Image processing method and electronic device

Abstract

The present application relates to an image processing method and an electronic device. After acquiring a first image of a target object photographed with a first shooting parameter, once it is determined that there is at least one pixel in at least a partial image area of ​​the first image that does not satisfy a preset pixel parameter condition, the shooting parameter is updated, and an updated image of at least a partial area of ​​the target object photographed with the updated shooting parameter is acquired. Thereafter, a target image is further generated based on the above-mentioned first image and the updated image, as well as a set of pixels to be processed consisting of the above-mentioned pixels that do not satisfy the preset pixel parameter conditions.

Description

Technical Field

[0001] The present application belongs to the technical field of information collection and processing, and in particular, relates to an image processing method and electronic equipment. Background Art

[0002] 3C products are a general term for computer, communication and consumer electronic products. In the manufacturing of 3C products, it is usually necessary to perform screen defect detection on the product's display, such as LCD (Liquid Crystal Display) defect detection, to ensure product quality. In traditional 3C product manufacturing, when performing screen defect detection on the display, problems such as the defect details cannot be captured or are not obvious in the photos often occur, which leads to algorithm misjudgment or wrong judgment. Summary of the invention

[0003] To this end, this application discloses the following technical solutions:

[0004] An image processing method, comprising:

[0005] Acquire a first image of a target object captured using first capturing parameters;

[0006] Determining that at least one pixel that does not satisfy a preset pixel parameter condition exists in at least a partial image area of ​​the first image, and obtaining a pixel set to be processed;

[0007] Determine an updated shooting parameter, and obtain an updated image of at least a partial area of ​​the target object shot with the updated shooting parameter; the at least partial area at least includes a set of points corresponding to the pixel set to be processed on the target object;

[0008] A target image is generated according to the first image, the updated image and the set of pixels to be processed.

[0009] Optionally, determining that there is at least one pixel that does not satisfy a preset pixel parameter condition in at least a partial image area of ​​the first image to obtain a pixel set to be processed includes:

[0010] Determine at least one pixel in at least a partial image area of ​​the first image whose pixel grayscale value and / or brightness value is not within a predetermined value interval, and obtain the pixel set to be processed.

[0011] Optionally, determining an updated shooting parameter and acquiring an updated image of at least a partial area of ​​the target object shot with the updated shooting parameter includes:

[0012] If the pixel set to be processed includes a first pixel whose pixel parameter value is greater than an upper threshold of the predetermined value interval, determining a second shooting parameter, and acquiring a second image of a first point set shot with the second shooting parameter; the first point set at least includes a set of points corresponding to each first pixel on the target object;

[0013] If the pixel set to be processed includes a second pixel whose pixel parameter value is less than the lower threshold of the predetermined value interval, determine a third shooting parameter, and obtain a third image of a second point set shot with the third shooting parameter; the second point set at least includes a set of points corresponding to each second pixel on the target object;

[0014] The parameter types of the second shooting parameter and the third shooting parameter are the same as the parameter type of the first shooting parameter, the second shooting parameter can reduce the exposure degree of the object compared with the first shooting parameter, and the third shooting parameter can increase the exposure degree of the object compared with the first shooting parameter;

[0015] Generating a target image according to the first image, the updated image and the set of pixels to be processed comprises:

[0016] A target image is generated according to the first image, the second image and / or the third image, and the pixel set to be processed.

[0017] Optionally, determining the second shooting parameter includes:

[0018] Determine a shooting parameter that matches the pixel parameter value of the first pixel from a target shooting parameter set to obtain the second shooting parameter;

[0019] The determining of the third shooting parameter includes:

[0020] Determine a shooting parameter that matches the pixel parameter value of the second pixel from the target shooting parameter set to obtain the third shooting parameter;

[0021] The target shooting parameter set also includes the first shooting parameter.

[0022] Optionally, generating a target image according to the first image, the second image and / or the third image, and the pixel set to be processed includes:

[0023] According to the position information of the first pixel and / or the second pixel included in the pixel set to be processed, the first image and the second image and / or the third image are fused to obtain a target image.

[0024] Optionally, the target object is a display screen;

[0025] Before acquiring the first image of the target object photographed with the first photographing parameter, the method further includes:

[0026] Acquire the configuration information of the target object, and acquire a shooting parameter set matching the configuration information of the target object, to obtain the target shooting parameter set; different objects with different configuration information correspond to different shooting parameter sets respectively;

[0027] The first shooting parameter is acquired from the target shooting parameter set, and the target object is photographed with the first shooting parameter.

