Method for detecting damage to a terminal screen and related device

Abstract

The present invention provides a method for recognizing screen damage of a terminal and a related device, the method includes: acquiring a first screen image of a detection target, dividing the first screen image into a first preset number of detection target images, inputting each detection target image into a recognition model to obtain the number of crack pixels of each detection target image, the recognition model being obtained by training based on each second screen image with crack pixels marked, determining that a screen damage has occurred on the screen of the first terminal if the number of crack pixels of any detection target image is equal to or greater than the second preset number, and determining that no screen damage has occurred on the screen of the first terminal if the number of crack pixels of each detection target image is less than the second preset number. In the present invention, the recognition model is obtained by training based on the second screen image with crack pixels marked, and the recognition model can accurately recognize screen cracks based on the current screen image of the terminal, thereby improving the accuracy of terminal damage recognition.

Description

[Technical field]

[0001] The present invention relates to the field of image recognition technology, and in particular to a method for detecting screen damage in a terminal and related devices. [Background technology]

[0002] With the development and spread of smart devices, the screen damage insurance business has been born. The screen damage insurance business is an insurance business that can compensate for unexpected damage to the screen of a device or replace the screen.

[0003] Currently, screen damage on devices is identified by manually reviewing screen images taken by users, but screen cracks may be minute and the screen images taken by users may not display the screen cracks.

[0004] This reduces the accuracy of detecting damage to the device's screen. Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention provides a method and related device for detecting damage to a terminal screen, which solves the technical problem of low accuracy of detecting damage to a terminal screen. [Means for solving the problem]

[0006] In one aspect, the present invention provides a method for detecting screen breakage of a terminal, the method comprising the steps of: acquiring a first screen image of a detection target and dividing the first screen image into a first preset number of detection target images, the first screen image including a screen of a first terminal, and the first screen image being captured while a screen of the first terminal is turned on; inputting each of the target images into a recognition model to obtain a number of crack pixels for each of the target images, the recognition model being trained based on each of the second screen images in which crack pixels are marked to obtain the number of crack pixels; If the number of cracked pixels in any of the detection target images is equal to or greater than a second preset number, determining that a screen breakage has occurred on the screen of the first terminal; and determining that no screen breakage has occurred on the screen of the first terminal if the number of cracked pixels in each of the detection target images is less than a second preset number.

[0007] In one embodiment, dividing the first screen image into a first preset number of images to be detected comprises: removing a background image in the first screen image to obtain a third screen image; Dividing the third screen image into a first preset number of images to be detected.

[0008] In one embodiment, dividing the first screen image into a first preset number of images to be detected comprises: converting the first screen image into a fourth screen image of a preset ratio, the preset ratio being an aspect ratio of an actual screen; Dividing the fourth screen image into a first preset number of images to be detected.

[0009] In one embodiment, before inputting each of the target images into a recognition model to obtain the number of crack pixels in each target image, further comprising: acquiring each second screen image with the cracked pixels marked thereon, the second screen image including a screen of a second terminal, the second screen image being taken while the screen of the second terminal is illuminated; Dividing each of the second screen images into a first preset number of training object images; Training a preset model based on each of the training object images to obtain a recognition model, and storing the recognition model.

[0010] In one embodiment, dividing each of the second screen images into a first preset number of training object images includes: performing a preset process on each of the second screen images to obtain an image to be divided, the preset process including performing a conversion of a preset ratio on the second screen images and / or removing a background image in the second screen images; Dividing the image to be segmented into a first preset number of training image targets.

[0011] In one embodiment, acquiring a first screen image of the first terminal to be detected includes: capturing an image of the first terminal while the screen is illuminated; Extracting key points in the image to obtain each corner of the screen of the first terminal; and dividing the image based on each of the corners to obtain the first screen image.

[0012] In another aspect, the present invention further provides a screen breakage recognition device for a terminal, the screen breakage recognition device for the terminal comprising: an acquisition module used for acquiring a first screen image of a detection target and dividing the first screen image into a first preset number of detection target images, the first screen image including a screen of a first terminal, and the first screen image being captured while the screen of the first terminal is turned on; an input module used to input each of the target images into a recognition model to obtain the number of crack pixels of each of the target images, the recognition model being trained based on each of the second screen images in which the crack pixels are marked; and a determination module adapted to determine that a screen breakage has occurred on the screen of the first terminal when the number of cracked pixels in any of the detection target images is equal to or greater than a second preset number; The determination module is further used for determining that no screen breakage has occurred on the screen of the first terminal when the number of cracked pixels in each of the detection target images is less than the second preset number.

