WO2023142438A1

WO2023142438A1 - Method for recognizing broken screen of terminal, and related device

Info

Publication number: WO2023142438A1
Application number: PCT/CN2022/112581
Authority: WO
Inventors: 茅天奇; 丁拥科; 王恒
Original assignee: 众安在线财产保险股份有限公司
Priority date: 2022-01-25
Filing date: 2022-08-15
Publication date: 2023-08-03
Also published as: CN114429464A

Abstract

The present invention provides a method for recognizing a broken screen of a terminal, and a related device. The method comprises: acquiring a first screen picture to be detected, and segmenting the first screen picture into a first preset number of pictures to be detected; inputting each picture to be detected into a recognition model to obtain the number of crack pixels of each picture to be detected, wherein the recognition model is obtained by training according to each second screen picture marked with the crack pixels; determining that a screen of a first terminal is broken when the number of crack pixels of any picture to be detected is greater than or equal to a second preset number; and determining that the screen of the first terminal is not broken when the number of crack pixels of each picture to be detected is less than the second preset number. In the present invention, the recognition model is obtained by training according to each second screen picture marked with the crack pixels, so that the recognition model can accurately recognize cracks of a screen on the basis of the current screen picture of the terminal, thereby improving the accuracy of terminal broken screen recognition.

Description

Terminal broken screen identification method and related equipment

This application claims the priority of the Chinese patent application with the application number 202210090385.X and the application title "Broken Screen Identification Method of Terminal and Related Equipment" filed with the China Patent Office on January 25, 2022, the entire contents of which are incorporated by reference in this application.

technical field

The present invention relates to the technical field of image recognition, in particular to a terminal broken screen recognition method and related equipment.

Background technique

With the development and popularization of smart terminals, the broken screen insurance business of terminals has been derived. The broken screen insurance business refers to the insurance business in which the screen of the terminal is accidentally damaged and can be compensated or the screen replaced.

At present, the damage of the screen of the terminal is manually checked and identified through the screen picture taken by the user. However, the cracks on the screen may be extremely subtle, and the screen pictures taken by users cannot show the cracks on the screen.

It can be seen that the accuracy of terminal broken screen recognition is low.

Contents of the invention

The invention provides a terminal broken screen identification method and related equipment, which are used to solve the problem of low accuracy of terminal broken screen identification.

In one aspect, the present invention provides a method for identifying a broken screen of a terminal, including:

Acquiring a first screen picture to be detected, and dividing the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the first screen picture is taken when the screen of the first terminal is on;

Inputting each of the pictures to be detected into a recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is trained according to each second screen picture marked with crack pixels;

When the number of cracked pixels in any of the pictures to be detected is greater than or equal to a second preset number, it is determined that the screen of the first terminal is broken;

When the number of cracked pixels in each picture to be detected is less than the second preset number, it is determined that the screen of the first terminal is not broken.

In one embodiment, the step of dividing the first screen picture into a first preset number of pictures to be detected includes:

removing the background image in the first screen image to obtain a third screen image;

Segmenting the third screen picture into a first preset number of pictures to be detected.

converting the first screen picture into a fourth screen picture with a preset ratio, wherein the preset ratio is an aspect ratio of an actual screen;

Segmenting the fourth screen picture into a first preset number of pictures to be detected.

In one embodiment, before the step of inputting each of the pictures to be detected to the recognition model to obtain the number of crack pixels in each picture to be detected, it also includes:

Acquiring each second screen picture marked with cracked pixels, the second screen picture includes the screen of the second terminal, and the second screen picture is taken when the screen of the second terminal is turned on;

dividing each of the second screen pictures into a first preset number of pictures to be trained;

A recognition model is obtained by training a preset model according to each of the pictures to be trained, and saving the recognition model.

In one embodiment, the step of dividing each second screen picture into a first preset number of pictures to be trained includes:

Perform preset processing on each of the second screen pictures to obtain the picture to be divided, and the preset processing includes converting the second screen picture to a preset ratio and/or removing Background screen;

The picture to be divided is divided into a first preset number of pictures to be trained.