[0028] Optionally, before determining whether there is at least one pixel whose display parameter does not satisfy the parameter condition in at least a partial image area of ​​the first image, the method further includes:

[0029] Performing image segmentation processing on the first image to obtain an image region corresponding to the target object in the first image, so as to process the image region corresponding to the target object.

[0030] Optionally, the predetermined value interval is [30, 230].

[0031] Optionally, after generating and outputting the target image, the method further includes:

[0032] Defect recognition processing is performed on the target image to identify defects existing in the target object.

[0033] In one aspect of the present application, an electronic device is also provided, comprising:

[0034] Image acquisition device;

[0035] A memory for storing at least one set of instructions;

[0036] A processor is used to implement the image processing method as described in any one of the above by running the instruction set in the memory.

[0037] It can be seen from the above scheme that the image processing method and electronic device provided by the present application, after obtaining a first image of the target object shot with a first shooting parameter, once it is determined that there is at least one pixel in at least a partial image area of ​​the first image that does not meet the preset pixel parameter conditions, then determine to update the shooting parameters, and obtain an updated image of at least a partial area of ​​the target object shot with the updated shooting parameters, and then further generate the target image based on the above-mentioned first image and updated image, as well as the set of pixels to be processed consisting of the above-mentioned pixels that do not meet the preset pixel parameter conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0039] Figure 1 is a processing flow chart of the image processing method provided by the present application;

[0040] Figure 2 is a screen image of a certain display captured based on the first capturing parameter provided by the present application;

[0041] Figure 3 This application provides Figure 2 There are overexposed pixel areas in the image;

[0042] Figure 4 This application provides Figure 2 There are underexposed pixel areas in the image;

[0043] Figure 5 is another processing flow chart of the image processing method provided by the present application;

[0044] Figure 6 is another processing flow chart of the image processing method provided by the present application;

[0045] Figure 7 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] In order to overcome the problem that in traditional 3C product manufacturing, when performing screen defect detection on displays, defect details often cannot be captured or are not obvious in the capture, which in turn leads to algorithm misjudgment or wrong judgment, the embodiments of the present application disclose an image processing method and an electronic device.

[0048] The image processing method disclosed in the present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor devices, and distributed computing environments including any of the above devices or equipment.

[0049] The processing flow of the image processing method is as follows Figure 1 As shown, specifically including:

[0050] Step 101: Acquire a first image of a target object captured using first shooting parameters.

[0051] The target object may be, but is not limited to, a display screen of a display to be inspected for screen defects, such as an LCD screen of a terminal device such as a notebook or a mobile phone, or an LED (light-emitting diode) screen.

[0052] The shooting parameters in the embodiments of the present application, such as the first shooting parameter and the second shooting parameter and the third shooting parameter mentioned below, refer to the parameters in the camera parameters that are related to the exposure effect / exposure performance, including the exposure time, sensitivity and other parameters. In addition, they may also include the aperture size, shutter speed, Gamma (also called grayscale coefficient) and / or Gain (camera gain) and other parameters.

[0053] Among them, the first shooting parameter is the regular parameter value of the above parameter type (such as exposure time, etc.) when taking a picture of the screen of the display during screen defect detection. For example, the parameter value is the system default configuration or is set by the technician based on experience, which can be generally applicable to most display screens to be inspected in the screen defect detection scenario, so that most display screens to be inspected can have a relatively ideal exposure effect.

[0054] In an embodiment of the present application, for a target object to be inspected, an image of the target object is initially captured with a first shooting parameter, and a first image of the target object captured with the first shooting parameter is obtained. For example, for a display screen to be inspected for screen defects, a screen image of the display screen captured with conventional exposure parameters is initially obtained.

[0055] Preferably, the image is captured when the display screen is on.

[0056] Step 102: Determine whether there is at least one pixel that does not meet a preset pixel parameter condition in at least a partial image area of ​​the first image, and obtain a pixel set to be processed.

[0057] In the embodiment of the present application, the above-mentioned preset pixel parameter condition is set as follows: the grayscale value and / or brightness value of the pixel is within a predetermined value range.

[0058] The above-mentioned predetermined value interval is specifically a conventional pixel grayscale / brightness value interval set based on underexposure / overexposure relative reference benchmark matching.

