Mobile phone hole area crack detection method and related equipment

Abstract

The invention relates to a mobile phone hole area crack detection method and related equipment. The method comprises the following steps: acquiring a hole area detection requirement of a to-be-detected mobile phone; determining a detection environment for detecting the to-be-detected mobile phone based on the hole area detection requirement; based on the detection environment, acquiring a shot image of a hole area of the to-be-detected mobile phone by using a camera; and identifying the shot image to obtain the crack defect type. The problems that in the prior art, due to the fact that human eyes are often affected by the environment, errors are large in the process that the human eyes recognize the cracks in the hole area of the mobile phone, and the detection efficiency of manual judgment and crack type determination is low are solved.

Description

Background Art

[0002] With the upgrading of mobile phones, the camera has also completed a gorgeous transformation from single camera to dual camera and then to multi-camera. The current three-camera lens includes RGB (Red, Green, Blue) color camera, Monochrome (black and white) camera and Telephoto (telephoto) camera.

[0003] You can use the combination of RGB+Mono to achieve super night scene shooting, and you can also use RGB+Tele to achieve optical zoom. The visual difference of the three lenses can also obtain the depth of field of the subject, achieving the effect of a large aperture, which is very practical. The integration of multi-functional camera technology and other image technologies can enable the mobile phone to obtain rich image information, which can further enhance the phone's low-light shooting, backlight photography, beauty, portrait lighting, high dynamic range and other functions.

[0004] Mobile phone cameras play a vital role in the development of mobile phones, so it is necessary to detect defects in the hole area of ​​mobile phones. The defects in the hole area of ​​mobile phones are mainly cracks.

[0005] In the prior art, the presence of crack defects and the type of cracks in the hole area of ​​a mobile phone are directly judged by the human eye. Since the human eye is often affected by the environment, the error generated in the process of the human eye identifying cracks in the hole area of ​​the mobile phone is large, and the detection efficiency of manual judgment and determination of crack types is low. Summary of the invention

[0006] In order to overcome the problem in the prior art that the human eye is often affected by the environment, resulting in large errors in the process of human eyes identifying cracks in the mobile phone hole area, and low detection efficiency in human judgment and determination of crack types, the present application provides a mobile phone hole area crack detection method and related equipment.

[0007] In the first aspect, in order to solve the above technical problems, the present application provides a method for detecting cracks in a mobile phone hole area, comprising:

[0008] Obtain the hole area detection requirements of the mobile phone to be tested;

[0009] Based on the hole area detection requirements, determine the detection environment for the mobile phone to be tested;

[0010] Based on the detection environment, a camera is used to obtain a photographic image of the hole area of ​​the mobile phone to be tested;

[0011] The captured images are identified to obtain the crack defect type.

[0012] Furthermore, the hole area detection requirements include the hole area crack type requirements; based on the hole area detection requirements, the detection environment for the mobile phone to be tested is determined, including:

[0013] Based on the requirements of the crack type in the hole area, determine the shooting requirements of the mobile phone to be tested; the shooting requirements include the ambient light requirements and the placement requirements of the mobile phone to be tested;

[0014] Determine ambient light information of a ring light source for testing the mobile phone to be tested based on ambient light requirements;

[0015] Determine the relative position between the hole area and the camera of the mobile phone to be tested based on the placement requirements;

[0016] The environment formed by combining the ambient light information and the relative position is used as the test environment for testing the mobile phone to be tested.

[0017] Furthermore, based on the detection environment, a camera is used to obtain a photographic image of the hole area of ​​the mobile phone to be tested, including:

[0018] Adjust the position of the camera in the testing environment and the position of the hole area of ​​the mobile phone to be tested so that the positional relationship between the hole area of ​​the mobile phone to be tested and the camera satisfies the relative position;

[0019] Adjust the operating parameters of the ring light source so that the ambient light emitted by the ring light source matches the ambient light information when the mobile phone under test is tested;

[0020] The hole area of ​​the mobile phone to be tested is photographed to obtain a photographed image.