[0013] In another aspect, the present invention further provides a screen breakage recognition device for a terminal, the device including a memory and a processor, The memory stores computer executable instructions; The processor executes the computer executable instructions stored in the memory, thereby causing the processor to perform the method for recognizing screen breakage in a terminal described above.

[0014] In another aspect, the present invention further provides a computer-readable storage medium having stored thereon computer-executable instructions, which, when executed by a processor, realise the above-described method for recognising screen breakage in a terminal.

[0015] In another aspect, the present invention Is, When the computer program is executed by the processor, the above-described method for recognizing a broken screen of a terminal is realized. M More to offer.

[0016] The present invention provides a method for detecting screen damage in a terminal and a related device, which includes obtaining a first screen image of a detection target, dividing the first screen image into a first preset number of detection target images, inputting each detection target image into a recognition model to obtain the number of crack pixels in each detection target image, and determining whether the number of crack pixels in any of the detection target images is a second preset number. That's all. if the number of crack pixels in each detection target image is less than the second preset number, it is determined that screen damage has occurred on the terminal screen. In the present invention, the recognition model is obtained by training based on the second screen image in which the crack pixels are marked, so that the recognition model can accurately recognize screen cracks based on the current screen image of the terminal, thereby improving the accuracy of terminal damage recognition. [Brief description of the drawings]

[0017] The drawings herein are incorporated into the specification, illustrate embodiments consistent with the present disclosure, and together with the specification serve to explain the principles of the present disclosure. [Figure 1] FIG. 2 is a scene schematic diagram of the terminal screen damage recognition method of the present invention; [Diagram 2] 1 is a flowchart of a first embodiment of a method for detecting damage to a terminal screen of the present invention. [Diagram 3] 11 is a detailed flowchart of step S10 in a second embodiment of a method for detecting damage to a terminal screen according to the present invention. [Figure 4] 13 is a detailed flowchart of step S10 in the third embodiment of the method for detecting damage to a terminal screen of the present invention. [Diagram 5] 10 is a flowchart of a fourth embodiment of a method for detecting damage to a terminal screen of the present invention. [Figure 6] FIG. 2 is a schematic diagram of a screen image with cracked pixels marked according to the present invention; [Figure 7]13 is a detailed flowchart of step S10 in the fifth embodiment of the method for detecting screen damage of a terminal according to the present invention. [Figure 8] 1 is a schematic diagram of a module of a terminal screen breakage recognition device of the present invention; [Figure 9] 1 is a hardware configuration diagram of a screen breakage recognition device of a terminal of the present invention. The above drawings show clear examples of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the concept of the present disclosure in any way, but are intended to explain the concept of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, detailed description will be given of exemplary embodiments shown in the drawings. When the following description refers to the drawings, the same numerals in different drawings represent the same or similar elements unless otherwise stated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure, as detailed in the appended claims.

[0019] The present invention provides a method for recognizing a screen breakage of a terminal. With reference to FIG. 1, a screen image is taken with the screen of a mobile phone turned on, and the screen image shows that two areas of the mobile phone are cracked, specifically the cracked areas of the screen image. The screen image is input to a terminal device as an image of a mobile phone to be detected. The terminal device may be any device with data processing capability, for example, the terminal device may be a computer. The recognition model can output the number of cracked pixels on the screen of the mobile phone by recognizing the image of the detection target, and the terminal device can output hint information that the screen of the mobile phone is broken or not broken according to the number and a preset number. For example, when the number of cracked pixels is more than the preset number, the terminal device outputs hint information that the screen of the mobile phone is broken, and when the number of cracked pixels is equal to or less than the preset number, the terminal device outputs hint information that the screen of the mobile phone is not broken.

[0020] Hereinafter, the technical solution of the present invention and how the technical solution of the present application solves the above technical problems will be described in detail with specific examples. Some of the following specific examples can be combined with each other, and the same or similar concepts or processes may not be described in some examples. Hereinafter, the embodiments of the present invention will be described with reference to the drawings.

