A method for image recognition and calibration processing of equipment nameplates

Abstract

The present invention discloses a method for image recognition and calibration processing of equipment nameplates, which relates to the technical field of image processing. The present invention obtains a nameplate image set of a target power equipment, screens the image set according to a preset method to obtain a first image set, further screens the first image set according to status data to obtain a second image set, transforms each image in the second image set to obtain a front-view image set, obtains a final calibrated image according to the front-view image set, and performs image recognition on the final calibrated image to determine the nameplate information of the power equipment. In this way, the obtained nameplate images of the target power equipment are corrected during recognition, so that the possibility of extracting errors or missing information in the final calibrated image is small, and the impact on the accuracy and efficiency of equipment management and maintenance is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method for identifying and calibrating an image of an equipment nameplate. Background Art

[0002] The nameplate of a power equipment is a label that identifies the basic information of the equipment, usually including the equipment name, manufacturer information, technical parameters, production date, product number, certification mark, and precautions. These information are crucial for the correct installation, operation, and maintenance of the equipment; by taking an image of the power equipment nameplate and performing identification and analysis on the captured image of the power equipment nameplate, the nameplate information can be digitally recorded and archived, improving the information management efficiency, ensuring data accuracy, supporting remote management and quick fault troubleshooting, and contributing to the efficient tracking, maintenance, and overall management of the equipment.

[0003] During the actual process of taking an image of a power equipment nameplate, it may be affected by various factors, resulting in poor image quality and being unable to reflect the equipment information in detail and accurately. In this case, directly performing identification and analysis on the captured image may lead to incorrect data extraction or information loss, affecting the accuracy and efficiency of equipment management and maintenance. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems, and a method for identifying and calibrating an image of an equipment nameplate is proposed.

[0005] The present invention proposes a method for identifying and calibrating an image of an equipment nameplate, and the method includes:

[0006] Obtain a nameplate image set of a target power equipment, and screen the image set according to a preset method to obtain a first image set;

[0007] For the first image set, extract the status data of each image, obtain a status coefficient according to the status data, and determine a second image set according to the image corresponding to the status coefficient; the status data includes brightness uniformity, image clarity, and feature matching integrity;

[0008] For each image in the second image set, determine its key points, and transform the image according to the key points to obtain a front-view image set;

[0009] For each image in the front-view image set, establish a new coordinate system, and perform position correction on each pixel point according to the status of the actual object corresponding to the key points to obtain the position coordinates of each pixel point. Obtain a final calibrated image according to the position coordinates of each pixel point, and perform image recognition on the final calibrated image to determine the power equipment nameplate information.

[0010] Optionally, screening the image set according to a preset method to obtain a first image set includes:

[0011] Place each image in the image set under preset image feature processing conditions to obtain a processed image set;

[0012] For the processed image set, obtain the values of each feature of each image before and after processing, and obtain the change rate of the feature based on the values before and after processing;

[0013] Compare the change rate of each feature of the image with the preset normal feature change rate range. If the change rates of all features of the image are within the preset normal feature change rate range, mark the image as the first available image;

[0014] If the change rate of any feature of the image is not within the preset normal feature change rate range, mark the image as the first unavailable image;

[0015] Use all the first available images in the image set as the first image set.

[0016] Optionally, for the first image set, extract the status data of each image, including:

[0017] The status data includes brightness uniformity, and the method for obtaining the brightness uniformity is:

[0018] Convert each image in the first image set into a grayscale image, and calculate the brightness mean value of the grayscale image. The calculation formula is:

[0019]

[0020] In the formula, μ is the brightness mean value, M is the number of rows of the image, N is the number of columns of the image, and I ij is the brightness value of the pixel at the i-th row and j-th column in the grayscale image;

[0021] Calculate the brightness value variance of the grayscale image based on each pixel brightness value and the brightness mean value, and record the reciprocal of the variance as the brightness uniformity. The calculation formula is:

[0022]

[0023] In the formula, E B is the variance of the changing image, and the brightness uniformity

[0024] Optionally, the status data includes image sharpness, and the method for obtaining the image sharpness is:

[0025] Apply the Laplace operator to each image in the first image set to obtain a transformed image L;

[0026] Calculate the pixel mean value of the transformed image L. The calculation formula is:

[0027]

[0028] Wherein, μL is the pixel mean value of the image after Laplace transform, A is the number of rows of the image after Laplace transform, D is the number of columns of the image after Laplace transform, and L ab is the pixel value of the image after Laplace transform at the position (a, b);

[0029] Calculate the variance of the image after Laplace transform, and the calculation formula can be:

[0030]

[0031] Take the variance of the image after Laplace transform as the image sharpness Etk, Etk = Var(L).

