Method and system for evaluating corrosion degree after salt spray test

Abstract

The application relates to a corrosion degree evaluation method and system after a salt spray test, the method comprising determining identity information of an evaluation object, and acquiring a pre-corrosion image and a post-corrosion image associated with the identity information of the evaluation object; analyzing the pre-corrosion image and the post-corrosion image to determine a corrosion area; performing classification processing on the corrosion area to obtain a classification result, the classification result comprising a plane corrosion type, a convex corrosion type and a concave corrosion type; determining an area value of each classification in the classification result and giving a corrosion degree evaluation result according to the area value of each classification. The corrosion degree evaluation method and system for the salt spray test disclosed by the application can determine the corrosion area type while determining the area of the corrosion area, and can give the corrosion degree evaluation result of a test piece according to the corrosion area type.

Description

Technical Field

[0001] This application relates to the field of image analysis technology, and in particular to a method and system for evaluating corrosion after salt spray testing. Background Technology

[0002] Salt spray testing accelerates the corrosion process of materials by simulating salt spray conditions in the marine atmospheric environment. In the test, samples are exposed to a salt spray environment containing a 5% sodium chloride solution (other reagents may be added depending on the corrosion conditions). By controlling temperature, humidity, and spray volume, the corrosion conditions in the actual environment are simulated.

[0003] The core of corrosion evaluation after salt spray testing is appearance rating, area quantification, corrosion type differentiation, weighing / thickness measurement, and classification according to national / international standards.

[0004] Image analysis is used to calculate the area of ​​salt spray corrosion. The core idea is: take a picture → image preprocessing → segment the corrosion area → calculate the pixel ratio → convert it into area percentage. Current real-world influencing factors include uneven lighting, perspective distortion, and surface condition interference. Regarding visual algorithms, thresholding relies too heavily on manual parameter tuning, resulting in incompatible parameters that cannot be reused and cannot be applied to the overall picture. Furthermore, simple thresholding can only determine the area and cannot distinguish corrosion morphologies, necessitating secondary processing. Summary of the Invention

[0005] This application provides a method and system for evaluating corrosion after salt spray testing, which can determine the type of corrosion zone while determining the area of ​​the corrosion zone, and can provide corrosion evaluation results of the test piece based on the type of corrosion zone.

[0006] The above-mentioned objective of this application is achieved through the following technical solution: In a first aspect, this application provides a method for evaluating corrosion after a salt spray test, including: Determine the identity information of the evaluation object and obtain the pre-corrosion and post-corrosion images associated with the identity information of the evaluation object; Analyze the images before and after corrosion to determine the corrosion area; The corroded areas are classified to obtain classification results, which include planar corrosion, raised corrosion, and recessed corrosion. Determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

[0007] In one possible implementation of the first aspect, analyzing the pre-corrosion image and the post-corrosion image and determining the corroded area includes: The images before and after erosion are registered using fixed feature points; The registered pre-erosion and post-erosion images are processed using pooling contrast or Lab space to identify the distinguishing regions in the post-erosion image. Filter the distinguishing regions and remove unreliable parts from them; The selected distinguishing regions are used as the erosion areas.

[0008] In one possible implementation of the first aspect, processing the registered pre-erosion and post-erosion images using a pooling contrast method includes: The first feature map is obtained by traversing the registered uncorroded image using the pooling operator. The second feature map is obtained by traversing the registered eroded image using the pooling operator. Compare the first feature map and the second feature map to determine the distinguishing regions on the second feature map; The distinct regions present in the eroded image are determined based on the distinct regions on the second feature map; When using the pooling operator for traversal, the maximum pixel value of the region where the pooling operator is located is used as the representative value of the region where the pooling operator is located. The step size of the pooling operator is one pixel; Use statistical methods to determine the distinguishing regions on the second feature map. In one possible implementation of the first aspect, processing the registered pre-erosion and post-erosion images using Lab space includes: The registered pre-erosion image is segmented to obtain multiple first image units; The registered eroded image is segmented to obtain multiple second image units, and the number of second image units is the same as that of the first image units and they correspond one-to-one. The first image unit and the second image unit corresponding to the first image unit are transferred into the Lab space to obtain the pixel brightness, red-green color components and yellow-blue color components. The total color difference value between the first image unit and the second image unit corresponding to the first image unit is calculated based on the pixel brightness, red-green color components and yellow-blue color components. The distinct regions on the etched image are determined based on the total color difference value; In the segmentation of the registered pre-erosion image and the registered post-erosion image, the step size for each segmentation is one pixel. When determining the distinguishing regions on the etched image based on the total color difference value, a statistical method is used to calibrate the distinguishing regions on the etched image.