[0021] Referring to FIG. 2, FIG. 2 is a first embodiment of a method for detecting screen breakage of a terminal according to the present invention, which includes the following steps:

[0022] Step S10, obtain a first screen image of the detection object, and divide the first screen image into a first preset number of images of the detection object, where the first screen image includes a screen of a first terminal, and the first screen image is taken while the screen of the first terminal is turned on.

[0023] In this embodiment, the execution subject is the screen breakage recognition device of the terminal, and for convenience of description, the device is hereinafter used to refer to the level recognition device of the terminal. The device may be any terminal device with data processing capability, for example, the device may be a computer, a notebook computer, or a mobile phone.

[0024] The device obtains a first screen image of a detection target. The first screen image includes a screen of a terminal, and the terminal is defined as a first terminal, which may be a mobile terminal such as a mobile phone, a tablet, etc. The first screen image is taken while the screen of the first terminal is turned on, that is, the first screen image includes the screen of the first terminal that is turned on, and it is easy to recognize whether the screen of the first terminal is cracked based on the turned on screen.

[0025] Furthermore, the device divides the first screen image into a first preset number of detection target images, where the first preset number may be any suitable value, for example, the first preset number may be 8. Moreover, each detection target image is preferably a square image of the same size, that is, the first screen image is evenly divided into the first preset number of detection target images.

[0026] Step S20: input the image of each detection target into a recognition model to obtain the number of crack pixels in each detection target image, and the recognition model is trained and obtained based on each second screen image in which the crack pixels are marked.

[0027] The device stores a recognition model. The recognition model is trained based on each second screen image with a marked cracked pixel. The second screen image includes a screen of a second terminal, and the second screen image is taken while the screen of the second terminal is turned on. The cracked pixel refers to a pixel in the second screen image that has a crack.

[0028] The device inputs the image of each target to a recognition model, which recognizes each target and outputs the number of crack pixels in each target image.

[0029] Step S30: if the number of cracked pixels in any of the images to be detected is equal to or greater than a second preset number, it is determined that a screen breakage occurs on the screen of the first terminal.

[0030] Although the cracks are generally concentrated in a certain area of ​​the screen, the total number of pixels on the entire screen is large, and the ratio of the cracked pixels corresponding to the cracks to the total number is relatively small, so the device erroneously determines that the screen of the first terminal does not have screen damage. Therefore, the device divides the first screen image and multiplies the total number of pixels of the image to be detected by a second preset In number By setting, the proportion of the number of cracked pixels can be increased, so as to reasonably determine whether the screen of the first terminal has screen damage, that is, to avoid the device from making a false determination.

[0031] If the device determines that the number of cracked pixels in any of the detected images is equal to or greater than a second preset number, it determines that a screen break has occurred on the screen of the first terminal.

[0032] Step S40: if the number of cracked pixels in each detection target image is less than a second preset number, it is determined that no screen breakage occurs on the screen of the first terminal.

[0033] The device can determine that no screen breakage has occurred on the screen of the first terminal by detecting that the number of cracked pixels in each target image is less than a second preset number.

[0034] In the technical solution provided by this embodiment, a first screen image of a target terminal is obtained, the first screen image is divided into a first preset number of target images, each target image is input into a recognition model to obtain the number of crack pixels of each target image, and if the number of crack pixels of any target image is equal to or greater than a second preset number, it is determined that screen damage has occurred on the screen of the terminal, and if the number of crack pixels of each target image is less than the second preset number, it is determined that screen damage has not occurred on the screen of the terminal. In the present invention, the recognition model is obtained by training based on the second screen image with the crack pixels marked, and the recognition model can accurately recognize screen cracks based on the current screen image of the terminal, thereby improving the accuracy of terminal damage recognition.

[0035] Referring to FIG. 3, FIG. 3 is a second embodiment of the terminal screen breakage recognition method of the present invention, based on the first embodiment, step S10 includes: Step S11: remove the background image in the first screen image to obtain a third screen image. Step S12, divide the third screen image into a first preset number of images to be detected.

[0036] In this embodiment, the first screen image is captured while the screen of the first terminal is turned on, and therefore the first screen image includes screen displayed content, which may cover or obscure cracks in the screen.

[0037] In response to this, the device obtains the first screen image and then image The background image in the third screen is removed to obtain the third screen image, that is, the third screen image is a pure color screen such as a white field screen.

[0038] The device further divides the third screen image into a first preset number of images to be detected, so that the device can more clearly recognize whether screen breakage has occurred on the screen of the terminal.