In one embodiment, the step of acquiring the first screen picture of the first terminal to be detected includes:

acquiring an image when the screen of the first terminal is turned on;

performing key point extraction in the image to obtain each corner point of the screen of the first terminal;

Segmenting the image according to each of the corner points to obtain the first screen picture.

On the other hand, the present invention also provides a device for identifying a broken screen of a terminal, including:

An acquisition module, configured to acquire a first screen picture to be detected, and divide the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the The first screen picture is taken when the screen of the first terminal is on;

An input module, configured to input each of the pictures to be detected into a recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is trained according to each second screen picture marked with crack pixels ;

A determining module, configured to determine that the screen of the first terminal is broken when the number of cracked pixels in any of the pictures to be detected is greater than or equal to a second preset number;

The determining module is further configured to determine that the screen of the first terminal is not broken when the number of cracked pixels in each of the pictures to be detected is less than the second preset number.

On the other hand, the present invention also provides a device for identifying a broken screen of 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, so that the processor executes the method for identifying a broken screen of a terminal as described above.

On the other hand, the present invention also provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to realize the above-mentioned terminal fragmentation. screen recognition method.

On the other hand, the present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for identifying a broken screen of a terminal as described above is implemented.

The terminal broken screen identification method and related equipment provided by the present invention obtain the first screen picture of the terminal to be detected, and divide the first screen picture into a first preset number of pictures to be detected, and input each picture to be detected Until the recognition model obtains the cracked pixels of each picture to be detected, when the number of cracked pixels in any picture to be detected is greater than the second preset number, it is determined that the screen of the terminal is broken. If the number of cracked pixels in each picture to be detected is If the number is less than the second preset number, it is determined that the screen of the terminal is not broken. In the present invention, the recognition model is trained according to the second screen picture marked with cracked pixels, so that the recognition model can accurately identify the crack of the screen based on the current screen picture of the terminal, improving the accuracy of terminal broken screen recognition.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

FIG. 1 is a schematic diagram of a scene of a method for identifying a broken screen of a terminal according to the present invention;

FIG. 2 is a schematic flowchart of a first embodiment of a method for identifying a broken screen of a terminal according to the present invention;

FIG. 3 is a schematic diagram of a detailed flow chart of step S10 in the second embodiment of the terminal broken screen identification method of the present invention;

FIG. 4 is a schematic diagram of a detailed flow chart of step S10 in the third embodiment of the terminal broken screen identification method of the present invention;

FIG. 5 is a schematic flowchart of a fourth embodiment of a method for identifying a broken screen of a terminal according to the present invention;

Fig. 6 is a schematic diagram of a screen picture marked with cracked pixels involved in the present invention;

FIG. 7 is a schematic diagram of a detailed flowchart of step S10 in the fifth embodiment of the method for identifying a broken screen of a terminal according to the present invention;

FIG. 8 is a block diagram of a device for identifying a broken screen of a terminal according to the present invention;

FIG. 9 is a schematic diagram of a hardware structure of a device for identifying a broken screen of a terminal according to the present invention.

By means of the above-mentioned drawings, certain embodiments of the present disclosure have been shown and will be described in more detail hereinafter. These drawings and written description are not intended to limit the scope of the disclosed concept in any way, but to illustrate the disclosed concept for those skilled in the art by referring to specific embodiments.

Detailed ways

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

The invention provides a broken screen identification method of a terminal. Referring to Figure 1, the screen picture is taken by turning on the screen of the mobile phone. The screen picture shows that there are cracks in two areas of the mobile phone, specifically the cracked area of the screen picture. The screen picture is input into the terminal device as the picture to be detected of the mobile phone. The terminal device may be any device capable of data processing, for example, the terminal device may be a computer. The recognition model recognizes the picture to be detected, so that the number of cracked pixels on the screen of the mobile phone can be output, and the terminal device can output a prompt message that the screen of the mobile phone is broken or not broken based on the number and the preset number. For example, if the number of cracked pixels is greater than the preset number, the terminal device outputs a prompt message that the screen of the mobile phone is broken; if the number of cracked pixels is less than or equal to the preset number, the terminal device outputs a prompt message that the screen of the mobile phone is not broken.

