A method and system for detecting flatness of a paint-sprayed aluminum plate

Abstract

A flatness detection method and system of a paint-sprayed aluminum plate, relating to the field of metallic property detection. The method is applied to an aluminum plate detection system, and the method comprises: obtaining a first surface image of the aluminum plate captured by an optical camera, the first surface image being composed of a plurality of pixel points, and each pixel point storing an RGB value and a brightness value; performing anti-reflection suppression processing on the first surface image to obtain a second surface image; performing image enhancement on the second surface image to obtain a third surface image; and performing texture recognition on the third surface image to obtain the flatness of the aluminum plate. The technical solution provided in the application solves the problem of low recognition accuracy of the flatness of the aluminum plate surface caused by the reflective characteristic of the aluminum plate material.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of metallic energy detection, and in particular to a flatness detection method and system for a paint-sprayed aluminum plate. BACKGROUND

[0002] An aluminum plate is a light metal and is prone to oxidation to form an oxide film. Although the film has a certain anti-oxidation effect, the film has a large porosity and poor mechanical properties, and cannot effectively prevent further corrosion of various media in the atmosphere. Therefore, the aluminum plate needs to be painted to prevent direct contact between the aluminum plate and the air, so as to achieve better anti-oxidation effect.

[0003] At present, the flatness of the aluminum plate needs to be detected before painting. If the aluminum plate surface has defects such as depressions, folds and patterns, the aluminum plate needs to be reprocessed to eliminate these defects before painting, so as to ensure that the paint-sprayed aluminum plate has good anti-oxidation effect after painting. With the continuous development of science and technology, the flatness detection of the aluminum plate has been gradually optimized from the traditional contact type micrometer detection to the non-contact image detection, thereby achieving a substantial improvement in detection accuracy.

[0004] However, due to the light-reflecting property of the aluminum plate material, the detail information of the photographed aluminum plate image is blurred, thereby reducing the recognition accuracy of the flatness of the aluminum plate surface. SUMMARY

[0005] In view of the low recognition accuracy of the flatness of the aluminum plate surface caused by the light-reflecting property of the aluminum plate material, the application provides a flatness detection method and system for a paint-sprayed aluminum plate.

[0006] In a first aspect, the application provides a flatness detection method for a paint-sprayed aluminum plate, applied to an aluminum plate detection system, and the method comprises the following steps:

[0007] obtaining a first surface image of the aluminum plate photographed by an optical camera, the first surface image being composed of a plurality of pixel points, and each pixel point storing an RGB value and a brightness value;

[0008] performing light reflection suppression processing on the first surface image to obtain a second surface image;

[0009] performing image enhancement on the second surface image to obtain a third surface image;

[0010] performing texture recognition on the third surface image to obtain the flatness of the aluminum plate.

[0011] Optionally, the first surface image is subjected to light reflection suppression processing to obtain a second surface image, specifically as follows:

[0012] By iterating through the RGB values ​​of multiple pixels, the minimum color channel value of the multiple pixels is obtained;

[0013] Iterate through the luminance values ​​corresponding to the minimum color channel values ​​to determine the maximum luminance value A{ },in, These are the maximum brightness values ​​of the R channel, G channel, and B channel, respectively, among the multiple minimum color channel values.

[0014] Acquire depth information of multiple pixels detected by a depth sensor, wherein the depth information is the physical straight-line distance from the pixel to the optical camera;

[0015] Based on the depth information of the multiple pixels, the confidence level of the multiple pixels is determined;

[0016] According to the maximum brightness value A{ } and the confidence levels of multiple pixels, and calculate the scattering coefficients of multiple pixels;

[0017] Using the scattering coefficient, the first surface image is subjected to reflection suppression processing to obtain the second surface image.

[0018] Optionally, image enhancement is performed on the second surface image to obtain a third surface image, specifically:

[0019] The first surface image is compared with the second surface image to determine the reflection suppression amplitude of multiple pixels;

[0020] Based on the reflection suppression amplitude of the multiple pixels, the image gain coefficient of the multiple pixels in the second surface image is determined;

[0021] Based on the image gain coefficients of multiple pixels in the second surface image, the second surface image is enhanced to obtain a third surface image.

[0022] Optionally, determining the gain coefficients of multiple pixels in the second surface image based on the reflection suppression amplitude of multiple pixels further includes:

[0023] Calculate the neighborhood variance of multiple pixels in the second surface image;

[0024] The image gain coefficients of the multiple pixels are adjusted based on the neighborhood variance of the multiple pixels in the second surface image.