[0039] In the technical solution provided by this embodiment, the device removes the background screen in the first screen image to obtain a third screen image, and further divides the third screen image into a first preset number of images to be detected, so as to avoid the background screen of the screen in the first screen image from affecting the recognition accuracy of the recognition model.

[0040] Referring to FIG. 4, FIG. 4 is a third embodiment of the method for detecting screen damage of a terminal according to the present invention, and based on the first or second embodiment, step S10 includes: Step S13, convert the first screen image into a fourth screen image of a preset ratio, where the preset ratio is the aspect ratio of the actual screen. Step S14: Divide the fourth screen image into a first preset number of images to be detected.

[0041] In this embodiment, the device converts the first screen image into a fourth screen image with a preset ratio, and the preset ratio is the aspect ratio of the actual screen. Specifically, the aspect ratio of the screen of a mobile phone is generally 2:1, and when the first screen image includes the screen of the mobile phone, the device converts the first screen image into a fourth screen image with a 2:1 ratio.

[0042] The device divides the fourth screen image into a first preset number of detection target images, for example, divides the fourth screen image equally into 2×4 to obtain eight detection target images.

[0043] In the technical solution provided by this embodiment, the device converts the first screen image into a fourth screen image of a preset ratio, and then divides the fourth screen image into a first preset number of images to be detected, that is, processes the image according to the actual aspect ratio of the screen of the first terminal, normalizes the image to be recognized, and unifies the recognition standard for whether screen damage occurs on the screen.

[0044] Referring to FIG. 5, FIG. 5 is a fourth embodiment of a method for recognizing screen breakage of a terminal according to the present invention, which is based on any one of the first to third embodiments and further includes the following before step S20:

[0045] Step S50, obtain each second screen image with the cracked pixels marked, where the second screen image includes a screen of a second terminal, and the second screen image is taken while the screen of the second terminal is turned on.

[0046] In this embodiment, the device needs to be trained to obtain a recognition model. Specifically, the device selects an image of a mobile phone of each model uploaded by the user from the database, where the mobile phone is a second terminal, and obtains a second screen image based on each image. The second screen image includes the screen of the second terminal, and the second screen image are taken while the screen of the second device is on. Each second screen image Cracks Mark the pixels. Specifically, refer to Fig. 6, Fig. 6 is a marked second screen image, that is, the white lines in the second screen image are the cracked pixels of the screen.

[0047] Step S60, divide each second screen image into a first preset number of training object images.

[0048] The device divides each second screen image into a first preset number of training object images, and divides the second screen images. How to divideThe method is the same as the method for dividing the first screen image, and the detailed description will not be repeated here.

[0049] Step S70, training the preset model based on each training object image to obtain a recognition model, and saving the recognition model.

[0050] The device can obtain a recognition model by training a preset model based on images of each training object, and then store the recognition model.

[0051] After obtaining the second screen image, the device performs preset processing on the second screen image to obtain an image to be divided, and the preset processing includes performing conversion of the second screen image to a preset ratio and / or removing a background screen in the second screen image. The conversion of the second screen image to a preset ratio is the same as the conversion of the first screen image to a preset ratio, and removing the background screen in the second screen image is the same as removing the background screen in the first screen image. For specific details, please refer to the above description, and detailed description will not be repeated here.

[0052] In the technical solution provided by this embodiment, the device obtains each second screen image marked with cracked pixels, divides each second screen image into a first preset number of training target images, thereby training a preset model according to each training target image to obtain a recognition model, and then accurately recognizes whether screen damage occurs on the terminal screen based on the recognition model.

[0053] Referring to FIG. 7, FIG. 7 is a fifth embodiment of a method for recognizing screen breakage of a terminal according to the present invention, and based on any one of the first to third embodiments, step S10 includes the following: Step S15: capture an image while the screen of the first terminal is turned on. Step S16: Extract key points in the image to obtain each corner of the screen of the first terminal. Step S17, divide the image based on each corner to obtain a first screen image.

[0054] In this embodiment, when performing screen damage recognition on a terminal, the terminal's posture is different, which affects the accuracy of the terminal's screen damage recognition. In response to this, the device can extract an image that includes only the terminal's screen from the image.

