings, further clarifies the application. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of this application.

[0044] The inventors discovered that when capturing images of the bent area of ​​a flexible screen using an image acquisition device, the images of the bent area exhibit strongly reflective edge reflective regions, or edge reflective bands. Based on this, such as Figure 1 As shown, one embodiment of this application provides a method for detecting break lines in a flexible screen, including the following steps:

[0045] S10. Use an image acquisition device to acquire images of the bending area of ​​the flexible screen.

[0046] In some embodiments, acquiring images of the bending area of ​​the flexible screen using an image acquisition device includes: acquiring multiple bending area images of the flexible screen using multiple image acquisition devices with different acquisition angles.

[0047] Therefore, subsequent images of multiple bending areas acquired from multiple angles can be used to identify break lines separately, thereby improving the accuracy of identifying break lines in the bending areas of flexible screens and avoiding missed detections due to factors such as the narrow acquisition range of a single image acquisition device.

[0048] In a specific example, such as Figure 2 As shown, taking the fracture line detection of curved screen 20 as an example, the bending area of ​​curved screen 20 is a concentrated area of ​​product defects, especially for example... Figure 2Regarding the fracture line 201 of the display layer shown, this example utilizes three image acquisition devices with different acquisition angles to acquire images of the bending area of ​​the curved screen 20, namely image acquisition devices 21, 22, and 23. Fracture line identification can then be performed on the bending area images of the curved screen 20 acquired by image acquisition device 21, image acquisition device 22, and image acquisition device 23, respectively. Image acquisition device 21 includes a CCD camera 211 and a point light source 212; image acquisition device 22 includes a CCD camera 221 and a point light source 222; and image acquisition device 23 includes a CCD camera 231 and a point light source 232. When acquiring images of the bending area, image acquisition devices 21, 22, and 23 are used respectively, and the point light sources 212, 222, and 232 in image acquisition devices 21, 22, and 23 are designed to prevent interference between each other through spatial positioning and / or time settings (e.g., sequential shooting). Among them, the fracture line is usually narrow and long, so the resolution of the images captured by the selected CCD cameras 231, 232 and 233 can be, for example, 2048*20000.

[0049] S20. Acquire the image of the bending area of ​​the flexible screen captured by the image acquisition device, and convert the bending area image into a binary image.

[0050] Continuing with the previous example, if CCD cameras 231, 232, and 233 are all CCD cameras that capture grayscale images, then based on the characteristic that the fracture line in the bending region is usually roughly parallel to the bending axis of the bending region, the grayscale images captured by CCD cameras 231, 232, and 233 can be compressed, for example, by a row compression ratio of 1-6 times and a column compression ratio of 1-3 times. Then, the compressed images are binarized to obtain, for example... Figure 3 The binarized bendable region image shown on the left side of the image, where, as Figure 3 The binarized bendable region image shown in the left-hand image is, for example... Figure 2 The image of the curved area of ​​the curved screen 20 acquired by the image acquisition device 22 is obtained after image compression and binarization.

[0051] In addition to the examples above, if the image of the bending area captured by the image acquisition device is a color image, it is necessary to convert the color image into a grayscale image before image compression and binarization.

[0052] In the above example, converting the image to a grayscale image can be achieved using various existing grayscale conversion algorithms, such as based on the following formula: Gray = (Red * 0.3 + Green * 0.59 + Blue * 0.11), where Gray is the grayscale value of the pixel, and Red, Green, and Blue are the red, green, and blue component values ​​of that pixel, respectively. Binarizing the image can be achieved using various existing binarization algorithms, such as the Otsu algorithm, Bernsen algorithm, Niblack algorithm, cyclic thresholding algorithm, iterative binarization algorithm, etc. The resulting binarized image can be set with a background grayscale value of 0 (i.e., black), and grayscale values ​​of 255 (i.e., white) for features such as edges and contours.

[0053] S30. Detect the edge reflection area in the binarized image, and determine the region of interest for the break line detection based on the edge reflection area.

[0054] Therefore, the flexible screen break line detection method provided in this embodiment is based on the edge reflective area with obvious grayscale features in the binarized image to accurately and efficiently extract the region of interest for break line detection.