[0059] Among them, the reference benchmark for underexposure (i.e., insufficient exposure, specifically manifested as an image that is too dark) is: the image grayscale / brightness is lower than the set lower threshold; the reference benchmark for overexposure (i.e., overexposure, specifically manifested as an image that is too bright) is: the image grayscale / brightness is higher than the set upper threshold, and the above lower threshold is less than the upper threshold, then the above predetermined value interval is [lower threshold, upper threshold].

[0060] Exemplarily, the predetermined value interval may be set to, but is not limited to, [0, 250], or [30, 230], etc.

[0061] This step specifically determines whether there is at least one pixel whose pixel parameter value is not in the above-mentioned predetermined value range in at least a part of the image area of ​​the first image, wherein, if there is a first pixel whose pixel parameter value is greater than the upper threshold of the above-mentioned predetermined value range, and / or there is a second pixel whose pixel parameter value is less than the lower threshold of the above-mentioned predetermined value range, then the first pixel and / or the second pixel is the overexposed or underexposed pixel in the first image. In this embodiment, the pixel set composed of these overexposed / underexposed pixels is determined as the pixel set to be processed, and subsequently, the main purpose will be to improve the exposure performance of this part of pixels in the first image.

[0062] On the contrary, if there are no pixels whose pixel parameter values ​​are not within the above-mentioned predetermined value range, the defect detection of the target object such as the screen of the display screen can be directly performed based on the first image.

[0063] Step 103: determine updated shooting parameters, and obtain an updated image of at least a partial area of ​​the target object shot with the updated shooting parameters; the at least partial area at least includes a set of points corresponding to the pixel set to be processed on the target object.

[0064] Conventional image grayscale / brightness calculations usually use an average-based calculation method, that is, the average grayscale / brightness of each pixel in a certain area of ​​the image is used as the pixel grayscale / brightness value of the area. However, in the field of display AOI (Automated Optical Inspection), defects are usually very subtle, and taking an average value is likely to average out some bright spots and dark spots, which is not conducive to defect detection.

[0065] In view of this feature, the present application calculates and determines the grayscale / brightness of pixels in units of pixels, and extracts pixels that are not in the set value range. For pixels that are not in the predetermined value range, such as [30, 230], the shooting parameters are adjusted, and the image is re-shot based on the updated shooting parameters obtained after the adjustment so that the grayscale / brightness is within the set value range.

[0066] The embodiment of the present application predetermines specific N groups of shooting parameters corresponding to different exposure performances of the object to be detected (e.g., the corresponding model of the display). By way of example, for the model of the display to be detected, three groups of exposure shooting parameters, low, medium, and high, are determined. For a series of overexposed pixels, they are all adjusted to be uniformly re-shot using the low exposure shooting parameters, and for a series of underexposed pixels, they are all adjusted to be uniformly re-shot using the high exposure shooting parameters.

[0067] Among them, the medium exposure shooting parameter refers to the first shooting parameter mentioned above, that is, the shooting parameter under normal exposure conditions. The high exposure shooting parameter and the low exposure shooting parameter are shooting parameters relative to the normal exposure conditions, and are consistent with the parameter type of the medium exposure shooting parameter. However, compared with the medium exposure shooting parameter (that is, the first shooting parameter), the low exposure shooting parameter can reduce the exposure level of the object being photographed, and compared with the medium exposure shooting parameter, the high exposure shooting parameter can increase the exposure level of the object being photographed.

[0068] On this basis, if the pixel set to be processed includes a first pixel whose pixel parameter value, such as pixel grayscale value / brightness value, is greater than the upper threshold of the above-mentioned predetermined value range, the second shooting parameter is determined, and a second image of the first point set shot with the second shooting parameter is obtained; the first point set includes at least a set of points corresponding to each first pixel on the target object.

[0069] Specifically, the above-mentioned low exposure shooting parameter can be determined as the second shooting parameter. If the pixel grayscale value / brightness value is greater than the upper threshold of the predetermined value interval, it indicates that the pixel is overexposed. In this case, by reducing the exposure of the point set corresponding to this part of pixels on the target object, its details can be better captured.