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 below with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Referring to FIG. 2, FIG. 2 is a first embodiment of a method for identifying a broken screen of a terminal according to the present invention. The method for identifying a broken screen of a terminal includes the following steps:

Step S10, acquire the first screen picture to be detected, and divide the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the first screen picture is the Taken when the screen of a terminal is on.

In this embodiment, the execution subject is a device for identifying a broken screen of a terminal. For convenience of description, the device is used below to refer to a device for identifying a level of a terminal. The device may be any terminal device capable of data processing, for example, the device may be a computer, notebook or mobile phone.

The device acquires the first screen picture to be detected. The first screen picture includes a screen of a terminal, and a terminal is defined as a first terminal, which may be a mobile terminal such as a mobile phone or a tablet. The first screen picture is taken when the screen of the first terminal is turned on, that is, the first screen picture includes the lighted screen of the first terminal, so that it is easier to identify whether the screen of the first terminal is lit based on the lighted screen. There are cracks.

Further, the device will divide the picture on the first screen into a first preset number of pictures to be detected. The first preset number may be any suitable value, for example, the first preset number may be 8. In addition, each picture to be detected is preferably a square picture with the same size, that is, the picture on the first screen is equally divided into a first preset number of pictures to be detected.

Step S20, input each picture to be detected into the recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is obtained by training according to each second screen picture marked with crack pixels.

A recognition model is stored in the device. The recognition model was trained on individual second-screen images annotated with cracked pixels. The second screen picture includes the screen of the second terminal, and the second screen picture is taken when the screen of the second terminal is turned on. Ripped pixels are those pixels in the second screen picture where the cracks are located.

The device inputs each picture to be detected into the recognition model. The identification model identifies each picture to be detected, thereby outputting the number of crack pixels in each picture to be detected.

In step S30, when the number of cracked pixels in any picture to be detected is greater than or equal to a second preset number, it is determined that the screen of the first terminal is broken.

Cracks are generally concentrated in a certain area of the screen, and the total number of pixels on the entire screen is relatively large. The ratio of the crack pixels corresponding to the cracks to the total number is relatively small, which makes the device misjudge that the screen of the first terminal is not broken. . Therefore, the device divides the picture on the first screen, and sets the total number of pixels in the picture to be detected as the second preset number setting, thereby increasing the proportion of the number of cracked pixels to reasonably determine whether cracks occur on the screen of the first terminal. Broken screen, that is, to avoid misjudgment of the device.

When the device determines that the number of cracked pixels in any picture to be detected is greater than or equal to a second preset number, it determines that the screen of the first terminal is cracked with sound.

Step S40, when the number of cracked pixels in each picture to be detected is less than a second preset number, it is determined that the screen of the first terminal is not broken.

When the device detects that the number of cracked pixels in each picture to be detected is less than the second preset number, it can determine that the screen of the first terminal is not broken.

In the technical solution provided in this embodiment, the first screen picture of the terminal to be detected is obtained, and the first screen picture is divided into a first preset number of pictures to be detected, and each picture to be detected is input into the recognition model to obtain For the crack pixels of each picture to be detected, when the number of crack pixels of any picture to be detected is greater than the second preset number, it is determined that the screen of the terminal is broken. If the number of crack pixels of each picture to be detected is less than the second preset number Set the number and make sure that the screen of the terminal is not broken. In the present invention, the recognition model is trained according to the second screen picture marked with cracked pixels, so that the recognition model can accurately identify the crack of the screen based on the current screen picture of the terminal, improving the accuracy of terminal broken screen recognition.

Referring to FIG. 3 , FIG. 3 is a second embodiment of a method for identifying a broken screen of a terminal according to the present invention. Based on the first embodiment, step S10 includes:

Step S11 , removing the background image in the first screen image to obtain a third screen image.