[0055] In a specific example, detecting reflective areas at the edges can be achieved using various existing edge detection algorithms, such as edge detection algorithms based on the Canny operator, Prewitt operator, Sobel operator, etc.

[0056] In some embodiments, determining the region of interest for break line detection based on the edge reflective area includes: selecting the region within a set pixel width range at a set pixel distance on a set side of the selected edge reflective area as the region of interest for break line detection.

[0057] Given that the image acquisition parameters, shooting angle, shooting distance, and bending angle of the bending area to be detected are determined, the size of the region of interest for break line detection and its positional relationship with the edge reflective area are also determined. Based on this, this method can ensure the accuracy and efficiency of extracting the region of interest for break line detection.

[0058] In some embodiments, the height of the region of interest for break line detection is selected to be the same as the height of the edge reflective region.

[0059] This method can further improve the efficiency of identifying fracture lines in the bending area of ​​flexible screens.

[0060] Continuing with the previous example, for example Figure 2 The image of the curved area of ​​the curved screen 20 acquired by the image acquisition device 22 is obtained after image compression and binarization processing, as shown in the figure. Figure 3 The binarized image shown on the left side of the image. Figure 2As shown, the image acquisition device 22 acquires the image of the left curved area of ​​the curved screen 20. Therefore, as... Figure 3 In the binarized image shown on the left, the edge-reflective region 31 is located on the left side of the binarized image, and the region of interest for breakline detection is located to the right of the edge-reflective region. That is, the region within a set pixel width at a set pixel distance to the right of the edge-reflective region 31 is the region of interest for breakline detection. Furthermore, when acquiring an image of the right-side bend of a curved screen using an image acquisition device, the parameters of the image acquisition device can be adjusted so that the edge-reflective region in the output right-side bend image is also located on the right side of the right-side bend image. In other words, the region of interest for breakline detection in the right-side bend image is still located to the right of the edge-reflective region. This improves image processing speed and further enhances detection efficiency.

[0061] For example Figure 3 The binarized image shown on the left side of the image has a thick bright line shape for the reflective edge area 31. After binarization, it forms a width of, for example, 50-150 pixels (width is...). Figure 3 After detecting the highlighted area (horizontal length of the left side of the image) and the edge reflection area in the binarized image, the region of interest for the break line detection can be obtained by expanding to the right. For example, taking the right side of the edge reflection area 31 as the reference, expanding to the right by X1 pixels and X2 pixels, the area between X1 and X2 is the selected region. Figure 3 The image on the right shows the region of interest (ROI) for the broken line detection, and the height of the ROI is selected to be the same as the height of the edge reflective region 31 (height is...). Figure 3 The vertical length of the left-hand image is such that, for example, the height of the edge reflective region 31 is 800 pixels, and the height of the region of interest for breakline detection is also selected as 800 pixels. The pixel distances X1 and X2 are determined based on the image acquisition parameters, shooting angle, shooting distance of the image acquisition unit 22, and the bending angle of the curved screen 20 in the bending area to be detected. Thus, when multiple curved screens 20 of the same model are detected sequentially, as long as the relative position of the image acquisition unit 22 and the curved screen 20 (e.g., placed on a fixture) is fixed, without changing the image acquisition parameters of the image acquisition unit 22, the position and shape of the edge reflective region 31 in the binarized image are basically the same for each curved screen 20 detected sequentially, the relative position of the edge reflective region 31 and the region of interest for breakline detection are the same, and the size of the region of interest for breakline detection is also the same, which is beneficial for achieving efficient pipeline detection.

[0062] S40. Perform image enhancement on the region of interest.

[0063] In some embodiments, image enhancement includes at least one of gamma transformation, noise point removal, and edge sharpening.

[0064] This method can further improve the accuracy of identifying fracture lines in the bending area of ​​flexible screens.

[0065] In a specific example, gamma transform increases the grayscale value of the Region of Interest (ROI) when the gamma value is greater than 1 and decreases the grayscale value of the ROI when the gamma value is less than 1, to correct overexposure or underexposure. Noise point removal can be achieved by using existing filtering algorithms to eliminate abnormal bright spot interference. Edge sharpening of the region of interest aims to further enhance the grayscale features of the break lines, and can be achieved using various existing sharpening algorithms, such as those based on the Canny operator, the Sobel operator, and the Laplas operator.