[0070] Among them, acquiring a second image of a first point set captured with a second shooting parameter may refer to acquiring an overall image of the target object captured with the second shooting parameter, or only acquiring an image of a point set corresponding to each first pixel captured with the second shooting parameter on the target object. For example, in a case where the pixel set to be processed includes a series of first pixels whose grayscale values / brightness values ​​are greater than 230, the entire display screen is re-captured with the second shooting parameter, or only each point on the display screen corresponding to a series of pixels whose grayscale values / brightness values ​​are greater than 230 is re-captured.

[0071] If the pixel set to be processed includes a second pixel whose pixel parameter value, such as pixel grayscale value / brightness value, is less than the lower threshold of the above-mentioned predetermined value range, the third shooting parameter is determined, and a third image of the second point set shot with the third shooting parameter is obtained; the second point set includes at least a set of points corresponding to each second pixel on the target object.

[0072] Specifically, the above-mentioned high exposure shooting parameter can be determined as the third shooting parameter. If the pixel grayscale value / brightness value is less than the lower threshold of the predetermined value interval, it indicates that the pixel is underexposed. In this case, by increasing the exposure of the point set corresponding to this part of pixels on the target object, its details can be better captured.

[0073] Similarly, acquiring a third image of the second point set captured with a third shooting parameter may refer to acquiring an overall image of the target object captured with the third shooting parameter, or acquiring an image of a point set corresponding to each second pixel captured with the third shooting parameter on the target object. For example, when the pixel set to be processed includes a series of second pixels whose grayscale value / brightness value is less than 30, the entire display screen is re-captured with the third shooting parameter, or only the points corresponding to the series of pixels whose grayscale value / brightness value is less than 30 on the display screen are re-captured.

[0074] It is easy to understand that the parameter types of the second shooting parameter and the third shooting parameter are the same as the parameter types of the first shooting parameter. For example, if the first shooting parameter only includes the exposure time, the second shooting parameter and the third shooting parameter only include the exposure time accordingly. If the first shooting parameter includes the exposure time, the aperture size and the shutter speed, the second shooting parameter and the third shooting parameter also include the exposure time, the aperture size and the shutter speed. Moreover, compared with the first shooting parameter, the second shooting parameter can reduce the exposure degree of the photographed object (manifested as the brightness of the photographed object is reduced), and compared with the first shooting parameter, the third shooting parameter can increase the exposure degree of the photographed object (manifested as the brightness of the photographed object is increased).

[0075] Step 104: Generate a target image according to the first image, the updated image and the pixel set to be processed.

[0076] Based on the second image and / or the third image captured based on the corresponding second shooting parameters and / or the third shooting parameters, the first image and the second image and / or the third image can be further fused according to the position information of the first pixel and / or the second pixel included in the pixel set to be processed to obtain the target image.

[0077] Specifically, if the set of pixels to be processed includes the first pixel, the parts of the second image corresponding to the first pixels will replace the first pixels in the first image, or the brightness values ​​will be averaged or weighted averaged together with the first pixels in the first image; if the set of pixels to be processed includes the second pixel, the parts of the third image corresponding to the second pixels will replace the second pixels in the first image, or the brightness values ​​will be averaged or weighted averaged together with the second pixels in the first image, to obtain the target image, thereby eliminating the overexposed and / or underexposed pixels in the original first image, and avoiding the problem that the defect details cannot be captured or are not obvious.

[0078] In the process of fusing the first image, the second image and / or the third image, necessary scaling processing may be performed on the corresponding images to make the proportions of the images consistent.

[0079] Combined with reference Figure 2-Figure 4 ,in, Figure 2 is a screen image of a display to be inspected for defects, shot based on the first shooting parameter, Figure 3 for Figure 2 There are overexposed pixel areas in the image. Figure 4 for Figure 2 There are underexposed pixel areas in the image. Figure 3 and Figure 4 There are a series of points where details are not clearly captured. If the defect falls on Figure 3-Figure 4 At these points in the image, it will be difficult to identify the defects. For these points, they can be detected by using the above-mentioned predetermined value range based on the present application, and re-shooting can be performed according to the corresponding updated shooting parameters. After that, the shooting effect of these points can be improved through image fusion processing, thereby reducing the algorithm's misjudgment or wrong judgment.