[0021] Furthermore, the captured images are identified to obtain the crack defect types, including:

[0022] Input the captured image into a preset deep learning network to extract the size and grayscale value of the cracks in the captured image;

[0023] Based on the size and grayscale value, the crack defect type in the hole area of ​​the tested mobile phone is obtained.

[0024] In a second aspect, the present application also provides a mobile phone hole area crack detection device, which applies a mobile phone hole area crack detection method, including a mobile phone to be tested 21, a mechanical platform 22, a ring light source 23, a camera 24 and a slide 25;

[0025] The mechanical stage 22 is connected to the slide 25, the slide 25 is connected to the camera 24, and the ring light source 23 is arranged on the lens 241 of the camera 24;

[0026] The mobile phone 21 to be tested is placed on the mechanical table 22, and the hole area of ​​the mobile phone 21 to be tested is set directly below the lens 241;

[0027] Based on the mobile phone 21 to be tested, the mechanical table 22, the ring light source 23, the camera 24 and the slide table 25, a testing environment for testing the mobile phone 21 to be tested is obtained, so that the camera 24 obtains a photographed image of the hole area of ​​the mobile phone 21 to be tested based on the testing environment, and identifies the photographed image to obtain the crack defect type.

[0028] Furthermore, the distance between the lens 241 and the aperture area is 65 mm, and the distance between the ring light source 23 and the aperture area is 75 mm.

[0029] Furthermore, the camera 24 and the slide table 25 are slidably arranged.

[0030] Furthermore, the sliding range of the camera 24 relative to the slide table 25 is ±10 mm.

[0031] In a third aspect, the present application also provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, and when the processor executes the program, the steps of a method for detecting cracks in a hole area of ​​a mobile phone as described above are implemented.

[0032] In a fourth aspect, the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the steps of a method for detecting cracks in a mobile phone hole area.

[0033] The beneficial effects of the present application are: by determining the detection environment based on the hole area detection requirements of the mobile phone to be tested, and in the detection environment, using a camera to obtain a photographed image of the hole area of ​​the mobile phone to be tested, and identifying the type of crack defect in the hole area in the photographed image, the crack defect type of the hole area of ​​the mobile phone to be tested is automatically identified, the error caused by human eye recognition is avoided, and the accuracy of the detection result is improved. At the same time, compared with human eye recognition, the automatic detection scheme of the present application improves the detection efficiency of judging and determining the crack type. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of a process for detecting cracks in a hole area of ​​a mobile phone according to the present application;

[0035] Figure 2 This is a schematic structural diagram of a mobile phone hole area crack detection device according to the present application.

[0036] Attached Figure 2 The parts represented by the various reference numerals are listed as follows:

[0037] 21. Mobile phone to be tested, 22. Mechanical table, 23. Ring light source, 24. Camera, 241. Lens, 25. Slide table. DETAILED DESCRIPTION

[0038] The following examples are provided to further explain and supplement the present application and do not constitute any limitation to the present application.

[0039] A method for detecting cracks in a hole area of ​​a mobile phone and related equipment according to an embodiment of the present application will be described below in conjunction with the accompanying drawings.

[0040] A method for detecting cracks in a hole area of ​​a mobile phone is disclosed in an embodiment of the present application. The method is applied to a terminal device. In the present application scheme, the terminal device is used as the execution subject to illustrate the present application scheme. The terminal device is used to execute the steps of a method for detecting cracks in a hole area of ​​a mobile phone.

[0041] like Figure 1 As shown, the present application provides a method for detecting cracks in a mobile phone hole area, comprising:

[0042] Step S11, obtaining the hole area detection requirements of the mobile phone to be tested;

[0043] Step S12, determining a testing environment for testing the mobile phone to be tested based on the hole area detection requirements;

[0044] Step S13, based on the detection environment, using a camera to obtain a photographic image of the hole area of ​​the mobile phone to be tested;

[0045] Step S14, identifying the captured image to obtain the crack defect type.