[0066] S50. Perform break line identification on the region of interest to obtain the break line detection results.

[0067] In some embodiments, identifying break lines in the region of interest includes: identifying break lines in the region of interest based on grayscale features; if a break line is identified, a determination is made: if the angle deviation between the break line and the bending axis of the bending area is less than a set angle threshold, the detection result is determined to be a defective break line.

[0068] The break line in the bending area is usually roughly parallel to the bending axis of the bending area. Based on this, this method can further determine whether the identified break line is indeed a defective break line in the display layer or a false defect caused by factors such as stains or flaws in the curved glass cover of a curved screen or the flexible cover of a foldable screen by judging whether the angular deviation between the identified break line and the bending axis is less than a set angle threshold. This further improves the accuracy of identifying the break line in the bending area of ​​the flexible screen.

[0069] Continuing with the previous example, after identifying the break line based on grayscale features in the region of interest, if a break line is determined to exist, the starting coordinates (x, y) of the break line are extracted. s y s ) and endpoint coordinates (x e y e ), calculate k = (x s -x e ) / (y s -y e) Determine whether -1 < k < 1 holds: If it holds, it indicates that the angular deviation between the fracture line and the bending axis of the bending region is less than 45°, and it is determined that the detection result shows a defect in the fracture line; if it does not hold, it indicates that the angular deviation between the fracture line and the bending axis of the bending region is greater than or equal to 45°, and it is determined that the fracture line is a false defect, that is, there is no fracture line in the bending region. It should be noted that the set angle threshold can be adjusted according to the actual situation.

[0070] In some embodiments, before making a judgment if a fracture line is recognized, it further includes: merging the fracture lines recognized in the region of interest based on the Hough transform.

[0071] Fracture lines are usually long, and the gray-scale features at the slightly fractured positions on the fracture line are not obvious and may not be correctly recognized. Based on this, this method can avoid the situation where one fracture line is recognized as multiple discontinuous fracture lines.

[0072] Combined with the above method, as Figure 4 shown, an exemplary process of the fracture line detection method for the flexible screen provided in this embodiment includes: First, collect an image of the bending region; then, perform gray-scale processing; then, perform image compression; then, perform binarization processing; then, detect the edge reflective band; then, select the ROI; then, perform image enhancement; then, perform fracture line recognition: If the recognition result is that there is no fracture line (i.e., no), it is determined that the flexible screen passes the test (i.e., OK); if the recognition result is that there is a fracture line (i.e., yes), then further perform angle screening (i.e., whether the angular deviation between the fracture line and the bending axis of the bending region is less than the set angle threshold). If the angle screening result fails (i.e., the angular deviation between the fracture line and the bending axis of the bending region is greater than or equal to the set angle threshold), it is determined that the flexible screen passes the test (i.e., OK); if the angle screening result passes (i.e., the angular deviation between the fracture line and the bending axis of the bending region is less than the set angle threshold), it is determined that the flexible screen fails the test (i.e., NG).

[0073] In summary, the fracture line detection method for the flexible screen provided in this embodiment is based on the edge reflective region with obvious gray-scale features in the binary image to accurately and efficiently extract the region of interest for fracture line detection, which can achieve accurate and efficient detection of the fracture line in the bending region of the flexible screen, effectively reducing the processing time for identifying the defects of the flexible screen and effectively improving the recognition rate of the defects of the flexible screen. Among them, for the original image collected with a resolution of, for example, 2048 * 20000, the processing time can be reduced to less than 150 ms.

[0074] As Figure 5 shown, another embodiment of the present application provides a fracture line detection device for a flexible screen, including:

[0075] The preprocessing module 501 is configured to acquire the bending area image of the flexible screen acquired by the image acquisition device 510, and convert the bending area image into a binary image;

[0076] The region of interest determination module 502 is configured to detect edge reflection regions in the binarized image and determine the region of interest for breakline detection based on the edge reflection regions; and

[0077] The recognition module 504 is configured to identify fracture lines in the region of interest and obtain fracture line detection results.