Step S12, dividing the picture on the third screen into a first preset number of pictures to be detected.

In this embodiment, the first screen picture is taken when the screen of the first terminal is turned on. Therefore, the first screen image includes content displayed on the screen, and the displayed content may cover the crack on the screen or make the crack difficult to be identified.

For this, after obtaining the first screen picture, the device removes the background picture in the first screen to obtain the third screen picture, that is, the third screen picture is a pure color picture, for example, a white field picture.

The device then divides the third screen picture into a first preset number of pictures to be detected, so that the device can more clearly identify whether the screen of the terminal is broken.

In the technical solution provided in this embodiment, the device removes the background picture in the first screen picture to obtain the third screen picture, and then divides the third screen picture into a first preset number of pictures to be detected, avoiding the first screen The background picture of the screen in the picture affects the recognition accuracy of the recognition model.

Referring to FIG. 4 , FIG. 4 is a third embodiment of a method for identifying a broken screen of a terminal according to the present invention. Based on the first or second embodiment, step S10 includes:

Step S13, converting the first screen picture into a fourth screen picture with a preset ratio, wherein the preset ratio is an aspect ratio of an actual screen.

Step S14, dividing the picture on the fourth screen into a first preset number of pictures to be detected.

In this embodiment, the device converts the first screen into a picture on the fourth screen with a preset ratio. The default ratio is the aspect ratio of the actual screen. Specifically, the aspect ratio of the mobile phone screen is generally 2:1. If the first screen picture includes the mobile phone screen, the device converts the first screen picture into a 2:1 fourth screen picture.

The device divides the picture on the fourth screen to obtain a first preset number of pictures to be detected. For example, the picture on the fourth screen is evenly divided into 2×4 to obtain eight pictures to be detected.

In the technical solution provided by this embodiment, the device converts the first screen picture into a fourth screen picture with a preset ratio, and then divides the fourth screen picture into a first preset number of pictures to be detected, that is, according to the first The actual aspect ratio of the screen of a terminal processes pictures, and normalizes the pictures to be recognized, so as to unify the recognition standard of whether the screen is broken or not.

Referring to Fig. 5, Fig. 5 is a fourth embodiment of the terminal broken screen identification method of the present invention, based on any one of the first to third embodiments, before step S20, it also includes:

Step S50 , acquiring each second screen picture with pixels marked with cracks, the second screen picture includes the screen of the second terminal, and the second screen picture is taken when the screen of the second terminal is turned on.

In this embodiment, the device needs to be trained to obtain a recognition model. Specifically, the device selects pictures of mobile phones of various models uploaded by the user from the database, and the mobile phone is the second terminal, and the second screen picture can be obtained based on each picture. The second screen picture includes the screen of the second terminal, and the second screen is taken when the screen of the second terminal is turned on. Each second screen image is tagged with cold pixels. Referring specifically to FIG. 6 , FIG. 6 is an annotated second screen picture, that is, the white lines in the second screen picture are composed of crack pixels on the screen.

Step S60, dividing each second screen picture into a first preset number of pictures to be trained.

The device divides each second-screen picture into a first preset number of pictures to be trained. The method of cutting the second-screen picture is the same as that of the first-screen picture, and will not be described again.

Step S70, train the preset model according to each picture to be trained to obtain a recognition model, and save the recognition model.

The device trains the preset model based on each picture to be trained to obtain the recognition model, and then saves the recognition model.

It should be noted that after the device obtains the second screen picture, it performs preset processing on the second screen picture to obtain the picture to be divided. The preset processing includes converting the second screen picture to a preset ratio and/or removing the second screen picture. The background picture in the screen picture. The conversion of the preset ratio of the second screen picture is the same as that of the first screen picture, and the removal of the background picture in the second screen picture is the same as the removal of the background picture in the first screen picture. Refer to the above description for details. No more details.

In the technical solution provided in this embodiment, the device acquires each second screen picture marked with cracked pixels, and divides each second screen picture into a first preset number of pictures to be trained, so that each picture to be trained The recognition model is obtained by training the preset model, and then based on the recognition model, it is accurately recognized whether the screen of the terminal is broken.