[0009] In one possible implementation of the first aspect, classifying the corroded areas and obtaining the classification results includes: Determine the edge contour of the corroded area; Multiple verification points were randomly selected on the edge contour of the corroded area; Select a verification area on each side of the verification point, with the two verification areas located on the inner and outer sides of the edge contour, respectively; Compare the brightness difference between the two verification areas; The classification of corrosion areas is determined based on the brightness difference. The classification results include planar corrosion, raised corrosion, and recessed corrosion.

[0010] In one possible implementation of the first aspect, when comparing the brightness difference between two verification regions, the total color difference value of the verification regions is also calculated. When the total color difference between two verification areas is greater than the corresponding set reference value, the classification result of the eroded area is determined based on the brightness difference. When the total color difference between two verification areas is less than or equal to the corresponding set reference value, the etched area is classified as planar etched area.

[0011] In one possible implementation of the first aspect, the classification results for raised corrosion and recessed corrosion are further validated. Validation of the classification results for raised corrosion and recessed corrosion includes: In the corrosion areas of raised and recessed corrosion types, look for characteristic areas, including fluffy areas and shaded areas; Corrosion areas that include fluffy areas are classified as raised corrosion, while corrosion areas that only include shaded areas are classified as sunken corrosion.

[0012] Secondly, this application provides a corrosion evaluation device after a salt spray test, comprising: The identity verification unit is used to determine the identity information of the evaluation object and acquire the pre-corrosion image and post-corrosion image associated with the identity information of the evaluation object. The comparative analysis unit is used to analyze images before and after corrosion to determine the corrosion area; The classification processing unit is used to classify the corroded areas and obtain classification results, which include planar corrosion, raised corrosion and recessed corrosion. The result output unit is used to determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

[0013] Thirdly, this application provides a corrosion evaluation system after a salt spray test, the system comprising: One or more memories for storing instructions; and One or more processors are configured to call and execute the instructions from the memory to perform the methods described in the first aspect and any possible implementation thereof.

[0014] Fourthly, this application provides a computer-readable storage medium, the computer-readable storage medium comprising: The program, when run by a processor, is executed as described in the first aspect and any possible implementation thereof.

[0015] Fifthly, this application provides a computer program product, including program instructions that, when run by a computing device, execute the method described in the first aspect and any possible implementation thereof.

[0016] Sixthly, this application provides a chip system including a processor for implementing the functions involved in the foregoing aspects, such as generating, receiving, transmitting, or processing the data and / or information involved in the foregoing methods.

[0017] This chip system can consist of chips or include chips and other discrete components.

[0018] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means, or the processor and the memory can be coupled to the same device. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of a corrosion evaluation method following a salt spray test, as provided in this application.

[0020] Figure 2 This is a schematic diagram showing the corrosion comparison of an evaluation object before and after, provided in this application.

[0021] Figure 3 This is a schematic diagram of a pooling operator provided in this application.

[0022] Figure 4 This is a schematic diagram of a 0-value pixel provided in this application.

[0023] Figure 5 This is a schematic diagram of a verification point and verification area provided in this application. Detailed Implementation

[0024] The technical solutions in this application will be further described in detail below with reference to the accompanying drawings.