[0025] Optionally, adjusting the image gain coefficients of the plurality of pixels based on the neighborhood variance of the plurality of pixels in the second surface image specifically involves:

[0026]

[0027] in, and are the image gain coefficients of the i-th pixel before and after adjustment, respectively. and These represent the minimum and maximum values ​​of the neighborhood variance of multiple pixels in the second surface image, respectively. Let be the neighborhood variance of the i-th pixel. It is the mean of the neighborhood variances of multiple pixels in the second surface image.

[0028] Optionally, calculating the neighborhood variance of multiple pixels in the second surface image specifically involves:

[0029] Perform a Fourier transform on the second surface image to obtain the frequency domain image of the second surface image;

[0030] The frequencies of multiple pixels in the frequency domain image of the second surface image;

[0031] The differences between the frequencies of multiple pixels in the second surface image and the inherent frequencies of the aluminum plate are calculated to determine the neighborhood variance of the multiple pixels. The neighborhood variance is either the brightness value variance or the gradient value variance.

[0032] Optionally, defect identification is performed on the third surface image to obtain the flatness of the aluminum plate, specifically as follows:

[0033] Convert the third surface image into a grayscale image;

[0034] Perform a Fourier transform on the grayscale image to obtain a frequency domain image;

[0035] Identify the periodic texture frequency features in the frequency domain image;

[0036] The similarity between the periodic texture frequency feature and the preset periodic texture frequency feature is calculated to obtain the flatness of the aluminum plate, wherein the preset periodic texture frequency feature is the periodic texture frequency feature of a normal aluminum plate.

[0037] Secondly, this application provides a flatness detection system for painted aluminum sheets. The system is an aluminum sheet detection system, comprising an acquisition module, a processing module, and an output module, wherein:

[0038] The acquisition module is used to acquire a first surface image of an aluminum plate captured by an optical camera. The first surface image is composed of multiple pixels, and each pixel stores RGB values ​​and brightness values.

[0039] The processing module is used to perform reflection suppression processing on the first surface image to obtain a second surface image; and to perform image enhancement on the second surface image to obtain a third surface image.

[0040] The output module is used to perform texture recognition on the third surface image to obtain the flatness of the aluminum plate.

[0041] Thirdly, this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of the first aspects.

[0042] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed, perform the method described in any one of the first aspects.

[0043] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0044] This application addresses the issue of strong reflectivity in aluminum plates by applying a reflectivity suppression process. This reduces the reflected light, resulting in a clearer surface image and more accurate subsequent flatness detection. However, since reflectivity suppression only weakens the effect of light, not completely eliminates it, and the inherent blurriness of the image can also reduce the accuracy of flatness detection, this application enhances the surface image after reflectivity suppression by improving both the light effect and blurriness aspects. Furthermore, by identifying the periodic texture frequency features in the enhanced surface image and calculating their similarity to the periodic texture frequency features of a normal aluminum plate, the flatness of the aluminum plate is obtained. In this process, if defects exist on the aluminum plate surface, its periodic texture frequency features will be disordered, resulting in a lower similarity and thus a lower flatness. This indirectly calculates the surface flatness of the aluminum plate, thereby reducing the detection requirements for feature recognition. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for detecting the flatness of painted aluminum plates provided in an embodiment of this application.

[0046] Figure 2 This is a schematic diagram of the flatness detection system for painted aluminum plates provided in an embodiment of this application.

[0047] Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0048] Explanation of reference numerals in the attached drawings: 1. Acquisition module; 2. Processing module; 3. Output module; 300. Electronic device; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 305. Memory. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0050] Currently, some aluminum plates have high reflectivity. When the ambient light is strong, the reflected area appears as a white blob after being reflected by the aluminum plate. The detailed information on the surface of the aluminum plate is replaced by white, which greatly reduces the recognition accuracy of current non-contact image detection.

[0051] Therefore, to solve this problem, this application provides a method for detecting the flatness of painted aluminum sheets. This method is applied to an aluminum sheet inspection system, such as... Figure 1 As shown, the method includes steps S101 to S104, which are as follows:

[0052] S101. Obtain a first surface image of the aluminum plate captured by an optical camera. The first surface image consists of multiple pixels, and each pixel stores RGB values ​​and brightness values.