[0080] It can be seen from the above scheme that the method of the embodiment of the present application, after obtaining the first image of the target object shot with the first shooting parameter, once it is determined that there is at least one pixel that does not meet the preset pixel parameter condition in at least a part of the image area of ​​the first image, then the updated shooting parameter is determined, and an updated image of at least a part of the area of ​​the target object shot with the updated shooting parameter is obtained, and then the target image is further generated based on the above-mentioned first image and the updated image, and the set of pixels to be processed consisting of the above-mentioned pixels that do not meet the preset pixel parameter condition. The present application determines the updated shooting parameter and obtains the updated image shot with the updated shooting parameter, and uses the updated image to optimize the shooting details of the pixels in the first image that do not meet the preset pixel parameter condition, so as to improve the problem that the defect details cannot be captured or the shooting is not obvious in the screen defect detection of the display, thereby reducing the probability of misjudgment or wrong judgment of the algorithm.

[0081] In addition, this embodiment predetermines three groups of exposure shooting parameters corresponding to the object to be detected, namely, low, medium, and high, and adjusts a series of overexposed pixels in the first image to be uniformly reshot using low exposure shooting parameters, while a series of underexposed pixels are adjusted to be uniformly reshot using high exposure shooting parameters. This avoids judging each pixel point that is not in the above-set value range and then adjusting the exposure parameters to perform a reshoot operation, thereby speeding up data processing, reducing processing time, and also being more in line with the needs of intelligent manufacturing.

[0082] The applicant has found that when detecting defects on display screens through image capture, underexposure or overexposure is the main reason why the details of screen defects cannot be captured or are not obvious. Based on this feature, in order to reduce the probability of algorithm misjudgment or misjudgment in defect detection scenarios of objects such as display screens, the embodiment of the present application provides an optimal underexposure and overexposure threshold range that matches the defect detection scenario in the field of industrial detection. Through a large number of analyses of millions of pictures on the production line and algorithm (defect detection algorithm) practice, if the image grayscale / brightness exceeds the preferred threshold range, such as 30 to 230, some LCD screen defects (such as bright spots, dark spots) will not be obvious or not be captured at all, resulting in poor defect contrast.

[0083] Therefore, in the embodiment of the present application, preferably, the underexposure and overexposure reference benchmarks are set to image grayscale / brightness of 30 to 230, wherein a grayscale / brightness greater than 230 is overexposure, and a grayscale / brightness less than 30 is underexposure, both of which will affect image details, resulting in poor contrast of screen defects and difficulty in accurate defect detection.

[0084] Accordingly, the above-mentioned preset pixel parameter condition is preferably set to: the grayscale value and / or brightness value of the pixel is in the interval [30, 230].

[0085] On this basis, in some embodiments, Figure 1 In the method shown, after the first image is acquired and enters step 102, the first image can be gray-processed to be converted into a gray-scale image, and it is determined whether there are pixels whose gray-scale values ​​are not in [30, 230] in at least a partial image area of ​​the gray-scale processed first image. If there is a first pixel whose gray-scale value exceeds 230, and / or there is a second pixel whose gray-scale value is less than 30, the first pixel and / or the second pixel are used as a pixel set to be processed. The first pixel is a collective term for a series of overexposed pixels in the first image, and the second pixel is a collective term for a series of underexposed pixels in the first image.

[0086] The at least partial image area of ​​the first image may refer to the entire area of ​​the first image, or may refer to an image area corresponding to a target object (such as a screen of a display screen) in the first image.

[0087] For the latter case, preferably, after obtaining the first image of the target object captured with the first shooting parameter and before grayscale processing of the first image, the first image may be firstly subjected to image segmentation processing, and the image area corresponding to the target object therein may be extracted, and the other parts may be filtered out. In practical applications, the first image may be subjected to image segmentation based on a machine vision algorithm, and the region of interest (ROI) therein may be extracted. The region of interest is the image area corresponding to the target object, such as the image area corresponding to the screen of the display screen, while the image parts corresponding to the parts outside the screen, such as the frame of the display screen or the background (the table top) are filtered out. The irrelevant parts are filtered out, and only the region of interest is processed.

[0088] In one embodiment, see Figure 5 The flowchart of the image processing method provided is as follows. After step 104, the image processing method disclosed in the present application may further include:

[0089] Step 105: perform defect recognition processing on the target image to identify defects existing in the target object.

[0090] Specifically, the target image may be detected by, but not limited to, calling an AOI algorithm to identify defects in a target object such as a display screen.