[0025] This application discloses a method for evaluating corrosion after salt spray testing. Please refer to [link / reference]. Figure 1 In some examples, the corrosion evaluation method disclosed in this application for salt spray testing includes the following steps: S101, determine the identity information of the evaluation object, and obtain the pre-corrosion image and post-corrosion image associated with the identity information of the evaluation object; S102, Analyze the images before and after corrosion to determine the corrosion area; S103, classify the corroded areas to obtain classification results, which include planar corrosion, raised corrosion and recessed corrosion. S104, determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

[0026] Specifically, in step S101, it is first necessary to determine the identity information of the evaluation object and simultaneously obtain the pre-corrosion image and post-corrosion image associated with the identity information of the evaluation object. Here, the evaluation object refers to the specimen that has completed the salt spray test, and the identity information of the evaluation object refers to the identification code of the specimen. The identification code of the specimen is unique, and the data generated in the entire salt spray test process can be integrated accordingly.

[0027] Pre-corrosion images refer to images taken of the object being evaluated before the salt spray test, such as... Figure 2 As shown.

[0028] Post-corrosion images refer to images taken of the object being evaluated after the salt spray test, such as... Figure 2 As shown.

[0029] For convenience, the evaluation object is usually placed on a fixed stand and sent into the salt spray test equipment to complete the test. This ensures that the images before and after corrosion can be obtained based on the same benchmark. At this time, the code on the fixed stand serves as the identification information of the evaluation object.

[0030] When shooting images before and after corrosion, the fixed platform is placed at the same shooting position to ensure consistency of shooting parameters and lighting parameters.

[0031] In step S102, the images before and after corrosion are analyzed to determine the corrosion area. The specific method is as follows: The images before and after erosion are registered using fixed feature points; The registered pre-erosion and post-erosion images are processed using pooling contrast or Lab space to identify the distinguishing regions in the post-erosion image. Filter the distinguishing regions and remove unreliable parts from them; The selected distinguishing regions are used as the erosion areas.

[0032] Here, we first need to fix the feature points to register the images before and after erosion. As mentioned earlier, the fixed feature points can be those on the fixed frame. These fixed feature points refer to the additional recognition features added when the fixed frame is made, such as a protrusion of a specific shape (rectangle, circle). By using the fixed feature points on the fixed frame, we can register the images before and after erosion (align, overlap, and match the two images to the exact same position, so that the pixel coordinates of the same point correspond exactly in both images).

[0033] Then, pooling contrast or Lab space is used to process the registered pre-erosion and post-erosion images to identify the distinguishing regions on the post-erosion image. Next, the distinguishing regions are filtered to remove unreliable parts.

[0034] Finally, the selected distinguishing areas are used as the erosion areas.

[0035] The distinguishing regions on the eroded image are the parts that may be eroded, but they need to be filtered out here because pooling contrast and Lab space have a certain probability of misjudgment. The methods for filtering distinguishing regions will be introduced when discussing pooling contrast and Lab space respectively.

[0036] After obtaining the corroded area, step S103 is executed. At this time, the corroded area needs to be classified to obtain the classification results. There are three types of classification results: planar corrosion, raised corrosion, and depressed corrosion. Planar corrosion refers to the surface of the evaluation object that only changes color, with a smooth surface, uniform brightness, and no obvious difference in brightness at the edges. Raised corrosion refers to the surface of the evaluation object that is raised, with the inner side being brighter and the outer side being darker, appearing as bumps / accumulations, and with loose texture. Depressed corrosion refers to the surface of the evaluation object that is concave, with the inner side being darker and the outer side being brighter, appearing as pits / dots, with obvious shadows.

[0037] Finally, in step S104, the area value of each category in the classification results is determined, and the corrosion evaluation result is given based on the area value of each category. The corrosion evaluation result here includes four data: corrosion area ratio, planar corrosion area ratio, raised corrosion area ratio, and recessed corrosion area ratio. The corrosion area ratio refers to the ratio of the corrosion area on the evaluation object to the total area. The planar corrosion area ratio, raised corrosion area ratio, and recessed corrosion area ratio refer to the proportion of different types of corrosion area.