[0046] A method for detecting cracks in the hole area of ​​a mobile phone in this embodiment determines the detection environment based on the hole area detection requirements of the mobile phone to be tested, and in the detection environment, uses a camera to obtain a photographed image of the hole area of ​​the mobile phone to be tested, identifies the type of crack defects in the hole area in the photographed image, and realizes automatic identification of the type of crack defects in the hole area of ​​the mobile phone to be tested, avoiding the errors caused by human eye recognition and improving the accuracy of the detection results. At the same time, compared with human eye recognition, the automatic detection scheme of this application improves the detection efficiency of judging and determining crack types.

[0047] Optionally, the hole area detection requirement includes a hole area crack type requirement; based on the hole area detection requirement, determining a detection environment for detecting the mobile phone to be tested includes:

[0048] Based on the requirements of the crack type in the hole area, determine the shooting requirements of the mobile phone to be tested; the shooting requirements include the ambient light requirements and the placement requirements of the mobile phone to be tested;

[0049] Determine ambient light information of a ring light source for testing the mobile phone to be tested based on ambient light requirements;

[0050] Determine the relative position between the hole area and the camera of the mobile phone to be tested based on the placement requirements;

[0051] The environment formed by combining the ambient light information and the relative position is used as the test environment for testing the mobile phone to be tested.

[0052] In this embodiment, the shooting requirements determined based on the hole area crack type requirements include the ambient light requirements and the placement requirements of the mobile phone to be tested. The ambient light information of the ring light source determined according to the ambient light requirements and the relative position of the hole area of ​​the mobile phone to be tested and the camera determined according to the placement requirements, the combined environment can meet the environmental requirements for testing the hole area of ​​the mobile phone to be tested based on the hole area crack type requirements. The combined environment is used as the detection environment for testing the mobile phone to be tested, which is convenient for the subsequent automated shooting detection of the mobile phone to be tested and improves the detection efficiency. Among them, the relative position of the hole area of ​​the mobile phone to be tested and the camera can be that the hole area of ​​the mobile phone to be tested is located directly below the camera, and the interval between the hole area of ​​the mobile phone to be tested and the camera is 65mm.

[0053] Optionally, based on the detection environment, using a camera to obtain a photographed image of the hole area of ​​the mobile phone to be tested includes:

[0054] Adjust the position of the camera in the testing environment and the position of the hole area of ​​the mobile phone to be tested so that the positional relationship between the hole area of ​​the mobile phone to be tested and the camera satisfies the relative position;

[0055] Adjust the operating parameters of the ring light source so that the ambient light emitted by the ring light source matches the ambient light information when the mobile phone under test is tested;

[0056] The hole area of ​​the mobile phone to be tested is photographed to obtain a photographed image.

[0057] In this embodiment, the position of the camera in the detection environment and the position of the hole area of ​​the mobile phone to be tested are adjusted so that the positional relationship between the hole area of ​​the mobile phone to be tested and the camera satisfies the relative position, and the operating parameters of the ring light source are adjusted so that the ambient light emitted by the ring light source matches the ambient light information when the mobile phone to be tested is tested. In this way, the mobile phone to be tested is in an environment that meets the hole area detection requirements, and the hole area of ​​the mobile phone to be tested is photographed in this environment, so that the captured image contains more effective information, which makes the recognition degree of the captured image higher, thereby improving the recognition accuracy of the crack defect type in the hole area in the captured image.

[0058] Optionally, the captured image is identified to obtain the type of crack defect, including:

[0059] Input the captured image into a preset deep learning network to extract the size and grayscale value of the cracks in the captured image;

[0060] Based on the size and grayscale value, the crack defect type in the hole area of ​​the tested mobile phone is obtained.