Referring to FIG. 7 , FIG. 7 is a fifth embodiment of a method for identifying a broken screen of a terminal according to the present invention. Based on any one of the first to third embodiments, step S10 includes:

Step S15, acquiring an image when the screen of the first terminal is turned on;

Step S16, extracting key points in the image to obtain each corner point of the screen of the first terminal;

Step S17, segmenting the image according to each corner point to obtain the first screen picture.

In this embodiment, when identifying a broken screen of the terminal, different gestures of the terminal will affect the accuracy of identifying the broken screen of the terminal. For this, the device may extract a picture including only the screen of the terminal from the image.

Specifically, the device first acquires an image when the screen of the first terminal is turned on, and the image is uploaded by the user. The device uses a key point extraction model to extract key points from the image to obtain each corner point of the screen of the first terminal in the image. The key point extraction model marks the positions of the four intersections of the extension lines of the four sides of the mobile phone frame 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.

The device can obtain the first screen picture by segmenting the image based on each corner point, that is, the device uses the picture containing only the screen to identify the broken screen.

In the technical solution provided by this embodiment, the device obtains the image when the screen of the first terminal is turned on, and determines each corner point of the screen from the image, so as to segment the first screen picture from the image according to each corner point, avoiding The posture of the terminal affects the accuracy of broken screen recognition.

The present invention also provides a device for identifying a broken screen of a terminal. Referring to FIG. 8 , the device for identifying a broken screen of a terminal 800 includes:

The acquisition module 810 is configured to acquire a first screen picture to be detected, and divide the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the first screen picture was taken when the screen of the first terminal was lit;

The input module 820 is used to input each picture to be detected into the recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is obtained by training according to each second screen picture marked with crack pixels;

A determining module 830, configured to determine that the screen of the first terminal is broken when the number of cracked pixels in any picture to be detected is greater than or equal to a second preset number;

The determination module 830 is configured to determine that the screen of the first terminal is not broken when the number of cracked pixels in each picture to be detected is less than a second preset number.

In an embodiment, the device 800 for identifying a broken screen of a terminal includes:

A processing module, configured to remove the background picture in the first screen picture to obtain the third screen picture;

The segmentation module is used to segment the picture on the third screen into a first preset number of pictures to be detected.

A conversion module, configured to convert the first screen picture into a fourth screen picture with a preset ratio, wherein the preset ratio is the aspect ratio of the actual screen;

A segmentation module, configured to segment the fourth screen picture into a first preset number of pictures to be detected.

The acquiring module 810 is configured to acquire each second screen picture marked with cracked pixels, the second screen picture includes the screen of the second terminal, and the second screen picture is taken when the screen of the second terminal is on;

A segmentation module, configured to segment each second screen image into a first preset number of images to be trained;

The training module is used to train the preset model according to each picture to be trained to obtain the recognition model, and save the recognition model.

The processing module is used to perform preset processing on each second screen picture to obtain the picture to be divided, and the preset processing includes converting the second screen picture to a preset ratio and/or removing the background picture in the second screen picture;

The segmentation module is used to segment the image to be segmented into a first preset number of images to be trained.

An acquisition module 810, configured to acquire an image when the screen of the first terminal is turned on;

An extraction module, configured to extract key points in the image to obtain each corner of the screen of the first terminal;

The segmentation module is configured to segment the image according to each corner point to obtain the first screen image.

Fig. 9 is a hardware structural diagram of a device for identifying a broken screen of a terminal according to an exemplary embodiment.

The device 900 for identifying a broken screen of a terminal 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 on the broken screen recognition device of the terminal, and may include more or less components than those shown in the figure, or combine certain components, or different components. layout. The memory 902 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

The processor 901 may invoke a computer program stored in the memory 902 to complete all or part of the steps of the above-mentioned method for identifying a broken screen of a terminal.

The transceiver 903 is used for receiving information sent by the external device and sending information to the external device.