[0055] Specifically, the device first obtains an image uploaded by a user while the screen of the first terminal is turned on. The device extracts key points from the image using a key point extraction model, and obtains each corner of the image of the screen of the first terminal. The key point extraction model marks the positions of the four intersections of the extension lines of the four sides of the frame of the mobile phone in the order of upper left, lower left, lower right, and upper right, and defines these four points as the key points of the mobile phone.

[0056] The device can obtain the first screen image by splitting the image based on each corner, ie, the device performs the recognition of the screen breakage on the image that contains only the screen.

[0057] In the technical solution provided by this embodiment, the device obtains an image of the first terminal while the screen is turned on, determines each corner of the screen from the image, and thereby divides the first screen image from the image based on each corner, so as to prevent the attitude of the terminal from affecting the accuracy of screen damage recognition.

[0058] The present invention further provides a terminal screen breakage recognition device. Referring to FIG. 8, the terminal screen breakage recognition device 800 includes: An acquisition module 810 used for acquiring a first screen image of a detection target and dividing the first screen image into a first preset number of images of the detection target, where the first screen image includes a screen of a first terminal, and the first screen image is taken while the screen of the first terminal is turned on; an input module 820, which is used to input each target image into a recognition model to obtain the number of crack pixels of each target image, the recognition model being trained based on each second screen image in which the crack pixels are marked; and a determination module 830, which is used to determine that a screen breakage occurs on the screen of the first terminal when the number of cracked pixels of any of the detected images is equal to or greater than a second preset number; The determining module 830 is used for determining that no screen breakage occurs on the screen of the first terminal when the number of cracked pixels of each detection target image is less than a second preset number.

[0059] In one embodiment, the terminal screen breakage recognition device 800 includes: a processing module used for removing a background image in the first screen image to obtain a third screen image; a division module used for dividing the third screen image into a first preset number of images to be detected.

[0060] In one embodiment, the terminal screen breakage recognition device 800 includes: A conversion module used for converting the first screen image into a fourth screen image of a preset ratio, the preset ratio being the aspect ratio of an actual screen; a division module used for dividing the fourth screen image into a first preset number of images to be detected.

[0061] In one embodiment, the terminal screen breakage recognition device 800 includes: an acquisition module 810 used to acquire each second screen image marked with cracked pixels, the second screen image including a screen of a second terminal, the second screen image being taken while the screen of the first terminal is illuminated; a segmentation module used for segmenting each second screen image into a first preset number of training object images; a training module used for training the preset model based on the image of each training object to obtain a recognition model, and storing the recognition model.

[0062] In one embodiment, the terminal screen breakage recognition device 800 includes: a processing module used for performing a preset processing on each second screen image to obtain an image to be divided, the preset processing including performing a conversion of a preset ratio on the second screen image and / or removing a background image in the second screen image; a segmentation module used for segmenting the segmentation target image into a first preset number of training target images.

[0063] In one embodiment, the terminal screen breakage recognition device 800 includes: an acquisition module 810 used for acquiring images while the screen of the first terminal is turned on; an extraction module used to extract key points in the image to obtain the corners of the screen of the first terminal; a division module used for dividing the image based on each corner to obtain a first screen image.

[0064] FIG. 9 is a hardware configuration diagram of a screen breakage recognition device of a terminal according to an exemplary embodiment.

[0065] The terminal screen breakage recognition device 900 may include a processor 901 such as a CPU, a memory 902, and a transceiver 903. Those skilled in the art can understand that the structure shown in FIG. 9 does not constitute a limitation of the terminal screen breakage recognition device, and may include more or fewer parts than those shown, combine some parts, or combine different part arrangements. The memory 902 may be realized by any type of volatile or non-volatile storage device, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, an optical disk, or a combination thereof.

[0066] The processor 901 can call the computer program stored in the memory 902 to complete all or part of the steps of the above-mentioned terminal screen damage recognition method.

[0067] The transceiver 903 is used to receive information transmitted from an external device and to transmit information to an external device.

[0068] A non-transitory computer-readable storage medium, the instructions of which, when executed by a processor of a terminal screen breakage recognition device, enable the terminal screen breakage recognition device to perform the terminal screen breakage recognition method described above.

[0069] Computer Programming In Ah hand, When this computer program is executed by a processor of the terminal screen breakage recognition device, it enables the terminal screen breakage recognition device to perform the terminal screen breakage recognition method described above.