[0053] In the above steps, when the optical camera photographs the surface of the aluminum plate, in order to ensure the quality of the captured image, the shooting angle, shooting distance, and ambient lighting of the optical camera need to be adjusted in advance. Then, the captured first surface image is uploaded to the aluminum plate detection system. The captured first surface image is a color image, which is composed of pixels. Each pixel stores RGB values, and each of the three color channels corresponds to a brightness value. For example, for a certain pixel, its color is composed of red channel value (R), green channel value (G), and blue channel value (B). Each color channel also has a corresponding brightness value, that is, the red channel value corresponds to the red brightness value, the green channel value corresponds to the green brightness value, and the blue channel value corresponds to the blue brightness value.

[0054] S102. Perform reflection suppression processing on the first surface image to obtain the second surface image.

[0055] In the above steps, due to the reflective properties of the aluminum plate, the local details on the surface of the aluminum plate appear obscured under the influence of light, thus blurring these details. Therefore, this application weakens the obscured light by performing reflection suppression processing on the first surface image, making the original details stand out, thereby ensuring more accurate subsequent flatness detection. Specifically:

[0056] Before proceeding, it's important to understand that the image of an aluminum plate captured by an optical camera consists of the portion of light reflected from the aluminum plate surface that reaches the camera after being scattered by the environment, and the portion of ambient light that is directly scattered to the camera. The scattering of light reflected from the aluminum plate surface by the environment causes a loss of color channel values, thus failing to reflect true color information. For a single pixel, different color channel values ​​are affected differently. If a color channel value is larger, its impact from light is more significant. If a color channel value remains small after being affected by light, it means that the color channel value is less affected. In this case, the brightness value of that color channel can be used to restore the more significantly affected color channel value, thereby achieving the effect of reflection suppression.

[0057] Based on this principle, this application first iterates through the RGB values ​​of multiple pixels in the first surface image and queries the minimum color channel value of each pixel. The minimum color channel value of a pixel reflects the relatively dark part of that pixel, that is, the color channel is least affected by light. Ideally, its color information is closer to its true color information after being captured by the optical camera.

[0058] Then, by iterating through the brightness values ​​corresponding to the minimum color channel values, the maximum brightness value A of the R channel, G channel, and B channel is queried respectively. ],in, These represent the maximum brightness values ​​of the R channel, G channel, and B channel, respectively, among multiple minimum color channel values. Here, because different color channels have different absorption and scattering characteristics, and different objects in the scene reflect and absorb different wavelengths of light differently, objects in areas with less environmental scattering have relatively higher brightness values ​​due to less interference from environmental scattering. Conversely, objects affected by significant environmental scattering have more uniform light, making it difficult to achieve exceptionally high brightness values. Therefore, the maximum brightness value of the R channel can be understood as the brightness value among all pixels in the R channel that is least affected by environmental scattering. This brightness value reflects the brightness closest to the object's true color; that is, in the R channel, this brightness value best represents the object's inherent brightness, without excessive interference from environmental scattering, and is the brightness value in the R channel that best reflects the object's inherent characteristics.

[0059] Then, a depth sensor is used to detect the depth information of multiple pixels. In this application, the depth information refers to the physical straight-line distance from the pixel to the optical camera. In real-world scenarios, as the depth of a pixel increases, the detail information of the pixel continuously shrinks, resulting in a decrease in detection accuracy. Therefore, this application determines the confidence level of each pixel based on the depth information of each pixel. The confidence level can be understood as the recognition accuracy of the information stored in the pixel. Specifically, it is obtained by calculating the depth ratio of each pixel to the pixel closest to the optical camera.

[0060] Then, based on the maximum brightness value A{ The scattering coefficient of each pixel is calculated using the confidence scores of multiple pixels, specifically using the following formula:

[0061] (1)

[0062] in, Let be the scattering coefficient of the i-th pixel. Let i be the confidence level of the i-th pixel. Let {R(i), G(i), B(i)} be the RGB values ​​of the i-th pixel. Maximum brightness value { }

[0063] In the above formula (1), the scattering coefficient can be understood as the degree of attenuation of the brightness value of a pixel. For pixels with more severe reflection, the scattering coefficient is higher; for pixels with good reflection, the scattering coefficient is lower. This represents the minimum ratio calculated by comparing the R, G, and B values ​​of the i-th pixel with the R, G, and B values ​​corresponding to the maximum brightness value; for an aluminum plate surface captured by an optical camera, this represents the light reflected from the aluminum plate surface. The portion that reaches the camera after being scattered by the environment The part that is directly scattered to the camera by ambient light The composition can be represented as:

[0064] (2)

[0065] in, Let x be the pixel value of the x-th pixel captured by the optical camera. This represents the actual pixel value of the x-th pixel. This represents the proportion of pixel values ​​at the x-th pixel that are not scattered by the environment. This represents the ambient light value.