[0061] In this embodiment, the preset deep learning network is a model that meets the classification requirements for the accuracy of crack defect type classification after pre-training. The captured image is then feature-recognized by the preset deep learning network to determine the size and grayscale value of the crack in the hole area of ​​the captured image. The matching crack defect type can be found in the preset crack matching table through the size and the grayscale value. In this way, the preset deep learning network can not only speed up the recognition efficiency compared to manual judgment of the crack defect type, but also avoid the error caused by human eye recognition, thereby improving the accuracy of the crack defect type.

[0062] In some embodiments, the preset deep learning network is a network obtained by deep learning and training the initial deep learning network using multiple defect sample images containing the morphology of cracks in the hole area of ​​the mobile phone. During the training process, the initial deep learning network extracts the size and grayscale value of the cracks in each defect sample image, and learns the type of cracks in each defect sample image, until the obtained initial deep learning network stops training when the recognition accuracy of the defect sample image meets the classification requirements, and the initial deep learning network at this time is used as the preset deep learning network used in the method of the present application. Using the preset deep learning network to identify and classify the captured images of the mobile phone to be tested can improve the accuracy of the crack defect type in the hole area of ​​the mobile phone to be tested.

[0063] In the process of using the preset deep learning network to perform defect detection on the photographed images of the hole area of ​​the mobile phone to be tested, since the length of the crack will affect the performance of the hole area of ​​the mobile phone to varying degrees, the crack defect is detected by setting a threshold range for the area of ​​the crack according to the size (shape and size) of the existing crack. When setting the area threshold range, the maximum crack range that affects the performance of the product is used as the threshold to avoid missing crack defects. At the same time, more defect sample images are collected to enrich the sample library so that the crack defect types corresponding to the multiple defect sample images used in the training of the preset deep learning network include all defect types. The number of training times is set to the number that can meet the model accuracy requirements, so that the preset deep learning network can learn the characteristic information such as size and grayscale value contained in all crack defect types, thereby improving the classification accuracy of the preset deep learning network.

[0064] like Figure 2 As shown, the present application provides a mobile phone hole area crack detection device, which applies a mobile phone hole area crack detection method, including a mobile phone to be tested 21, a mechanical platform 22, a ring light source 23, a camera 24 and a slide 25;

[0065] The mechanical stage 22 is connected to the slide 25, the slide 25 is connected to the camera 24, and the ring light source 23 is arranged on the lens 241 of the camera 24;

[0066] The mobile phone 21 to be tested is placed on the mechanical table 22, and the hole area of ​​the mobile phone 21 to be tested is set directly below the lens 241;

[0067] Based on the mobile phone 21 to be tested, the mechanical table 22, the ring light source 23, the camera 24 and the slide table 25, a testing environment for testing the mobile phone 21 to be tested is obtained, so that the camera 24 obtains a photographed image of the hole area of ​​the mobile phone 21 to be tested based on the testing environment, and identifies the photographed image to obtain the crack defect type.

[0068] In a mobile phone hole area crack detection device of this embodiment, the hole area of ​​the mobile phone to be tested is placed on a mechanical table directly below the lens, and the operating parameters of the ring light source are adjusted so that the ambient light emitted by the ring light source matches the ambient light information when the mobile phone to be tested is tested. In this way, a detection environment for testing the mobile phone to be tested is constructed. When in use, in this detection environment, a camera is used to obtain a captured image of the hole area of ​​the mobile phone to be tested, and the captured image is identified to obtain the type of crack defect, thereby realizing automatic identification of the type of crack defect in the hole area of ​​the mobile phone to be tested, avoiding errors caused by human eye recognition, and improving the accuracy of the detection results. At the same time, compared with human eye recognition, the automatic detection scheme of this application improves the detection efficiency of judging and determining the crack type.