[0091] When the original image of the target object is underexposed / overexposed, the embodiment of the present application adjusts the shooting parameters to re-shoot and fuses the multiple images to eliminate the insufficient or over-bright parts of the target object, thereby eliminating the problem that the defect details in the image of the target object are not clearly captured or not captured. As a result, the accuracy of defect detection on the target object can be further improved and the probability of algorithm misjudgment or wrong judgment can be reduced.

[0092] In one embodiment, see Figure 6 The flowchart of the image processing method provided is as follows. Before step 101, the image processing method disclosed in the present application may further include:

[0093] Step 601: Acquire configuration information of a target object, and acquire a shooting parameter set matching the configuration information of the target object to obtain a target shooting parameter set; different objects with different configuration information correspond to different shooting parameter sets.

[0094] To further meet the needs of intelligent manufacturing, the embodiments of the present application predetermine N specific groups of shooting parameters corresponding to different exposure performances for each configuration of the object to be detected (e.g., different models of displays) through analysis of big data, such as big data analysis of batch positive and negative samples in the cloud, such as the three groups of low, medium and high exposure shooting parameters mentioned above.

[0095] Among them, the above-mentioned positive samples may refer to display screen images with normal exposure of defect details and good defect detail shooting effects, and the negative samples may refer to display screen images with abnormal exposure of defect details, defect details not captured or not clearly captured. By analyzing the shooting parameters corresponding to the batch positive and negative samples of the objects to be detected with different configurations on the cloud, three groups of exposure shooting parameters, low, medium and high, are formulated for each configuration of the objects to be detected. The values ​​of the three groups of exposure shooting parameters of the objects to be detected with different configurations are different, so as to support the shooting equipment to call the matching shooting parameter set in a targeted manner for the objects to be detected with a certain configuration to quickly adjust the exposure and reshoot.

[0096] On this basis, for the target object to be detected, its configuration information can be first obtained, including but not limited to the serial number (SN), model, size and other information of the LCD display screen. In one embodiment, an electronic code such as a QR code or a barcode carrying the configuration information of the target object can be bound to the target object in advance, such as attaching a paper electronic code to the display screen, or displaying the electronic code on a lit display screen, etc. Before taking a photo of the target object, scan the electronic code first to obtain the model, serial number and other configuration information of the target object.

[0097] Afterwards, according to the configuration information of the target object to be detected, such as scanning / parsing / shooting the above-mentioned QR code / electronic code, the exposure parameter set matching it can be called from the cloud to obtain the target shooting parameter set of the current target object to be detected. The target shooting parameter set includes three groups of shooting parameters: medium, low, and high, which respectively represent the first shooting parameter, the second shooting parameter, and the third shooting parameter described above in this application.

[0098] Optionally, three groups of high, medium and low shooting parameters corresponding to each configuration can be preset on the shooting device side, and the matching shooting parameter set (including the three groups of high, medium and low shooting parameters) can be called directly on the shooting device side according to the configuration information of the current object to be detected. This embodiment does not limit this.

[0099] Step 602: Acquire a first shooting parameter from a target shooting parameter set, and shoot the target object with the first shooting parameter.

[0100] On this basis, the medium exposure shooting parameter in the target shooting parameter set is called and used as the first shooting parameter to shoot the target object, and then continue to execute Figure 1 or Figure 5 The subsequent steps of the method shown are terminated until the target image is obtained or the defect detection of the target object is completed.

[0101] This embodiment, through big data analysis of batch positive and negative samples in the cloud, pre-formulates three sets of exposure shooting parameters of low, medium and high for each configuration of the object to be detected, which can facilitate the device to quickly call or adjust the exposure-related shooting parameters for image capture for each configuration of the object to be detected, thereby accelerating the image processing speed and correspondingly accelerating the defect recognition speed of the display object to be detected.

[0102] The present application also discloses an electronic device, the structure of which is as follows: Figure 7 As shown, including:

[0103] Image acquisition device 701.

[0104] The image acquisition device may include, for example, a camera module of an electronic device, which is used to capture images of the device to be tested, not limited to the first, second, and third images described above.

[0105] The memory 702 is used to store at least one set of instruction sets.

[0106] The instruction set may be implemented in the form of a computer program.

[0107] The processor 703 is used to implement the image processing method disclosed in any of the above method embodiments by running the instruction set in the memory.

[0108] The processor 703 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, etc.

[0109] In addition, the electronic device may also include components such as a communication interface and a communication bus. The memory, the processor and the communication interface communicate with each other through the communication bus.