[0032] Optionally, the state data includes the feature matching integrity, and the acquisition method of the feature matching integrity is:

[0033] For each image in the first image set, use the feature point detection algorithm to detect the key feature points in the image as the to-be-detected image feature points;

[0034] Use the matching algorithm to calculate the feature point matching pairs between the to-be-detected image and the reference image as the feature point matching quantity;

[0035] Divide the feature point matching quantity of each image by the total number of to-be-detected image feature points to obtain the feature matching integrity, and the calculation formula is: Ews = qa / nk, where Ews is the feature matching integrity, qa is the feature point matching quantity, and nk is the total number of to-be-detected image feature points.

[0036] Optionally, obtain the state coefficient according to the state data, and determine the second image set according to the image corresponding to the state coefficient, including:

[0037] The state data includes the brightness uniformity, the image sharpness and the feature matching integrity. Normalize the state data including the brightness uniformity, the image sharpness and the feature matching integrity, and obtain the state coefficient according to the normalized state data. The calculation formula is,

[0038]

[0039] Wherein, Pgt is the state coefficient, Efd, Etk and Ews respectively represent the brightness uniformity, the image sharpness and the feature matching integrity, b1, b2, b3 are the proportionality coefficients of the brightness uniformity, the image sharpness and the feature matching integrity, and b1, b2, b3 are all greater than 0;

[0040] Compare the status coefficient with the preset status coefficient threshold. If the status coefficient is not less than the preset status coefficient threshold, record the image corresponding to the status coefficient as the second available image;

[0041] If the status coefficient is less than the preset status coefficient threshold, record the image corresponding to the status coefficient as the second unavailable image;

[0042] Use all the first available images in the first image set as the second image set.

[0043] Optionally, transform the images according to the key points, and the obtained front-facing image set includes:

[0044] Mark the key points of each image in the second image set, denoted as marked key points;

[0045] Based on the marked key points, use perspective transformation to calculate the transformation matrix for the image to be transformed from the current angle to the front-facing angle, and transform each image according to the calculated transformation matrix to obtain the front-facing angle image of the image;

[0046] Use the front-facing angle image of each image in the second image set as a new image set to obtain the front-facing image set.

[0047] Optionally, perform position correction on each pixel point according to the state of the actual object corresponding to the key point to obtain the position coordinates of each pixel point, and obtain the final calibrated image according to the position coordinates of each pixel point, including:

[0048] For each image in the front-facing image set, use the pixel coordinates corresponding to a certain key point as the new coordinate center, and establish a new coordinate system based on the new coordinate center;

[0049] Map the pixel point corresponding to the center in the new coordinate system to the actual power equipment nameplate, and establish a coordinate system for the actual power equipment nameplate according to several key points, denoted as the actual coordinate system, and the center of the actual coordinate system is the key point corresponding to the new coordinate center;

[0050] Obtain the coordinates of the four corner points of the image in the actual coordinate system and the coordinates of the four corner points in the new coordinate system, and calculate the scaling ratio according to the coordinates in the new coordinate system and the coordinates in the actual coordinate system;

[0051] Obtain the coordinates of the position of the power equipment nameplate corresponding to each pixel point of each image in the new coordinate system in the actual coordinate system, and determine the coordinates of each pixel point in the new coordinate system according to the coordinates in the actual coordinate system and the scaling ratio to obtain the corrected image of the image;

[0052] Obtain the corrected image of each image in the frontal image set, overlap the images with the same new coordinate system, calculate the average value of the coordinates of the same pixel points as the final position coordinates of the pixel points, calculate the final position coordinates of each pixel point, and obtain the final corrected image.