[0066] In expression (2), if the pixel value of the x-th pixel is very small in the entire aluminum plate surface image, the RGB channel value of that pixel will also be relatively small. Therefore, reflection suppression is performed to... Set it to 0, then... As output As input, the expression is transformed to obtain the formula for calculating the scattering coefficient. It should be explained that for pixels with very small values, they often correspond to darker objects in the actual scene, and are less affected by ambient light scattering and other interference factors. In this case, the calculation is performed using the pixel with the smallest value. This is used as a standard for suppressing reflections in other pixels, and the scattering coefficient of each pixel is determined to facilitate the restoration of the true image of the aluminum plate surface. In addition, it should be noted that since the true pixel value of each pixel is affected by environmental interference and cannot be known, the pixel with the smallest value is set to 0 to minimize the calculation error of the scattering coefficient.

[0067] Finally, after calculating the scattering coefficient of each pixel, the scattering coefficient of each pixel is... Pixel values ​​captured by an optical camera And the maximum brightness value A{ Substitute the values ​​into formula (2) to solve for the second surface image after reflection suppression.

[0068] S103. Perform image enhancement on the second surface image to obtain the third surface image.

[0069] In the above steps, suppressing the reflection in the first surface image only reduces the influence of environmental scattering on the aluminum plate surface image. However, the noise inherent in the aluminum plate surface image itself will still cause errors in the flatness detection of the aluminum plate. In addition, the reflection suppression in the second surface image cannot completely eliminate the influence of aluminum plate reflection. Therefore, image enhancement is still required for the second surface image to improve the accuracy of subsequent flatness detection. Specifically:

[0070] First, a wavelet transform algorithm is used to enhance the second surface image. Specifically, the second surface image is first subjected to wavelet transform to decompose the pixel value of each pixel in the second surface image, and obtain the high-frequency wavelet coefficients and low-frequency wavelet coefficients of each pixel in the frequency range. Then, a preset gain coefficient is used to gain the high-frequency wavelet coefficients of each pixel (detail information usually exists in high-frequency information). Finally, the pixels after gain are restored to obtain a third surface image with more prominent detail information.

[0071] However, since the reflectivity of each pixel varies, using a preset gain coefficient for pixels with a large reflectivity suppression may cause excessive noise amplification, leading to image distortion. Therefore, to reduce this, this application compares the first surface image with the second surface image to determine the reflectivity suppression of each pixel. Specifically, it compares the original pixel value of a pixel with the pixel value obtained after reflectivity suppression. The larger the ratio, the greater the reflectivity suppression; the smaller the ratio, the smaller the reflectivity suppression. Then, the reflectivity suppression of multiple pixels is normalized. Finally, the normalized result of each pixel is multiplied by a preset gain coefficient to obtain the image gain coefficient of each pixel in the second surface image, thereby reducing the occurrence of excessive noise amplification.

[0072] Then, regarding the noise inherent in the aluminum plate surface image itself, this application determines the degree of noise influence on the aluminum plate surface image by calculating the neighborhood variance of multiple pixels in the second surface image. The neighborhood variance is the variance of brightness values ​​or gradient values ​​within a preset adjacent range centered on the pixel. Specifically, the second surface image is subjected to a Fourier transform to obtain its frequency domain image; then, the frequency of each pixel in the frequency domain image is extracted. Next, the difference between the frequency of each pixel and the inherent frequency of the aluminum plate is calculated. If the frequency of the pixel is greater than the inherent frequency of the aluminum plate, and the difference is also greater than the inherent frequency... The upper limit of the fluctuation range indicates that the pixel is affected by high-frequency noise. If the frequency of the pixel is less than the natural frequency of the aluminum plate, and the difference is greater than the lower limit of the fluctuation range of the natural frequency, it indicates that the pixel is affected by low-frequency noise. For the surface image of the aluminum plate, the image gradient value is very sensitive to high-frequency noise, and the image brightness value is very sensitive to low-frequency noise. Therefore, if the noise frequency of the pixel is high-frequency, the neighborhood variance of the gradient value of the pixel is calculated, and if the noise frequency of the pixel is low-frequency, the neighborhood variance of the brightness value of the pixel is calculated. This more accurately describes the noise interference and the degree of interference experienced by each pixel.