[0078] In some embodiments, the flexible screen break line detection device provided in this embodiment further includes an image acquisition unit 510 for acquiring images of the bending area of ​​the flexible screen.

[0079] In some embodiments, the image acquisition device 510 includes multiple image acquisition devices 510 with different acquisition angles. In a specific example, such as Figure 2 As shown, the flexible screen break line detection device provided in this embodiment includes three image acquisition units.

[0080] In some embodiments, the image acquisition device 510 includes a CCD camera and a point light source. For example, the image acquisition device 510 including a CCD camera and a point light source... Figure 2 The image acquisition device shown in the image.

[0081] In some embodiments, the region of interest determination module 502 is configured to determine the region of interest for break line detection based on the edge reflective region, including: the region within a set pixel width range at a set pixel distance on a set side of the selected edge reflective region is the region of interest for break line detection.

[0082] In some embodiments, the region of interest determination module 502, configured to determine the region of interest for break line detection based on the edge reflective region, further includes: selecting the height of the region of interest for break line detection to be the same as the height of the edge reflective region.

[0083] In some embodiments, the identification module 504 is configured to identify fracture lines in the region of interest and obtain fracture line detection results including: identifying fracture lines in the region of interest based on grayscale features; if a fracture line is identified, a judgment is made: based on the fact that the angle deviation between the fracture line and the bending axis of the bending area is less than a set angle threshold, the detection result is determined to be a defective fracture line.

[0084] In some embodiments, the identification module 504 is configured to identify fracture lines in the region of interest, and the fracture line detection result further includes: merging the fracture lines identified in the region of interest based on Hough transform.

[0085] In some embodiments, such as Figure 5 As shown, the flexible screen fracture line detection device provided in this embodiment also includes an image enhancement module 503, configured to perform image enhancement on the region of interest.

[0086] In some embodiments, image enhancement includes at least one of gamma transformation, noise point removal, and edge sharpening.

[0087] In a specific example, such as Figure 5 As shown, the preprocessing module 501, the region of interest determination module 502, the image enhancement module 503, and the recognition module 504 in the flexible screen break line detection device provided in this embodiment are integrated into the computer device 500. Figure 5 As shown, the flexible screen break line detection device in this example includes three image acquisition units 510. The computer device 500 and the three image acquisition units 510 are respectively connected through a network that provides a communication link. The network can include various connection types, such as wired, wireless communication links or fiber optic cables, etc. Figure 5 As shown, the computer device 500 is connected to the three image acquisition units 510 via wireless communication links. The computer device 500 can be a variety of distributed or individual electronic devices that support image processing, including but not limited to tablet computers, laptops, and desktop computers.

[0088] It should be noted that the principle and working process of the flexible screen break line detection device provided in this embodiment are similar to the above-described flexible screen break line detection method. The relevant parts can be referred to the above description, and will not be repeated here.

[0089] like Figure 6 As shown, a computer system suitable for implementing the fracture line detection device provided in the above embodiments includes a central processing module (CPU), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage portion into a random access memory (RAM). Various programs and data required for the operation of the computer system are also stored in the RAM. The CPU, ROM, and RAM are connected via a bus. An input / output (I / O) interface is also connected to the bus.

[0090] The following components are connected to the I / O interface: input sections including keyboards, mice, etc.; output sections including liquid crystal displays (LCDs) and speakers, etc.; storage sections including hard disks, etc.; and communication sections including network interface cards such as LAN cards and modems. The communication sections perform communication processing via networks such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as required.

[0091] Specifically, according to this embodiment, the process described in the flowchart above can be implemented as a computer software program. For example, this embodiment includes a computer program product comprising a computer program tangibly embodied on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium.

[0092] The flowcharts and schematic diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of the system, method, and computer program product of this embodiment. In this regard, each block in the flowchart or schematic diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the schematic diagram and / or flowchart, and combinations of blocks in the schematic diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The modules described in this embodiment can be implemented in software or hardware. These modules can also be housed in a processor; for example, a processor may be described as including a preprocessing module, a region of interest determination module, and an identification module. The names of these modules do not necessarily limit the functionality of the module itself. For example, the identification module could also be described as a "break line detection module."