[0070] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any modifications, uses or adaptations of the present disclosure in accordance with the general principles of the present disclosure, including common knowledge or customary technical means known in the art that are not disclosed herein. The specification and examples are to be treated as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0071] It should be understood that the present disclosure is not limited to the exact construction described above and shown in the drawings, but various modifications and variations are possible without departing from the scope of the present disclosure, which is limited only by the appended claims.

[0072] This application claims priority to a Chinese patent application filed with the China Patent Office on January 25, 2022, bearing application number 202210090385.X and title "Method for recognizing terminal screen breakage and related device," the entire contents of which are incorporated herein by reference.

Claims

1. A method for detecting damage to a screen of a terminal, comprising: acquiring a first screen image of a detection target and dividing the first screen image into a first preset number of detection target images, the first screen image including a screen of a first terminal, the first screen image being captured while a screen of the first terminal is turned on; inputting each of the target images into a recognition model to obtain a number of crack pixels for each of the target images, the recognition model being trained based on each of the second screen images in which crack pixels are marked to obtain the number of crack pixels; If the number of cracked pixels in any of the detection target images is equal to or greater than a second preset number, determining that a screen breakage has occurred on the screen of the first terminal; If the number of crack pixels in each of the detection target images is less than the second preset number, determining that no screen damage has occurred on the screen of the first terminal. A method for detecting damage to a terminal screen, comprising:

2. Dividing the first screen image into a first preset number of images to be detected includes: removing a background image in the first screen image to obtain a third screen image; and dividing the third screen image into a first preset number of images to be detected.

2. The method for detecting screen damage in a terminal according to claim 1.

3. Dividing the first screen image into a first preset number of images to be detected includes: converting the first screen image into a fourth screen image of a preset ratio, the preset ratio being an aspect ratio of an actual screen; and dividing the fourth screen image into a first preset number of images to be detected.

2. The method for detecting screen damage in a terminal according to claim 1.

4. before inputting each of the detection target images into a recognition model to obtain the number of crack pixels of each of the detection target images, acquiring each second screen image with the cracked pixels marked thereon, the second screen image including a screen of a second terminal, the second screen image being taken while the screen of the second terminal is illuminated; Dividing each of the second screen images into a first preset number of training object images; training a preset model based on each of the training object images to obtain a recognition model, and storing the recognition model; 2. The method for detecting screen damage in a terminal according to claim 1.

5. Dividing each of the second screen images into a first preset number of training object images includes: performing a preset process on each of the second screen images to obtain an image to be divided, the preset process including performing a conversion of a preset ratio on the second screen images and / or removing a background image in the second screen images; Dividing the segmentation target image into a first preset number of training target images.

5. The method for detecting damage to a terminal screen according to claim 4.

6. Obtaining a first screen image of a first terminal to be detected includes: capturing an image while the screen of the first terminal is illuminated; Extracting key points in the image to obtain each corner of the screen of the first terminal; and dividing the image based on each of the corners to obtain the first screen image.

6. The method for detecting damage to a terminal screen according to claim 1,

7. A device for detecting screen breakage of a terminal, comprising: an acquisition module used for acquiring a first screen image of a detection target and dividing the first screen image into a first preset number of images of the detection target, the first screen image including a screen of a first terminal, and the first screen image being captured while the screen of the first terminal is turned on; an input module used to input each of the target images into a recognition model to obtain the number of crack pixels of each of the target images, the recognition model being trained based on each of the second screen images in which the crack pixels are marked; and a determination module adapted to determine that a screen breakage has occurred on the screen of the first terminal when the number of crack pixels in any of the detection target images is equal to or greater than a second preset number; The determining module is further adapted to determine that no screen damage has occurred on the screen of the first terminal when the number of cracked pixels of each of the detection target images is less than the second preset number. A device for detecting damage to a terminal screen.

8. A screen breakage recognition device for a terminal including a memory and a processor, The memory stores computer executable instructions; The processor executes the computer executable instructions stored in the memory to cause the processor to execute the method for recognizing screen breakage of a terminal according to any one of claims 1 to 6. A device for recognizing screen breakage of a terminal.

9. A computer-executable instruction is stored in the memory, and when the computer-executable instruction is executed by a processor, the method for recognizing a screen breakage of a terminal according to any one of claims 1 to 6 is realized. A computer-readable storage medium comprising:

10. A computer program product including a computer program, the method for recognizing a screen breakage of a terminal according to any one of claims 1 to 6 being realized when the computer program is executed by a processor.

23. A computer program product comprising:

Images