[0069] In some embodiments, the camera body in the present application uses a 25M area array camera body. In order to cooperate with the camera and meet the requirements of image acquisition accuracy, the lens of the present application uses a 3X telecentric optical lens with an aperture from Canrui, and the working distance of the telecentric optical lens is fixed at 65mm. Among them, the optical imaging telecentric lens is compatible with the area array camera body. The telecentric optical lens enables the edge information of the hole area of ​​the mobile phone to be tested to be imaged on the CCD (Charge-coupled Device, also known as a photosensitive element) of the area array camera body, thereby reducing the distortion of the captured image. Since different light sources can highlight different appearance defects, the selection of machine vision light sources is particularly important. Under the illumination of a suitable light source (the ring light source of the present application), an image with good uniformity and consistency can be obtained, thereby improving the recognition and detection efficiency and accuracy of the visual algorithm.

[0070] In the present application, the operating parameters of the ring light source are adjusted using a light source controller. The ambient light obtained by using the ring light source is dark field light. After the cracks in the hole area of ​​the mobile phone to be tested are illuminated by the dark field light, the amount and angle of light reflected into the camera are different from the background texture because the cracks have a certain depth, which is reflected in the captured image as a difference in brightness and contrast between the defects and the background texture. That is, dark field light can improve the contrast between the cracks in the hole area of ​​the mobile phone to be tested and the background texture of the hole area, improve the imaging effect of the captured image, and ensure the stability of the image, thereby enhancing the crack defect characteristics in the captured image and improving the stability and accuracy of subsequent feature extraction and classification in the preset deep learning network.

[0071] The ring light source is installed around the telecentric optical lens, 10mm away from the glass mirror of the telecentric optical lens, to ensure that the imaging effect of the telecentric optical lens is not affected by temperature drift and causes defocus, so that more light can enter the camera to ensure the brightness and uniformity of the captured image. In addition, 10mm is the distance at which the most light enters the camera, i.e., the image is relatively brightest, as determined by laboratory tests. It can be installed according to this value during actual installation for the best imaging effect.

[0072] The terminal device used to execute the steps of a method for detecting cracks in the hole area of ​​a mobile phone in the present application is a PLC (Programmable Logic Controller). The ring light source is logically controlled to a stroboscopic state by the light source controller, that is, the ring light source is lit at the moment the camera is triggered. The mobile phone to be tested moves to the bottom of the camera with the transmission function of the mechanical table and enters the shooting range of the camera. At this time, a trigger signal is generated and sent to the light source controller. By writing logic in the light source controller, after the light source controller receives the trigger signal sent by the PLC, a certain delay time is set, the light source is lit and a trigger signal is given to the camera. After the camera receives the trigger signal, it lights up the ring light source and shoots the hole area of ​​the mobile phone to be tested to obtain a captured image.

[0073] In this implementation, accessories such as power trigger wires and network cables are used. The power trigger wires are used to power the mechanical table, the ring light source, the terminal device, the light source controller, etc., so that the method of the present application is implemented based on the device of the present application. The network cable is used to transmit signals, and the captured images obtained by the area array camera can be transmitted to the terminal device (for example, the terminal device is a computer) in the form of image signals, and then the captured images are recognized and processed using a preset deep learning network, and the image processing results are output to obtain the crack defect type in the hole area of ​​the mobile phone to be tested.

[0074] Optionally, the distance between the lens 241 and the hole area is 65 mm, and the distance between the ring light source 23 and the hole area is 75 mm.

[0075] In this embodiment, the position of the hole area of ​​the mobile phone to be tested and the position of the camera are adjusted based on the relative position of the hole area of ​​the mobile phone to be tested and the camera in a method for detecting cracks in the hole area of ​​a mobile phone, so that the hole area of ​​the mobile phone to be tested is located directly below the lens of the camera, and the distance between the lens and the hole area is 65mm. The lens of this application uses a 3X telecentric optical lens with an aperture from Canrui, and the working distance of the telecentric optical lens is fixed at 65mm. At this time, the detection accuracy of the shooting is 1.87μm. Therefore, the distance between the lens and the hole area is set to 65mm, and the image quality of the captured image taken using this lens is high, and the clarity, brightness, contrast and color in the captured image can meet the subsequent recognition requirements. At the same time, the height position of the ring light source also has a great influence on the imaging effect, which is a necessary factor to be considered. Based on the ambient light information of the ring light source in a method for detecting cracks in the hole area of ​​a mobile phone, the height and angle of the ring light source are adjusted and fixed, so that the distance between the ring light source and the hole area is 75mm, the depth of field is ±30μm, and the hole area is located directly below the ring light source. At the same time, the operating parameters of the ring light source are adjusted so that the ambient light emitted by the ring light source matches the ambient light information when the hole area of ​​the mobile phone to be tested is tested. When collecting the photographic image of the hole area of ​​the mobile phone to be tested, the ring light source is set horizontally, so as to improve the high contrast of the crack defect in the hole area of ​​the mobile phone to be tested, so that the crack information in the collected photographic image can meet the subsequent image recognition requirements.