[0073] If the neighborhood variance of a pixel is large, it indicates that the noise in the region where that pixel is located is significant. In this case, the gain coefficient needs to be reduced to prevent excessive amplification of the noise. Then, based on the neighborhood variance of each pixel in the second surface image, the gain coefficient, which has been adjusted after reflection suppression, is further adjusted to obtain the final gain coefficient for each pixel. The specific adjustment method is as follows:

[0074]

[0075] in, and are the image gain coefficients of the i-th pixel before and after adjustment, respectively. and These represent the minimum and maximum values ​​of the neighborhood variance of multiple pixels in the second surface image, respectively. Let be the neighborhood variance of the i-th pixel. It is the mean of the neighborhood variances of multiple pixels in the second surface image.

[0076] In the above formula, This can be understood as normalizing the neighborhood variance of pixels in the second surface image, thereby limiting the neighborhood variance of each pixel in the image to a metric range of [0,1], and avoiding... The calculation results deviate from the normal values; for In this case, the mean of the neighborhood variances of multiple pixels is selected as the reference center for the neighborhood variances of multiple pixels; at this time, with Centered on, according to relatively The degree of deviation is used to adjust the gain coefficient of each pixel, thereby reflecting the gain adjustment requirements of different pixel noise levels relative to the average noise level, and thus improving the value of the second surface image after gain.

[0077] Finally, based on the adjusted gain coefficients of multiple pixels in the final second surface image, a wavelet image enhancement algorithm is used to enhance the second surface image to obtain the third surface image.

[0078] S104. Perform texture recognition on the third surface image to obtain the flatness of the aluminum plate.

[0079] In the above steps, if there are defects on the aluminum plate surface, they are generally irregular and minute, causing traditional flatness recognition algorithms to only identify the presence of flatness defects but not their severity. Therefore, to solve this problem, this application first converts the third surface image into a grayscale image, then performs a Fourier transform on the grayscale image to obtain a frequency image, converting the grayscale image from the spatial domain to the frequency domain. It should be noted that under normal circumstances, the texture of the painted aluminum plate surface exhibits a certain periodicity, which manifests as specific frequency components in the frequency domain. However, when flatness defects exist on the aluminum plate surface, the periodicity of the texture is disrupted, and correspondingly, the frequency components in the frequency domain also change. Based on this characteristic, the periodic texture frequency features in the frequency image are identified, and then the similarity between the periodic texture frequency features and a preset periodic texture frequency feature is calculated, thereby obtaining a more accurate flatness of the aluminum plate. The preset periodic texture frequency feature is the periodic texture frequency feature of a normal aluminum plate.

[0080] Reference Figure 2This application also provides a flatness detection system for painted aluminum sheets. The system is an aluminum sheet detection system, which includes an acquisition module 1, a processing module 2, and an output module 3, wherein:

[0081] Module 1 is used to acquire a first surface image of an aluminum plate captured by an optical camera. The first surface image consists of multiple pixels, and each pixel stores RGB values ​​and brightness values.

[0082] Processing module 2 is used to perform reflection suppression processing on the first surface image to obtain the second surface image; and to perform image enhancement on the second surface image to obtain the third surface image.

[0083] Output module 3 is used to perform texture recognition on the third surface image to obtain the flatness of the aluminum plate.

[0084] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0085] This application also discloses an electronic device. (See reference...) Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0086] The communication bus 302 is used to enable communication between these components.

[0087] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0088] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0089] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0090] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a method of detecting the flatness of painted aluminum panels.

[0091] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call an application program stored in the memory 305 for detecting the flatness of painted aluminum plates. When executed by one or more processors 301, the electronic device 300 performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0092] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0093] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0094] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0096] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0097] The above description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and the disclosure of practical truths.