[0053] Advantages of the present invention:

[0054] The present invention proposes a method for identifying and calibrating the image of an equipment nameplate. By obtaining the nameplate image sets of multiple target power equipment, screening the image sets according to a preset method to obtain the first image set, further screening the first image set according to the status data to obtain the second image set, transforming each image in the second image set to obtain the frontal image set, obtaining the final calibrated image according to the frontal image set, and performing image recognition on the final calibrated image to determine the nameplate information of the power equipment. In this way, the obtained nameplate images of the target power equipment are corrected during recognition, so that the final calibrated image has less extraction error or information loss, reducing the impact on the accuracy and efficiency of equipment management and maintenance. Description of the drawings

[0055] The following further describes the present invention with reference to the drawings.

[0056] Figure 1 It is a flowchart of a method for identifying and calibrating the image of an equipment nameplate provided by the present invention. Detailed implementation manners

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0058] Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] The embodiments of the present invention provide a method for identifying and calibrating the image of an equipment nameplate. Refer to Figure 1 , Figure 1 It is a flowchart of a method for identifying and calibrating the image of an equipment nameplate provided by the embodiments of the present invention. The method includes the following steps:

[0060] Obtain the nameplate image sets of the target power equipment, and screen the image sets according to a preset method to obtain the first image set;

[0061] For the first image set, extract the status data of each image, obtain the status coefficient according to the status data, and determine the second image set according to the image corresponding to the status coefficient;

[0062] For each image in the second image set, determine its key points, and transform the image according to the key points to obtain the front-facing image set;

[0063] For each image in the front-facing image set, establish a new coordinate system, and perform position correction on each pixel point according to the status of the actual object corresponding to the key point to obtain the position coordinates of each pixel point. Obtain the final calibrated image according to the position coordinates of each pixel point, and perform image recognition on the final calibrated image to determine the nameplate information of the power equipment.

[0064] Based on a method for image recognition and calibration processing of an equipment nameplate provided by an embodiment of the present invention, in the above manner, the nameplate image of the target power equipment obtained is corrected during recognition, so that the final calibrated image can have less extraction errors or information loss, and reduce the impact on the accuracy and efficiency of equipment management and maintenance.

[0065] In one embodiment, screening the image set according to a preset method to obtain the first image set includes:

[0066] Place each image in the image set under preset image feature processing conditions to obtain a processed image set;

[0067] For the processed image set, obtain the values of each feature of each image before and after processing, and obtain the change rate of the feature according to the values before and after processing;

[0068] Compare the change rate of each feature of the image with the preset normal feature change rate range. If the change rates of all features of the image are within the preset normal feature change rate range, mark the image as the first available image;

[0069] If the change rate of any feature of the image is not within the preset normal feature change rate range, mark the image as the first unavailable image;

[0070] Use all the first available images in the image set as the first image set.

[0071] It should be noted that the preset image feature processing conditions are set by professionals according to the actual situation, such as edge detection, contrast enhancement, noise removal, etc., and may also include other methods, which are not limited here; in addition, the preset normal feature change rate range is also set by professionals according to the actual situation, and is not specifically limited.

[0072] For example: Assume there are two images, A and B. Now, under the preset image feature processing conditions for A and B, the preset normal feature change rate ranges are as follows:

[0073] Number of edge pixels: The change rate is between 0.2 and 0.5;

[0074] Contrast value: The change rate is between 0.5 and 0.8;

[0075] Noise level: The change rate is between -0.3 and -0.1;

[0076] Screening of initially available images:

[0077] Processing process of image A,

[0078] Edge detection: Original image: Number of edge pixels = 800;

[0079] Processed image: Number of edge pixels = 960;

[0080] Change rate: (960 - 800) / 800 = 0.2;

[0081] Contrast enhancement: Original image: Contrast value = 0.4;

[0082] Processed image: Contrast value = 0.7;

[0083] Change rate: (0.7 - 0.4) / 0.4 = 0.75;

[0084] Noise removal: Original image: Noise level = 0.6;

[0085] Processed image: Noise level = 0.45;

[0086] Change rate: (0.45 - 0.6) / 0.6 = -0.25;

[0087] Change rate results of image A: Change rate of number of edge pixels: 0.2 (within the normal range);

[0088] Change rate of contrast value: 0.75 (within the normal range);

[0089] Change rate of noise level: -0.25 (within the normal range);

[0090] Therefore, image A meets the normal change range of all processing conditions and is marked as an initially available image.