[0110] The communication interface is used for communication between electronic devices and other devices. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0111] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0112] For the convenience of description, the above system or device is described as being divided into various modules or units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0113] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0114] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0115] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An image processing method, comprising: Acquire a first image of a target object captured using first capturing parameters; The target object includes: a display screen of a display to be subjected to screen defect detection; Determining that at least one pixel that does not satisfy a preset pixel parameter condition exists in at least a partial image area of ​​the first image, and obtaining a pixel set to be processed; Determine updated shooting parameters, and obtain an updated image of at least a partial area of ​​the target object shot with the updated shooting parameters; the at least partial area at least includes a set of points corresponding to the to-be-processed pixel set on the target object; wherein a series of overexposed pixels in the first image are adjusted to be uniformly re-shot using the second shooting parameters, and a series of underexposed pixels in the first image are adjusted to be uniformly re-shot using the third shooting parameters; the parameter types of the second shooting parameters and the third shooting parameters are the same as the parameter types of the first shooting parameters, the second shooting parameters can reduce the exposure of the object compared with the first shooting parameters, and the third shooting parameters can increase the exposure of the object compared with the first shooting parameters; A target image is generated according to the first image, the updated image and the position information of each pixel in the pixel set to be processed.

2. The method according to claim 1, wherein determining that there is at least one pixel in at least a portion of the image area of ​​the first image that does not satisfy a preset pixel parameter condition, and obtaining a pixel set to be processed, comprises: Determine at least one pixel in at least a partial image area of ​​the first image whose pixel grayscale value and / or brightness value is not within a predetermined value interval, and obtain the pixel set to be processed.

3. The method according to claim 2, determining updated shooting parameters, and acquiring an updated image of at least a partial area of ​​the target object shot with the updated shooting parameters, comprising: If the pixel set to be processed includes a first pixel whose pixel parameter value is greater than an upper threshold of the predetermined value interval, determining a second shooting parameter, and acquiring a second image of a first point set shot with the second shooting parameter; the first point set at least includes a set of points corresponding to each first pixel on the target object; If the pixel set to be processed includes a second pixel whose pixel parameter value is less than the lower threshold of the predetermined value interval, determine a third shooting parameter, and obtain a third image of a second point set shot with the third shooting parameter; the second point set at least includes a set of points corresponding to each second pixel on the target object; Generating a target image according to the first image, the updated image and the set of pixels to be processed comprises: A target image is generated according to the first image, the second image and / or the third image, and the pixel set to be processed.

4. The method according to claim 3, wherein determining the second shooting parameter comprises: Determine a shooting parameter that matches the pixel parameter value of the first pixel from a target shooting parameter set to obtain the second shooting parameter; The determining of the third shooting parameter includes: Determine a shooting parameter that matches the pixel parameter value of the second pixel from the target shooting parameter set to obtain the third shooting parameter; The target shooting parameter set also includes the first shooting parameter.

5. The method according to claim 3, wherein generating a target image according to the first image, the second image and / or the third image, and the position information of each pixel in the pixel set to be processed comprises: According to the position information of the first pixel and / or the second pixel included in the pixel set to be processed, the first image and the second image and / or the third image are fused to obtain a target image.

6. The method according to claim 4, wherein: The target object is a display screen; Before acquiring the first image of the target object photographed with the first photographing parameter, the method further includes: Acquire the configuration information of the target object, and acquire a shooting parameter set matching the configuration information of the target object, to obtain the target shooting parameter set; different objects with different configuration information correspond to different shooting parameter sets respectively; The first shooting parameter is acquired from the target shooting parameter set, and the target object is photographed with the first shooting parameter.

7. The method according to claim 1, before determining whether there is at least one pixel whose display parameter does not satisfy the parameter condition in at least a partial image area of ​​the first image, further comprising: Performing image segmentation processing on the first image to obtain an image region corresponding to the target object in the first image, so as to process the image region corresponding to the target object.

8. According to the method of claim 2, the predetermined value interval is [30, 230].

9. The method according to claim 1, after generating and outputting the target image, further comprising: Defect recognition processing is performed on the target image to identify defects existing in the target object.

10. An electronic device, comprising: Image acquisition device; A memory for storing at least one set of instructions; A processor, configured to implement the image processing method according to any one of claims 1 to 9 by running the instruction set in the memory.

Images