[0038] The specific steps for processing the registered pre-erosion and post-erosion images using pooling contrast are as follows: S201, Use the pooling operator to traverse the registered image before erosion to obtain the first feature map; S202, the pooling operator is used to traverse the registered eroded image to obtain the second feature map; S203, compare the first feature map and the second feature map, and determine the distinguishing regions on the second feature map; S204, determine the distinct regions present in the eroded image based on the distinct regions on the second feature map; When using the pooling operator for traversal, the maximum pixel value of the region where the pooling operator is located is used as the representative value of the region where the pooling operator is located. The step size of the pooling operator is one pixel; Use statistical methods to determine the distinguishing regions on the second feature map. In steps S201 to S204, the pooling operator refers to a region with a fixed length and a fixed width, typically using 3x3 to 5x5 pixels.

[0039] The specific process of using the pooling operator to traverse the registered uncorrupted image is the pooling operator ( Figure 3 As shown, the process starts from a corner of the image before erosion (usually the top left corner) and moves by one pixel at a time. When the process reaches a position, the maximum pixel value of the region where the pooling operator is located is taken as the representative value of the region where the pooling operator is located.

[0040] The first feature map is obtained by traversing the registered pre-erosion image, and the second feature map is obtained by traversing the registered post-erosion image. Then, the first feature map and the second feature map are compared to determine the distinguishing regions on the second feature map. Finally, the distinguishing regions existing in the post-erosion image are determined based on the distinguishing regions on the second feature map.

[0041] Comparing the first feature map and the second feature map means comparing whether the representative values ​​at corresponding positions are the same. If they are the same, it means that a region on the image before erosion and a region on the image after erosion are the same, otherwise they are different.

[0042] At the same time, it is also necessary to use statistical methods to determine the distinguishing regions on the second feature map. Specifically, the step size of each movement of the pooling operator is one pixel. Therefore, when determining the distinguishing regions on the second feature map, we can count whether each pixel is included in the distinguishing region. The maximum number of times a pixel is included in the distinguishing region (the size of the pooling operator is 3x3) is 9.

[0043] Based on the above, the number of times a pixel is classified into a distinguishing region can be used to determine whether a pixel belongs to a distinguishing region.

[0044] In some possible implementations, a pixel needs to be included in the distinguishing region more than or equal to 4 times.

[0045] It should be noted that pixels at the edges need to be processed using edge augmentation. Figure 4 As shown, specifically, additional zero-value pixels are added to the edges of the images before and after erosion. Figure 4 The dashed part in the diagram is used to ensure that pixels at the edge are included in the distinguishing region the most often.

[0046] The Lab space is used to process the registered pre-erosion and post-erosion images as follows: The registered pre-erosion image is segmented to obtain multiple first image units; The registered eroded image is segmented to obtain multiple second image units, and the number of second image units is the same as that of the first image units and they correspond one-to-one. The first image unit and the second image unit corresponding to the first image unit are transferred into the Lab space to obtain the pixel brightness, red-green color components and yellow-blue color components. The total color difference value between the first image unit and the second image unit corresponding to the first image unit is calculated based on the pixel brightness, red-green color components and yellow-blue color components. The distinct regions on the etched image are determined based on the total color difference value; In the segmentation of the registered pre-erosion image and the registered post-erosion image, the step size for each segmentation is one pixel. When determining the distinguishing regions on the etched image based on the total color difference value, a statistical method is used to calibrate the distinguishing regions on the etched image.

[0047] In this method, the registered pre-erosion image and the registered post-erosion image are first segmented in the same way. Then, they are compared based on three indicators: pixel brightness, red-green color components, and yellow-blue color components. Pixel brightness is referenced by the pixel value (0-255), with larger values ​​indicating brighter pixels. For the red-green color components, the value is used as a reference, with a median value of 128 being neutral, values ​​greater than 128 being reddish, and values ​​less than 128 being greenish. For the yellow-blue color components, the value is used as a reference, with a median value of 128 being neutral, values ​​greater than 128 being yellowish, and values ​​less than 128 being bluish.

[0048] The total color difference value is calculated as follows: ; Where ΔL=L 后 L 前 Δa=a 后 a 前 Δb=b 后 b 前 . When determining the distinguishing regions on the eroded image based on the total color difference value, a statistical method is used to calibrate the distinguishing regions on the eroded image. Specifically, when segmenting the registered pre-erosion image and the registered post-erosion image, the step size for each segmentation is one pixel. At this time, a pixel can participate in a maximum of 9 judgment processes. Based on the above, the number of times a pixel is classified into a distinguishing region can be used to determine whether the pixel belongs to a distinguishing region.