[0091] Processing process of image B, edge detection, original image: Number of edge pixels = 900;

[0092] Processed image: Number of edge pixels = 1400;

[0093] Rate of change: (1400 - 900) / 900 = 0.56;

[0094] Contrast enhancement, original image: contrast value = 0.5; processed image: contrast value = 1.0; rate of change: (1.0 - 0.5) / 0.5 = 1.0

[0095] Noise removal, original image: noise level = 0.7; processed image: noise level = 0.6 Rate of change: (0.6 - 0.7) / 0.7 = -0.14;

[0096] Rate of change results for Image B; rate of change of the number of edge pixels: 0.56 (outside the normal range);

[0097] Rate of change of contrast value: 1.0 (outside the normal range);

[0098] Rate of change of noise level: -0.14 (within the normal range);

[0099] Since both the rate of change of the number of edge pixels and the rate of change of the contrast value of Image B are outside the normal range, it is marked as an unusable image.

[0100] In one implementation, if, under preset image feature processing conditions, the rate of change of the basic feature values of an image conforms to common sense and is within the preset normal feature rate of change range, this means that the image performs well under these processing conditions, has consistency and reliability. Therefore, such an image can be considered initially usable and is more likely to identify useful information in subsequent calibration processing. This method evaluates various features of an image through multiple preset processing conditions and determines whether the image is within a reasonable range through the rate of change of the feature values. This multi-dimensional screening method can not only filter out images that perform abnormally under certain specific processing conditions but also comprehensively evaluate the overall quality of the image under different processing conditions, thereby screening out a set of images with higher quality and suitable for further processing. In this way, it is possible to effectively reduce the interference of invalid images and improve the accuracy and efficiency of subsequent image processing and analysis.

[0101] In one embodiment, for the first image set, the state data extracted for each image includes:

[0102] The state data includes brightness uniformity, and the method for obtaining brightness uniformity is:

[0103] Convert each image in the first image set into a grayscale image and calculate the brightness mean value of the grayscale image. The calculation formula is:

[0104]

[0105] Wherein, μ is the average brightness, M is the number of rows of the image, N is the number of columns of the image, and I ij is the brightness value of the pixel at the i-th row and j-th column in the grayscale image;

[0106] Calculate the variance of the brightness value of the grayscale image based on the brightness value of each pixel and the average brightness, and denote the reciprocal of the variance as the brightness uniformity. The calculation formula is:

[0107]

[0108] Wherein, E B is the variance of the transformed image, and the brightness uniformity

[0109] It should be noted that the larger the brightness uniformity Efd, the more uniform the brightness of the corresponding image of the power equipment nameplate being photographed. This is particularly important for the photographed image of the power equipment nameplate because a uniform brightness distribution helps the stability and accuracy of subsequent image processing and information extraction. In practical applications, an image with a higher brightness uniformity can ensure that the text and symbols on the nameplate are clearly visible, and there will be no information loss or difficulty in recognition due to local over-dark or over-bright areas. It can more accurately identify and extract the key features on the power equipment nameplate, which further improves the efficiency and accuracy of image processing and ensures that the final corrected image has high-quality available information.

[0110] In one implementation manner, through the above method, the calculated brightness uniformity is more accurate and can more precisely reflect the brightness uniformity of the photographed image of the power equipment nameplate, and further screen out the images that can identify effective information.

[0111] In one embodiment, the status data includes image sharpness. The method for obtaining the image sharpness is:

[0112] Apply the Laplace operator to each image in the first image set to obtain the transformed image L;

[0113] Calculate the pixel mean of the transformed image L. The calculation formula is:

[0114]

[0115] Wherein, μL is the pixel mean of the image after Laplace transform, A is the number of rows of the image after Laplace transform, D is the number of columns of the image after Laplace transform, and L ab is the pixel value of the image after Laplace transform at the position (a, b);

[0116] Calculate the variance of the image after Laplace transform. The calculation formula can be:

[0117]

[0118] The variance of the image after Laplace transform is used as the image sharpness Etk, and Etk = Var(L).