[0094] In another aspect, this embodiment also provides a non-volatile computer storage medium. This non-volatile computer storage medium can be the non-volatile computer storage medium included in the above-described device, or it can be a separate non-volatile computer storage medium not assembled into the terminal. The non-volatile computer storage medium stores one or more programs. When the one or more programs are executed by a device, the device: acquires an image of the bending area of ​​the flexible screen captured by an image acquisition device, and converts the bending area image into a binary image; detects the edge reflection area in the binary image, determines the region of interest for break line detection based on the edge reflection area; and performs break line identification on the region of interest to obtain the break line detection result.

[0095] In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0096] It should also be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0097] Obviously, the above embodiments of this application are merely examples for clearly illustrating this application, and are not intended to limit the implementation of this application. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all implementation methods here. Any obvious variations or modifications derived from the technical solutions of this application are still within the protection scope of this application.

Claims

1. A method for detecting fracture lines in a flexible screen, characterized in that, include: The bending area image of the flexible screen is acquired by the image acquisition device, the bending area image is compressed, and the compressed bending area image is converted into a binarized image. The edge reflection regions in the binarized image are detected, and the region of interest for the break line detection is determined based on the edge reflection regions. Break lines are identified in the region of interest to obtain break line detection results. The step of determining the region of interest for break line detection based on the edge reflective area includes: selecting the region within a set pixel width range at a set pixel distance on a set side of the edge reflective area as the region of interest for break line detection; The step of identifying the break line in the region of interest includes: identifying the break line in the region of interest based on grayscale features; if a break line is identified, a judgment is made: if the angle deviation between the break line and the bending axis of the bending area is less than a set angle threshold, the detection result is determined to be that there is a defective break line. Based on the fact that the angular deviation between the fracture line and the bending axis of the bending area is greater than or equal to a set angle threshold, the detection result is determined to be that there is no fracture line in the bending area.

2. The method according to claim 1, characterized in that, The height of the region of interest for the fracture line detection is selected to be the same as the height of the edge reflective region.

3. The method according to claim 1, characterized in that, Before making a judgment if a break line is identified, the method further includes: merging the break lines identified in the region of interest based on the Hough transform.

4. The method according to claim 1, characterized in that, After determining the region of interest for break line detection based on the edge reflective area and before performing break line identification on the region of interest, the method further includes: performing image enhancement on the region of interest.

5. The method according to claim 4, characterized in that, The image enhancement includes at least one of gamma transformation, noise point removal, and edge sharpening.

6. The method according to any one of claims 1-5, characterized in that, The acquisition of the flexible screen bending area image acquired by the image acquisition device includes: acquiring multiple bending area images of the flexible screen acquired by multiple image acquisition devices with different acquisition angles.

7. A device for detecting fracture lines in a flexible screen, characterized in that, include: The preprocessing module is configured to acquire the bending area image of the flexible screen acquired by the image acquisition device, compress the bending area image, and convert the compressed bending area image into a binarized image. The region of interest determination module is configured to detect the edge reflection region in the binarized image and determine the region of interest for the break line detection based on the edge reflection region; as well as The identification module is configured to identify fracture lines in the region of interest and obtain fracture line detection results. The region of interest determination module is configured to determine the region of interest for break line detection based on the edge reflective region by selecting a region within a preset pixel width range at a preset pixel distance on a preset side of the edge reflective region as the region of interest for break line detection. The identification module is configured to identify break lines in the region of interest and obtain break line detection results, including: identifying break lines in the region of interest based on grayscale features and making a judgment: if a break line exists and the angle deviation between the break line and the bending axis of the bending area is less than a preset angle threshold, then the detection result is determined to be a defective break line. Based on the fact that the angular deviation between the fracture line and the bending axis of the bending area is greater than or equal to a set angle threshold, the detection result is determined to be that there is no fracture line in the bending area.

8. The apparatus according to claim 7, characterized in that, The device also includes the image acquisition unit for acquiring images of the bending area of ​​the flexible screen.

9. The apparatus according to claim 8, characterized in that, The image acquisition device includes multiple image acquisition devices with different acquisition angles.

10. The apparatus according to claim 8 or 9, characterized in that, The image acquisition device includes a CCD camera and a point light source.

11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-6.

12. A computer non-transient readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images