[0049] In some possible implementations, a pixel needs to be included in the distinguishing region more than or equal to 4 times.

[0050] In some examples, the corroded areas are classified and the classification results are obtained in the following ways: Determine the edge contour of the corroded area; Multiple verification points were randomly selected on the edge contour of the corroded area; Select a verification area on each side of the verification point, with the two verification areas located on the inner and outer sides of the edge contour, respectively; Compare the brightness difference between the two verification areas; The classification of corrosion areas is determined based on the brightness difference. The classification results include planar corrosion, raised corrosion, and recessed corrosion.

[0051] This method determines the type of corrosion zone by examining the verification areas on both sides of the verification point. Typically, 4-8 verification points are selected. Figure 5 As shown, the size of the verification area is controlled at 9×9 or 11×11 pixels. If the brightness difference between the two verification areas (range: 10~15) is very small, the classification result is determined to be planar corrosion. If the brightness of the verification area on the inside is significantly less than that of the verification area on the outside, the classification result is determined to be concave corrosion. If the brightness of the verification area on the inside is significantly greater than that of the verification area on the outside, the classification result is determined to be convex corrosion.

[0052] This judgment method requires that at least 60%-70% of the verification areas on both sides of the verification point meet this requirement.

[0053] In addition, when comparing the brightness difference between two verification areas, the total color difference value of the verification areas is also calculated. When the total color difference between two verification areas is greater than the corresponding set reference value, the classification result of the eroded area is determined based on the brightness difference. When the total color difference between two verification areas is less than or equal to the corresponding set reference value, the etched area is classified as planar etched area.

[0054] Here, the total color difference value between the two verification areas is in the range of 30 to 35. That is, when the total color difference value between the two verification areas is greater than 30 to 35, the classification result is either raised corrosion or recessed corrosion. When the total color difference value between the two verification areas is less than 30 to 35, the classification result is planar corrosion.

[0055] In some examples, the classification results for raised corrosion and depressed corrosion are also validated. Validation of the classification results for raised corrosion and depressed corrosion includes: In the corrosion areas of raised and recessed corrosion types, look for characteristic areas, including fluffy areas and shaded areas; Corrosion areas that include fluffy areas are classified as raised corrosion, while corrosion areas that only include shaded areas are classified as sunken corrosion.

[0056] Here, the eroded areas are classified by fluffy areas and shadow areas. The fluffy areas are determined by texture features, that is, by calculating the texture features of the eroded areas. Here, two feature values ​​are selected: variance and gradient. A large variance means that the texture is messy and fluffy. The reference value here is 30 to 40 (the eroded areas are normalized to 0 to 100).

[0057] The method for determining the shadow area is based on brightness. Specifically, low-brightness areas are extracted from the eroded area. The brightness of the low-brightness areas must be less than 60% to 70% of the global average, and the minimum shadow area must be 15 to 40 pixels.

[0058] This application also provides a device for evaluating corrosion after a salt spray test, comprising: The identity verification unit is used to determine the identity information of the evaluation object and acquire the pre-corrosion image and post-corrosion image associated with the identity information of the evaluation object. The comparative analysis unit is used to analyze images before and after corrosion to determine the corrosion area; The classification processing unit is used to classify the corroded areas and obtain classification results, which include planar corrosion, raised corrosion and recessed corrosion. The result output unit is used to determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

[0059] Furthermore, the pre-corrosion and post-corrosion images were analyzed to determine the corroded areas, including: The images before and after erosion are registered using fixed feature points; The registered pre-erosion and post-erosion images are processed using pooling contrast or Lab space to identify the distinguishing regions in the post-erosion image. Filter the distinguishing regions and remove unreliable parts from them; The selected distinguishing regions are used as the erosion areas.