[0119] It should be noted that the greater the image sharpness, the clearer the corresponding image of the power equipment nameplate captured. This is especially important for the captured images of power equipment nameplates because clear images can capture and identify the text, symbols, and other important information on the nameplate more accurately. During the management and maintenance process of power equipment, the information on the nameplate is a key data source for equipment identification, parameter query, and maintenance records. If the image is not clear, it may lead to blurred text, difficult-to-identify symbols, increasing the difficulty of information entry and recognition, and even causing misreading and incorrect records; high-definition images help improve the effectiveness of subsequent image processing algorithms, such as character recognition and feature extraction. These algorithms usually perform more stably and accurately on clear images, and can extract the key information on the nameplate more reliably, ensuring the efficient progress of the management and maintenance work of power equipment. At the same time, clear images also have higher availability and reference value in archiving and long-term storage, facilitating future reference and verification.

[0120] In one implementation method, through the above method, the calculated image sharpness is more accurate and can more precisely reflect the clarity of the image of the power equipment nameplate captured, further screening out the images that can identify effective information.

[0121] In one embodiment, the status data includes the feature matching completeness, and the method for obtaining the feature matching completeness is as follows:

[0122] For each image in the first image set, use the feature point detection algorithm to detect the key feature points in the image as the to-be-tested image feature points;

[0123] Use the matching algorithm to calculate the feature point matching pairs between the to-be-tested image and the reference image as the feature point matching quantity;

[0124] Divide the feature point matching quantity of each image by the total number of to-be-tested image feature points to obtain the feature matching completeness. The calculation formula is: Ews = qa / nk, where Ews is the feature matching completeness, qa is the feature point matching quantity, and nk is the total number of to-be-tested image feature points.

[0125] It should be noted that the reference image is set by professional personnel according to the actual situation, and there is no specific limitation; the feature point detection algorithm can be, for example, SIFT or SURF, and the matching algorithm can be, for example, KNN, BFMatcher, which can be specifically selected and applied according to the actual situation, without specific limitation and elaboration.

[0126] It should be noted that the greater the feature matching completeness, the more key features are included in the corresponding photographed power equipment nameplate. This is especially important for the photographed images of power equipment nameplates because the nameplate usually contains key information such as the equipment model, serial number, manufacturer information, technical parameters, etc. These information are important bases for equipment identification, maintenance, and management. If the feature matching degree in the image is high, it means that the photographed image contains more key features of the nameplate, which helps to improve the accuracy and reliability of subsequent processing such as character recognition (OCR) and feature extraction. Complete feature matching can also ensure the accuracy of the image during comparison and archiving, thus ensuring the integrity and traceability of the information. Images with high feature matching degrees can more effectively support the management work of power equipment, reduce errors and omissions, and improve work efficiency.

[0127] In one implementation method, through the above method, the calculated feature matching completeness of the image is more accurate and can more accurately reflect the inclusion degree of the key features of the photographed power equipment nameplate image, further screening out the images that can identify valid information.

[0128] In one embodiment, a state coefficient is obtained according to the state data, and the second image set is determined according to the image corresponding to the state coefficient, including:

[0129] The state data includes brightness uniformity, image clarity, and feature matching completeness. The state data including brightness uniformity, image clarity, and feature matching completeness is normalized, and a state coefficient is obtained according to the normalized state data. The calculation formula is

[0130]

[0131] In the formula, Pgt is the state coefficient, Efd, Etk, and Ews respectively represent brightness uniformity, image clarity, and feature matching completeness, b1, b2, and b3 are the proportionality coefficients of brightness uniformity, image clarity, and feature matching completeness, and b1, b2, and b3 are all greater than 0;

[0132] The state coefficient is compared with a preset state coefficient threshold. If the state coefficient is not less than the preset state coefficient threshold, the image corresponding to the state coefficient is recorded as the second available image;

[0133] If the state coefficient is less than the preset state coefficient threshold, the image corresponding to the state coefficient is recorded as the second unavailable image;

[0134] All the first available images in the first image set are used as the second image set.