[0076] Optionally, the camera 24 and the slide table 25 are slidably arranged.

[0077] In this embodiment, the slide is a Z-axis slide that allows the camera to slide in the vertical direction. Through the sliding arrangement of the camera and the slide, the height of the camera can be adjusted so that the shooting height of the camera can meet the preset requirements, thereby satisfying the positional relationship corresponding to the relative position of the camera and the hole area of ​​the mobile phone to be tested, so that the focusing effect during shooting is better, thereby improving the image quality of the captured image obtained by the camera lens.

[0078] Optionally, the sliding range of the camera 24 relative to the slide table 25 is ±10 mm.

[0079] In this embodiment, the sliding range of the camera relative to the slide table is set to ±10 mm to achieve fine adjustment of the position of the camera.

[0080] Optionally, the slide table 25 and the mechanical table 22 are slidably arranged.

[0081] In this embodiment, the slide is a Z-axis slide that allows the camera to slide in the vertical direction. Through the sliding arrangement of the slide and the mechanical stage, the height of the camera connected to the slide can be adjusted so that the shooting height of the camera can meet the preset requirements, thereby satisfying the positional relationship corresponding to the relative position of the camera and the hole area of ​​the mobile phone to be tested, so that the focusing effect during shooting is better, thereby improving the image quality of the captured image obtained by the camera lens.

[0082] Optionally, the sliding range of the slide table 25 relative to the mechanical table 22 is ±10 mm.

[0083] In this embodiment, the sliding range of the slide table relative to the mechanical stage is set to ±10 mm, so as to achieve fine adjustment of the position of the camera connected to the slide table.

[0084] This application mainly involves crack defect detection in the hole area of ​​the mobile phone to be tested, and realizes high-contrast capture of crack defects in the hole area, which is conducive to good defect detection in the later stage of the algorithm, and realizes stability and reliability of crack defect detection in the hole area. At the same time, machine vision is used to automatically detect crack defects in the hole area of ​​the mobile phone, and cameras are used to replace human eyes, eliminating errors caused by human eyes, greatly improving the accuracy and work efficiency of detection, which is conducive to improving the production efficiency of the enterprise, and at the same time can ensure the detection rate of defects, effectively improving the yield of the hole area of ​​the mobile phone. Using the method and device of this application to detect crack defects in the hole area of ​​the mobile phone to be tested can achieve the following effects: (1) fast detection speed and high efficiency, reducing the time of crack detection in the hole area of ​​the mobile phone, and improving the efficiency of mobile phone production and sales; (2) strict detection, improving the profit and stability of mobile phone screen products; (3) high accuracy, which is conducive to improving the yield of the hole area of ​​mobile phone screen products; (4) wide application of detection, freeing people from the boring work of hole area crack detection.

[0085] A computing device according to an embodiment of the present application includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, some or all steps of the above-mentioned method for detecting cracks in the hole area of ​​a mobile phone are implemented.

[0086] Among them, the computing device can be a computer, and correspondingly, its program is computer software. The above-mentioned parameters and steps in a computing device of the present application can refer to the parameters and steps in an embodiment of a mobile phone hole area crack detection method mentioned above, and will not be repeated here.