[0060] Furthermore, the registered pre-erosion and post-erosion images are processed using a pooling contrast method, including: The first feature map is obtained by traversing the registered uncorroded image using the pooling operator. The second feature map is obtained by traversing the registered eroded image using the pooling operator. Compare the first feature map and the second feature map to determine the distinguishing regions on the second feature map; The distinct regions present in the eroded image are determined based on the distinct regions on the second feature map; When using the pooling operator for traversal, the maximum pixel value of the region where the pooling operator is located is used as the representative value of the region where the pooling operator is located. The step size of the pooling operator is one pixel; Use statistical methods to determine the distinguishing regions on the second feature map. Furthermore, processing the registered pre-erosion and post-erosion images using Lab space includes: The registered pre-erosion image is segmented to obtain multiple first image units; The registered eroded image is segmented to obtain multiple second image units, and the number of second image units is the same as that of the first image units and they correspond one-to-one. The first image unit and the second image unit corresponding to the first image unit are transferred into the Lab space to obtain the pixel brightness, red-green color components and yellow-blue color components. The total color difference value between the first image unit and the second image unit corresponding to the first image unit is calculated based on the pixel brightness, red-green color components and yellow-blue color components. The distinct regions on the etched image are determined based on the total color difference value; In the segmentation of the registered pre-erosion image and the registered post-erosion image, the step size for each segmentation is one pixel. When determining the distinguishing regions on the etched image based on the total color difference value, a statistical method is used to calibrate the distinguishing regions on the etched image.

[0061] Furthermore, the corroded areas are classified, and the classification results include: Determine the edge contour of the corroded area; Multiple verification points were randomly selected on the edge contour of the corroded area; Select a verification area on each side of the verification point, with the two verification areas located on the inner and outer sides of the edge contour, respectively; Compare the brightness difference between the two verification areas; The classification of corrosion areas is determined based on the brightness difference. The classification results include planar corrosion, raised corrosion, and recessed corrosion.

[0062] Furthermore, when comparing the brightness difference between two verification areas, the total color difference value of the verification areas is also calculated. When the total color difference between two verification areas is greater than the corresponding set reference value, the classification result of the eroded area is determined based on the brightness difference. When the total color difference between two verification areas is less than or equal to the corresponding set reference value, the etched area is classified as planar etched area.

[0063] Furthermore, it also includes verifying the classification results for raised corrosion and pitted corrosion, which includes: In the corrosion areas of raised and recessed corrosion types, look for characteristic areas, including fluffy areas and shaded areas; Corrosion areas that include fluffy areas are classified as raised corrosion, while corrosion areas that only include shaded areas are classified as sunken corrosion.

[0064] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0065] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0066] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0067] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods 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 interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0069] 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.

[0070] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0071] It should also be understood that in the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, a first time window and a second time window are only to indicate different time windows. They should not have any effect on the time windows themselves, and the aforementioned terms "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0072] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0073] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium 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 described in the various embodiments of this application. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0074] This application also provides a corrosion evaluation system after a salt spray test, the system comprising: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory, performing the methods described above.

[0075] This application also provides a computer program product including instructions that, when executed, cause the terminal device and the network device to perform operations corresponding to the methods described above.

[0076] This application also provides a chip system including a processor for implementing the functions involved in the above description, such as generating, receiving, transmitting, or processing the data and / or information involved in the above methods.

[0077] This chip system can consist of chips or include chips and other discrete components.

[0078] The processor mentioned above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits that execute a program to control the method of transmitting the feedback information described above.

[0079] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can also be coupled to the same device.

[0080] Optionally, the computer instructions are stored in memory.

[0081] Optionally, the memory can be a storage unit within the chip, such as a register or cache. Alternatively, the memory can be a storage unit located outside the chip within the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, such as RAM.

[0082] It is understood that the memory in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0083] Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0084] Volatile memory can be RAM, which is used as an external cache. There are many different types of RAM, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory.