[0135] In one implementation method, the preset state coefficient threshold is set by professionals according to the actual situation, and specific details are not limited and will not be elaborated.

[0136] In one implementation method, through the above method, the second image set screened from the first image set ensures the quality and consistency of the images. This screening method based on brightness uniformity, image clarity, and feature matching integrity can effectively filter out images that do not meet the standards, thereby improving the accuracy and efficiency of subsequent processing and analysis. The images screened in this way are not only clearer and more uniform in visual effect, but also contain more key features, ensuring the integrity and reliability of the nameplate information. This is of great significance for the management, maintenance, and data archiving of power equipment, and can significantly reduce misreading and incorrect records caused by image quality problems, improving the working efficiency and data accuracy of the entire system.

[0137] In one embodiment, the images are transformed according to key points, and the obtained front-view image set includes:

[0138] Mark the key points of each image in the second image set, denoted as marked key points;

[0139] Based on the marked key points, use perspective transformation to calculate the transformation matrix for converting the image from the current angle to the front-view angle, and transform each image according to the calculated transformation matrix to obtain the front-view angle image of the image;

[0140] Take the front-view angle image of each image in the second image set as a new image set to obtain the front-view image set.

[0141] It should be noted that correcting the image to the front-view angle image can be:

[0142] 1. Mark key points: Determine the key points on the power equipment nameplate image. These key points can be the four corners of the nameplate or other obvious marking points. The selection of key points should ensure that they can be accurately located in all images.

[0143] 2. Calculate the transformation matrix: Use an image processing algorithm (such as perspective transformation) to calculate the transformation matrix for converting the image from the current angle to the front-view angle. This matrix needs to be calculated based on the marked key points.

[0144] 3. Apply the transformation: Use the calculated transformation matrix to transform each image so that the nameplate appears at the front-view angle in the image.

[0145] For example, assume a nameplate image. By marking its four corner points and calculating the perspective transformation matrix, the following are the specific steps:

[0146] Mark key points. Assume the corner point coordinates of the original image: upper left corner (100, 150), upper right corner (400, 120), lower right corner (420, 300), lower left corner (110, 320);

[0147] Calculate the transformation matrix: The size of the target image is (500, 400).

[0148] Coordinates of the target points: Upper left corner (0, 0), upper right corner (500, 0), lower right corner (500, 400), lower left corner (0, 400);

[0149] Apply the transformation: Use the perspective transformation algorithm to calculate the transformation matrix, and apply the transformation matrix to the original image to obtain an image with a front-facing view angle.

[0150] Use the front-facing view angle image of each image in the second image set as a new image set to obtain a front-facing image set.

[0151] In one implementation, through the above method, each image in the second image set is converted into an image with a front-facing view angle. In this way, the consistency, readability, and recognition accuracy of the images are significantly improved, the subsequent processing process is simplified, the data storage and retrieval are optimized, and this process ensures that the information on the nameplate of the power equipment is clear and complete, providing a reliable basis for subsequent image processing and information extraction, thereby greatly improving the overall work efficiency and the accuracy of data processing.

[0152] In one embodiment, perform position correction on each pixel point according to the state of the actual object corresponding to the key point to obtain the position coordinates of each pixel point, and obtain the final calibrated image according to the position coordinates of each pixel point, including:

[0153] For each image in the front-facing image set, use the new coordinate center of the pixel coordinates corresponding to a certain key point, and establish a new coordinate system based on the new coordinate center;

[0154] Map the pixel point corresponding to the center in the new coordinate system to the actual nameplate of the power equipment, and establish a coordinate system for the actual nameplate of the power equipment according to several key points, denoted as the actual coordinate system, and the center of the actual coordinate system is the key point corresponding to the new coordinate center;

[0155] Obtain the coordinates of the four corner points of the image in the actual coordinate system and the coordinates of the four corner points in the new coordinate system, and calculate the scaling ratio according to the coordinates in the new coordinate system and the coordinates in the actual coordinate system;