[0098] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for detecting the flatness of painted aluminum sheets, characterized in that, The method, applied in an aluminum plate inspection system, includes: A first surface image of an aluminum plate captured by an optical camera is obtained. The first surface image consists of multiple pixels, and each pixel stores RGB values ​​and brightness values. The first surface image is subjected to reflection suppression processing to obtain the second surface image, specifically as follows: By iterating through the RGB values ​​of multiple pixels, the minimum color channel value of the multiple pixels is obtained; Iterate through the luminance values ​​corresponding to the minimum color channel values ​​to determine the maximum luminance value A{ },in, These are the maximum brightness values ​​of the R channel, G channel, and B channel, respectively, among the multiple minimum color channel values. Acquire depth information of multiple pixels detected by a depth sensor, wherein the depth information is the physical straight-line distance from the pixel to the optical camera; The confidence level of the multiple pixels is determined based on the depth information of the multiple pixels. Specifically, the confidence level of the multiple pixels is obtained by calculating the depth ratio of each pixel to the pixel closest to the optical camera. According to the maximum brightness value A{ } and the confidence levels of multiple pixels, the scattering coefficients of multiple pixels are calculated, specifically as follows: in, Let be the scattering coefficient of the i-th pixel. Let i be the confidence level of the i-th pixel. Let {R(i), G(i), B(i)} be the RGB values ​​of the i-th pixel. Maximum brightness value { }; Using the scattering coefficient, the first surface image is subjected to reflection suppression processing to obtain the second surface image; Image enhancement is performed on the second surface image to obtain the third surface image, specifically as follows: The first surface image is compared with the second surface image to determine the reflection suppression amplitude of multiple pixels; Based on the reflection suppression amplitude of the multiple pixels, the image gain coefficient of the multiple pixels in the second surface image is determined; Based on the image gain coefficients of multiple pixels in the second surface image, image enhancement is performed on the second surface image to obtain a third surface image; Texture recognition is performed on the third surface image to obtain the flatness of the aluminum plate.

2. The method according to claim 1, characterized in that, The step of determining the gain coefficient of multiple pixels in the second surface image based on the reflection suppression amplitude of multiple pixels further includes: Calculate the neighborhood variance of multiple pixels in the second surface image; The image gain coefficients of the multiple pixels are adjusted based on the neighborhood variance of the multiple pixels in the second surface image.

3. The method according to claim 2, characterized in that, The step of adjusting the image gain coefficients of multiple pixels based on the neighborhood variance of multiple pixels in the second surface image specifically involves: in, and are the image gain coefficients of the i-th pixel before and after adjustment, respectively. and These represent the minimum and maximum values ​​of the neighborhood variance of multiple pixels in the second surface image, respectively. Let be the neighborhood variance of the i-th pixel. It is the mean of the neighborhood variances of multiple pixels in the second surface image.

4. The method according to claim 2, characterized in that, The calculation of the neighborhood variance of multiple pixels in the second surface image is specifically as follows: Perform a Fourier transform on the second surface image to obtain the frequency domain image of the second surface image; The frequencies of multiple pixels in the frequency domain image of the second surface image; The differences between the frequencies of multiple pixels in the second surface image and the inherent frequencies of the aluminum plate are calculated to determine the neighborhood variance of the multiple pixels. The neighborhood variance is either the brightness value variance or the gradient value variance.

5. The method according to claim 1, characterized in that, Defect identification is performed on the third surface image to obtain the flatness of the aluminum plate, specifically as follows: Convert the third surface image into a grayscale image; Perform a Fourier transform on the grayscale image to obtain a frequency domain image; Identify the periodic texture frequency features in the frequency domain image; The similarity between the periodic texture frequency feature and the preset periodic texture frequency feature is calculated to obtain the flatness of the aluminum plate, wherein the preset periodic texture frequency feature is the periodic texture frequency feature of a normal aluminum plate.

6. A flatness detection system for painted aluminum panels, characterized in that, The system is used to perform a method for detecting the flatness of painted aluminum plates as described in any one of claims 1-5. The system is an aluminum plate detection system, comprising an acquisition module (1), a processing module (2), and an output module (3), wherein: The acquisition module (1) is used to acquire a first surface image of an aluminum plate captured by an optical camera. The first surface image is composed of multiple pixels, and each pixel stores RGB values ​​and brightness values. The processing module (2) is used to perform reflection suppression processing on the first surface image to obtain a second surface image; and to perform image enhancement on the second surface image to obtain a third surface image. The output module (3) is used to perform texture recognition on the third surface image to obtain the flatness of the aluminum plate.

7. An electronic device, characterized in that, The device includes a processor (301), a memory (305), a user interface (303), and a network interface (304). The memory (305) is used to store instructions. The user interface (303) and the network interface (304) are used to communicate with other devices. The processor (301) is used to execute the instructions stored in the memory (305) to cause the electronic device (300) to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 5.

Images