[0085] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for evaluating corrosion after a salt spray test, characterized in that, include: Determine the identity information of the evaluation object and obtain the pre-corrosion and post-corrosion images associated with the identity information of the evaluation object; Analyze the images before and after corrosion to determine the corrosion area; The corroded areas are classified to obtain classification results, which include planar corrosion, raised corrosion, and recessed corrosion. Determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

2. The method for evaluating corrosion after salt spray testing according to claim 1, characterized in that, The analysis of pre-corrosion and post-corrosion images and the determination of the corroded areas include: The images before and after erosion are registered using fixed feature points; The registered pre-erosion and post-erosion images are processed using pooling contrast or Lab space to identify the distinguishing regions in the post-erosion image. Filter the distinguishing regions and remove unreliable parts from them; The selected distinguishing regions are used as the erosion areas.

3. The method for evaluating corrosion after salt spray testing according to claim 2, characterized in that, The registered pre-erosion and post-erosion images were processed using a pooling contrast method, including: The first feature map is obtained by traversing the registered uncorroded image using the pooling operator. The second feature map is obtained by traversing the registered eroded image using the pooling operator. Compare the first feature map and the second feature map to determine the distinguishing regions on the second feature map; The distinct regions present in the eroded image are determined based on the distinct regions on the second feature map; When using the pooling operator for traversal, the maximum pixel value of the region where the pooling operator is located is used as the representative value of the region where the pooling operator is located. The step size of the pooling operator is one pixel; Use statistical methods to determine the distinguishing regions on the second feature map.

4. The method for evaluating corrosion after salt spray testing according to claim 2, characterized in that, Processing the registered pre-erosion and post-erosion images using Lab space includes: The registered pre-erosion image is segmented to obtain multiple first image units; The registered eroded image is segmented to obtain multiple second image units, and the number of second image units is the same as that of the first image units and they correspond one-to-one. The first image unit and the second image unit corresponding to the first image unit are transferred into the Lab space to obtain the pixel brightness, red-green color components and yellow-blue color components. The total color difference value between the first image unit and the second image unit corresponding to the first image unit is calculated based on the pixel brightness, red-green color components and yellow-blue color components. The distinct regions on the etched image are determined based on the total color difference value; In the segmentation of the registered pre-erosion image and the registered post-erosion image, the step size for each segmentation is one pixel. When determining the distinguishing regions on the etched image based on the total color difference value, a statistical method is used to calibrate the distinguishing regions on the etched image.

5. The method for evaluating corrosion after salt spray testing according to claim 1, characterized in that, The corrosion areas were classified, and the classification results included: Determine the edge contour of the corroded area; Multiple verification points were randomly selected on the edge contour of the corroded area; Select a verification area on each side of the verification point, with the two verification areas located on the inner and outer sides of the edge contour, respectively; Compare the brightness difference between the two verification areas; The classification of corrosion areas is determined based on the brightness difference. The classification results include planar corrosion, raised corrosion, and recessed corrosion.

6. The method for evaluating corrosion after salt spray testing according to claim 5, characterized in that, When comparing the brightness difference between two verification areas, the total color difference value of the verification areas is also calculated. When the total color difference between two verification areas is greater than the corresponding set reference value, the classification result of the eroded area is determined based on the brightness difference. When the total color difference between two verification areas is less than or equal to the corresponding set reference value, the etched area is classified as planar etched area.

7. The method for evaluating corrosion after salt spray testing according to claim 5, characterized in that, This also includes validating the classification results for raised corrosion and pitted corrosion. The validation of the classification results for raised corrosion and pitted corrosion includes: In the corrosion areas of raised and recessed corrosion types, look for characteristic areas, including fluffy areas and shaded areas; Corrosion areas that include fluffy areas are classified as raised corrosion, while corrosion areas that only include shaded areas are classified as sunken corrosion.

8. A corrosion evaluation device after a salt spray test, characterized in that, include: The identity verification unit is used to determine the identity information of the evaluation object and acquire the pre-corrosion image and post-corrosion image associated with the identity information of the evaluation object. The comparative analysis unit is used to analyze images before and after corrosion to determine the corrosion area; The classification processing unit is used to classify the corroded areas and obtain classification results, which include planar corrosion, raised corrosion and recessed corrosion. The result output unit is used to determine the area value of each category in the classification results and give the corrosion evaluation result based on the area value of each category.

9. A corrosion evaluation system for use after salt spray testing, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by the processor, executes the method as described in any one of claims 1 to 7.

Images