[0156] Obtain the coordinates of the position of the power equipment nameplate corresponding to each pixel point in the new coordinate system in the actual coordinate system, and determine the coordinates of each pixel point in the new coordinate system according to the coordinates in the actual coordinate system and the scaling ratio to obtain the corrected image of the image;

[0157] Obtain the corrected image of each image in the frontal image set, overlap the images with the same new coordinate system, calculate the average value of the coordinates of the same pixel points as the final position coordinates of the pixel points, calculate the final position coordinates of each pixel point, and obtain the final corrected image.

[0158] In one implementation, a certain key point is generally set as the four corner points of the image. These four corner points are located at the four corners of the image (such as the upper left corner, the upper right corner, the lower left corner, and the lower right corner). These points are set as the key points of the new coordinate system. Selecting these corner points is usually the most obvious and easily recognizable points. The positions of these points in the image are fixed and not easily interfered by other objects or noises, making them stable reference points. When the corner points are used as key points, it is easier to calculate the scaling ratio and other geometric transformations of the image. Through the coordinates of the corner points, the width and height of the image, as well as other transformation parameters such as the rotation angle and scaling ratio, can be directly calculated, so as to perform accurate correction.

[0159] In one implementation, the final corrected image obtained through the above method has high precision and consistency. Through accurate coordinate mapping and scaling ratio calculation of the key points, geometric correction of the image is realized. The position of each pixel point is calculated by the average value of multiple images, reducing noise and errors, thus providing a more accurate and consistent image view. This corrected image can effectively improve the recognition and analysis accuracy of the nameplate of power equipment, and improve the reliability and efficiency of image processing.

[0160] The above has described an embodiment of the present invention in detail, but the content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for equipment nameplate image recognition and calibration, characterized in that: The following steps are involved: Acquire a nameplate image set of a target electric power device, and filter the image set according to a preset method to obtain a first image set; For the first image set, extract state data of each image, obtain a state coefficient according to the state data, and determine the second image set according to the image corresponding to the state coefficient; the state data includes brightness uniformity, image clarity and feature matching completeness; For each image in the second image set, determine its key point, and transform the image according to the key point to obtain a front view image set; For each image in the front-view image set, a new coordinate system is established, and the position of each pixel is corrected according to the state of the actual object corresponding to the key point to obtain the position coordinates of each pixel. The final calibrated image is obtained based on the position coordinates of each pixel, and image recognition is performed on the final calibrated image to determine the nameplate information of the power equipment.

2. The method for calibrating and processing equipment nameplate images according to claim 1, characterized in that: The first image set is obtained by screening the image set according to a preset method, including: Subjecting each image in the image set to a preset image feature processing condition to obtain a processed image set; For the processed image set, obtain the value of each feature of each image before and after processing, and obtain the change rate of the feature according to the value before and after processing; Comparing the change rate of each feature of the image with a preset normal feature change rate range, and if the change rates of all features of the image are within the preset normal feature change rate range, marking the image as a first usable image; If the change rate of any feature of the image is not within the preset normal feature change rate range, marking the image as a first unusable image; Take all first available images in the image set as the first image set.

3. The method for equipment nameplate image recognition and calibration according to claim 1, characterized in that: For the first set of images, extracting status data of each image includes: The state data includes brightness uniformity, and the method for obtaining the brightness uniformity is: Each image in the first image set is converted into a grayscale image, and the brightness mean of the grayscale image is calculated using the formula: In the formula, μ is the mean brightness, M is the number of rows in the image, N is the number of columns in the image, and I ij is the brightness value of the pixel in the i-th row and j-th column in the grayscale image; The brightness variance of the grayscale image is calculated based on the brightness value of each pixel and the brightness mean, and the inverse of the variance is recorded as the brightness uniformity. The calculation formula is: In the formula, E B is the variance of the changing image, brightness uniformity 4. The method for calibrating and processing equipment nameplate images according to claim 3, characterized in that: The state data includes image clarity, and the method for obtaining the image clarity is: Applying the Laplacian operator to each image in the first image set to obtain a transformed image L; Calculate the pixel mean of the transformed image L, and the calculation formula is: Where μL is the pixel mean of the image after Laplace transformation, A is the number of rows of the image after Laplace transformation, D is the number of columns of the image after Laplace transformation, and L is ab is the pixel value of the image at position (a, b) after Laplace transformation; Calculate the variance of the image after Laplace transformation. The calculation formula can be: The variance of the image after Laplace transformation is taken as the image clarity Etk, Etk=Var(L).