A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the broken screen recognition device of the terminal, the broken screen recognition device of the terminal can execute the above broken screen recognition method of the terminal.

A computer program product, including a computer program, when the computer program is executed by a processor of the broken screen recognition device of the terminal, the broken screen recognition device of the terminal can execute the above broken screen recognition method of the terminal.

Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and examples are to be considered exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

A method for identifying a broken screen of a terminal, comprising:

Acquiring a first screen picture to be detected, and dividing the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the first screen picture is taken when the screen of the first terminal is on;

Inputting each of the pictures to be detected into a recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is trained according to each second screen picture marked with crack pixels;

When the number of cracked pixels in any of the pictures to be detected is greater than or equal to a second preset number, it is determined that the screen of the first terminal is broken;

When the number of cracked pixels in each picture to be detected is less than the second preset number, it is determined that the screen of the first terminal is not broken.
The method for identifying a broken screen of a terminal according to claim 1, wherein the step of dividing the first screen picture into a first preset number of pictures to be detected comprises:

removing the background image in the first screen image to obtain a third screen image;

Segmenting the third screen picture into a first preset number of pictures to be detected.
The method for identifying a broken screen of a terminal according to claim 1, wherein the step of dividing the first screen picture into a first preset number of pictures to be detected comprises:

converting the first screen picture into a fourth screen picture with a preset ratio, wherein the preset ratio is an aspect ratio of an actual screen;

Segmenting the fourth screen picture into a first preset number of pictures to be detected.
The method for identifying a broken screen of a terminal according to claim 1, wherein before the step of inputting each of the pictures to be detected to the recognition model to obtain the number of crack pixels of each picture to be detected, further comprising:

Acquiring each second screen picture marked with cracked pixels, the second screen picture includes the screen of the second terminal, and the second screen picture is taken when the screen of the second terminal is turned on;

dividing each of the second screen pictures into a first preset number of pictures to be trained;

A recognition model is obtained by training a preset model according to each of the pictures to be trained, and saving the recognition model.
The terminal broken screen recognition method according to claim 4, wherein the step of dividing each of the second screen pictures into a first preset number of pictures to be trained comprises:

Perform preset processing on each of the second screen pictures to obtain the picture to be divided, and the preset processing includes converting the second screen picture to a preset ratio and/or removing Background screen;

The picture to be divided is divided into a first preset number of pictures to be trained.
The method for identifying a broken screen of a terminal according to any one of claims 1-5, wherein the step of acquiring the first screen picture of the first terminal to be detected comprises:

acquiring an image when the screen of the first terminal is turned on;

performing key point extraction in the image to obtain each corner point of the screen of the first terminal;

Segmenting the image according to each of the corner points to obtain the first screen picture.
A device for identifying a broken screen of a terminal, characterized in that it comprises:

An acquisition module, configured to acquire a first screen picture to be detected, and divide the first screen picture into a first preset number of pictures to be detected, the first screen picture includes the screen of the first terminal, and the The first screen picture is taken when the screen of the first terminal is on;

An input module, configured to input each of the pictures to be detected into a recognition model to obtain the number of crack pixels in each picture to be detected, wherein the recognition model is trained according to each second screen picture marked with crack pixels ;

A determining module, configured to determine that the screen of the first terminal is broken when the number of cracked pixels in any of the pictures to be detected is greater than or equal to a second preset number;

The determining module is further configured to determine that the screen of the first terminal is not broken when the number of cracked pixels in each of the pictures to be detected is less than the second preset number.
A device for identifying a broken screen of a terminal, comprising: a memory and a processor;

the memory stores computer-executable instructions;

The processor executes the computer-executed instructions stored in the memory, so that the processor executes the method for identifying a broken screen of a terminal according to any one of claims 1 to 6.
A computer-readable storage medium, characterized in that computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement any one of claims 1 to 6. The broken screen identification method of the terminal.
A computer program product, comprising a computer program, characterized in that, when the computer program is executed by a processor, the method for identifying a broken screen of a terminal according to any one of claims 1 to 6 is implemented.