[0087] In an embodiment of the present application, a computer-readable storage medium is provided, in which instructions are stored. When the instructions are executed, the steps of the above-mentioned method for detecting cracks in the hole area of ​​a mobile phone are executed.

[0088] The computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0089] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of the embodiment of the present disclosure. The aforementioned computer-readable storage medium may be a non-transitory computer-readable storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes, or a transient computer-readable storage medium.

[0090] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] Those skilled in the art know that the present application can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, generally referred to as "module" or "system" herein. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.

[0092] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0093] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting cracks in a mobile phone hole area, characterized in that: include: Obtain the hole area detection requirements of the mobile phone to be tested; Based on the hole area detection requirements, determine the detection environment for detecting the mobile phone to be tested; Based on the detection environment, using a camera to obtain a photographed image of the hole area of ​​the mobile phone to be tested; The captured image is identified to obtain the type of crack defect.

2. The method according to claim 1, characterized in that The hole area detection requirement includes a hole area crack type requirement; and determining a detection environment for detecting the mobile phone to be tested based on the hole area detection requirement includes: Based on the hole area crack type requirement, determining the shooting requirements of the mobile phone to be tested; wherein the shooting requirements include ambient light requirements and placement requirements of the mobile phone to be tested; Determine ambient light information of a ring light source for detecting the mobile phone to be tested based on the ambient light requirement; Determining the relative position of the hole area of ​​the mobile phone to be tested and the camera based on the placement requirement; The environment formed by combining the ambient light information and the relative position is used as a detection environment for detecting the mobile phone to be tested.

3. The method according to claim 2, characterized in that The method of obtaining a photographed image of the hole area of ​​the mobile phone to be tested by using a camera based on the detection environment includes: Adjusting the position of the camera in the detection environment and the position of the hole area of ​​the mobile phone to be tested so that the positional relationship between the hole area of ​​the mobile phone to be tested and the camera satisfies the relative position; Adjusting the operating parameters of the ring light source so that the ambient light emitted by the ring light source matches the ambient light information when the mobile phone to be tested is tested; The hole area of ​​the mobile phone to be tested is photographed to obtain a photographed image.

4. The method according to any one of claims 1 to 3, characterized in that: The step of identifying the captured image to obtain the type of crack defect includes: Inputting the captured image into a preset deep learning network to extract the size and grayscale value of the crack in the captured image; Based on the size and the grayscale value, the crack defect type of the hole area of ​​the mobile phone to be tested is obtained.

5. A mobile phone hole area crack detection device, using a mobile phone hole area crack detection method as claimed in any one of claims 1 to 4, characterized in that: It includes a mobile phone to be tested (21), a mechanical platform (22), a ring light source (23), a camera (24) and a slide platform (25); The mechanical platform (22) is connected to the slide platform (25), the slide platform (25) is connected to the camera (24), and the ring light source (23) is arranged on the lens (241) of the camera (24); The mobile phone to be tested (21) is placed on the mechanical platform (22), and the hole area of ​​the mobile phone to be tested (21) is arranged directly below the lens (241); Based on the mobile phone to be tested (21), the mechanical platform (22), the ring light source (23), the camera (24) and the slide table (25), a detection environment for detecting the mobile phone to be tested (21) is obtained, so that the camera (24) obtains a photographed image of the hole area of ​​the mobile phone to be tested (21) based on the detection environment, and identifies the photographed image to obtain a crack defect type.

6. The device according to claim 5, characterized in that The distance between the lens (241) and the hole area is 65 mm, and the distance between the ring light source (23) and the hole area is 75 mm.

7. The device according to claim 5 or 6, characterized in that The camera (24) and the slide table (25) are slidably arranged.

8. The device according to claim 7, characterized in that The sliding range of the camera (24) relative to the slide table (25) is ±10 mm.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a method for detecting cracks in a hole area of ​​a mobile phone as described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the steps of a method for detecting cracks in a hole area of ​​a mobile phone as described in any one of claims 1 to 4.

Images