5. The method for calibrating and processing equipment nameplate images according to claim 3, characterized in that: The state data includes feature matching completeness, and the method for obtaining the feature matching completeness is: For each image in the first image set, a feature point detection algorithm is used to detect key feature points in the image as feature points of the image to be tested; Using a matching algorithm to calculate the feature point matching pairs between the image to be tested and the reference image as the number of feature point matching; The feature matching completeness is obtained by dividing the number of feature point matches of each image by the total number of feature points of the image to be tested. The calculation formula is: Ews=qa / nk, where Ews is the feature matching completeness, qa is the number of feature point matches, and nk is the total number of feature points of the image to be tested.

6. The method for calibrating and processing equipment nameplate images according to claim 1, characterized in that: Obtaining a state coefficient according to the state data, and determining a second image set according to an image corresponding to the state coefficient includes: The state data includes brightness uniformity, image clarity and feature matching completeness. The state data including brightness uniformity, image clarity and feature matching completeness are normalized, and the state coefficient is obtained according to the normalized state data. The calculation formula is: Where Pgt is the state coefficient, Efd, Etk and Ews represent brightness uniformity, image clarity and feature matching completeness respectively, b1, b2 and b3 are the proportional coefficients of brightness uniformity, image clarity and feature matching completeness, and b1, b2 and b3 are all greater than 0; Compare the state coefficient with a preset state coefficient threshold, and if the state coefficient is not less than the preset state coefficient threshold, record the image corresponding to the state coefficient as the second available image; If the state coefficient is less than a preset state coefficient threshold, the image corresponding to the state coefficient is recorded as a second unusable image; All first available images in the first image set are taken as the second image set.

7. The method for equipment nameplate image recognition and calibration according to claim 1, characterized in that: The image is transformed according to the key points, and the orthographic image set includes: Marking the key points of each image in the second image set as marked key points; Based on the marked key points, use perspective transformation to calculate the transformation matrix of the image from the current angle to the orthographic angle, and transform each image according to the calculated transformation matrix to obtain the orthographic angle image of the image; The front-view angle image of each image in the second image set is taken as a new image set to obtain a front-view image set.

8. The method for calibrating and processing equipment nameplate images according to claim 1, characterized in that: According to the state of the actual object corresponding to the key point, each pixel point is positionally corrected to obtain the position coordinates of each pixel point. The final calibration image is obtained according to the position coordinates of each pixel point, including: For each image in the orthographic image set, the pixel coordinates corresponding to a key point are changed to the new coordinate circle center, and a new coordinate system is established based on the new coordinate circle center; Mapping the pixel points corresponding to the origin in the new coordinate system to the actual nameplate of the electric power equipment, and establishing a coordinate system for the actual nameplate of the electric power equipment according to a number of key points, recorded as the actual coordinate system, the origin of the actual coordinate system is the key point corresponding to the origin of the new coordinate system; Get the coordinates of the four corner points of the image in the actual coordinate system, the coordinates of the four corner points in the new coordinate system, and calculate the scaling ratio based on the coordinates in the new coordinate system and the coordinates in the actual coordinate system; Obtain the coordinates of the electric equipment nameplate position corresponding to each pixel point of each image in the new coordinate system in the actual coordinate system, and determine the coordinates of each pixel point in the new coordinate system according to the coordinates in the actual coordinate system and the scaling ratio to obtain a corrected image of the image; Obtain the corrected image of each image in the orthographic image set, and overlap the images with the same new coordinate system, calculate the average value of the coordinates of the same pixel points as the final position coordinates of the pixel points, calculate the final position coordinates of each pixel point, and obtain the final corrected image.

Images