Structured extraction method and system for nameplate information of power equipment

Abstract

The invention discloses a power equipment nameplate information structured extraction method and system, and relates to the technical field of image processing. Obtaining an original image set of the power equipment, and determining a target area of the nameplate for any original image; calculating the offset of the ghost area relative to the main body area, determining the reinforcement weight of the ghost area according to the offset, and performing optimization operation on the target area to obtain a target image; performing region division on each target image to obtain a target region set, performing quality evaluation on regions in the target image set, and reserving and splicing the regions meeting a preset condition to obtain an enhanced image; and nameplate text information in the enhanced image is extracted, and the nameplate text information is stored in a structured form. Through accurate positioning of the target area, calculation of ghosting offset and enhancement processing, and area quality evaluation and intelligent splicing, the identification precision of nameplate text information is significantly improved, and the accuracy of power equipment information acquisition is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a method and system for extracting structured nameplate information of electric equipment. Background Art

[0002] The nameplate of power equipment is a direct identification of the equipment's identity and characteristics. It carries important information such as the equipment's basic information, technical parameters, operating conditions, and safety warnings. It is an indispensable basis for guiding equipment selection, installation, operation and maintenance, fault analysis, and safety management. It not only helps operators quickly understand equipment performance and ensure that the equipment operates efficiently and stably under appropriate conditions, but also provides key references when overhauling, replacing, or upgrading equipment, thus promoting the overall reliability, economy, and safety of the power system.

[0003] The staff used image processing technology, optical character recognition, and natural language processing to efficiently and accurately extract the information on the nameplate of the power equipment. This process converts the text, numbers, and symbols on the nameplate into editable and searchable structured data through automated scanning, recognition, and analysis, greatly facilitating the storage, management, and analysis of data, and improving the convenience and efficiency of the management and maintenance of power equipment.

[0004] During actual operation, the nameplate information of the power equipment cannot be accurately focused due to the vibration of the equipment operation, the captured image is prone to afterimages, and the nameplate information cannot be accurately identified. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that the nameplate information of electric equipment cannot be accurately focused due to the vibration of the equipment operation, and the captured image is prone to afterimage, and a method and system for structured extraction of nameplate information of electric equipment is proposed.

[0006] In a first aspect of the present invention, a method for extracting structured nameplate information of electric equipment is first proposed, the method comprising:

[0007] Obtaining an original image set of the power equipment, and determining a target area of ​​the nameplate for any original image; the target area includes: a main body area and an afterimage area;

[0008] Calculating the offset of the residual image area relative to the main area, determining the enhancement weight of the residual image area according to the offset, and performing an optimization operation on the target area to obtain a target image;

[0009] Divide each target image into regions to obtain a target region set, perform quality assessment on the regions in the target image set, retain the regions that meet preset conditions and splice them to obtain an enhanced image;

[0010] The nameplate text information in the enhanced image is extracted, and the nameplate text information is stored in a structured form.

[0011] Optionally, calculating the offset of the afterimage area in the target area relative to the main area, the method includes:

[0012] Identify the positioning anchor point in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area;

[0013] The number of afterimage areas is determined based on the coordinates of the positioning anchor point.

[0014] Optionally, determining the enhancement weight of the residual image area according to the offset, the method includes:

[0015] Convert each residual image area into a grayscale image, identify the pixel gradient area of ​​the grayscale image, and if there is a continuous area in the pixel gradient area, determine the area as an edge area;

[0016] Calculating the pixel difference of the edge area, and if the pixel difference satisfies the gradient threshold, retaining the residual image area to obtain an edge area set;

[0017] The image weights in the edge region set are determined according to the offset, and the edge is enhanced according to the image weight to obtain a repaired image.

[0018] Optionally, performing an optimization operation on the target area to obtain a target image, the method includes:

[0019] Determine an edge enhancement coefficient of the main body area according to the repaired image, and modify an edge enhancement range of the main body area according to the edge enhancement coefficient;

[0020]

[0021] Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

[0022] Optionally, performing quality assessment on a region in the target image set, the method includes:

[0023] Acquire information identification data, and perform quality assessment on the area in the target image set by using a quality assessment formula; the information identification data includes: meaningless information data, invalid information extraction times, and total information extraction times;

[0024] Quality assessment formula:

[0025]

[0026] Among them, PSNRX is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

[0027] In a second aspect of the present invention, a system for extracting structured nameplate information of electric equipment is proposed, including: the system includes: an image acquisition module, an image enhancement module, an image stitching module and an information storage module:

[0028] The image acquisition module is used to acquire an original image set of the electric power equipment and determine a target area of ​​the nameplate for any original image; the target area includes: a main body area and an afterimage area;

[0029] The image enhancement module is used to calculate the offset of the residual image area relative to the main area, determine the enhancement weight of the residual image area according to the offset, and perform an optimization operation on the target area to obtain a target image;

[0030] The image stitching module is used to divide each target image into regions to obtain a target region set, perform quality assessment on the regions in the target image set, retain the regions that meet the preset conditions and stitch them to obtain an enhanced image;

[0031] The information storage module is used to extract the nameplate text information in the enhanced image and store the nameplate text information in a structured form.

[0032] Optionally, the image enhancement module includes: an offset calculation module and an afterimage quantity determination module:

[0033] The offset calculation module is used to identify the positioning anchor point in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area;

[0034] The afterimage quantity determination module is used to determine the quantity of the afterimage areas according to the coordinates of the positioning anchor point.

[0035] Optionally, the image enhancement module includes: an edge judgment module, an edge screening module and an edge enhancement module:

[0036] The edge judgment module is used to convert each residual image area into a grayscale image, identify the pixel gradient area of ​​the grayscale image, and if there is a continuous area in the pixel gradient area, then the area is judged as an edge area;

[0037] The edge screening module is used to calculate the pixel difference of the edge area, and if the pixel difference meets the gradient threshold, the residual image area is retained to obtain an edge area set;

[0038] The edge enhancement module is used to determine the image weight in the edge region set according to the offset, and perform edge enhancement according to the image weight to obtain a restored image.

[0039] Optionally, the image enhancement module includes: an edge coefficient enhancement module:

[0040] The edge coefficient enhancement module is used to determine the edge enhancement coefficient of the main area according to the repaired image, and to correct the edge enhancement range of the main area according to the edge enhancement coefficient;

[0041]

[0042] Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

[0043] Optionally, the image stitching module includes: a quality assessment module:

[0044] The quality assessment module is used to obtain information identification data and perform quality assessment on the area in the target image set through a quality assessment formula; the information identification data includes: meaningless information data, invalid information extraction times and total information extraction times;

[0045] Quality assessment formula:

[0046]

[0047] Among them, PSNR X is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

[0048] Beneficial effects of the present invention:

[0049] The present invention proposes a structured extraction method for nameplate information of electric equipment, which obtains the original image set of the electric equipment, determines the target area of ​​the nameplate for any original image; calculates the offset of the residual image area relative to the main area, determines the enhancement weight of the residual image area according to the offset, and performs optimization operations on the target area to obtain the target image; divides each target image into regions to obtain a target region set, performs quality assessment on the regions in the target image set, retains and splices the regions that meet the preset conditions to obtain an enhanced image; extracts the nameplate text information in the enhanced image, and stores the nameplate text information in a structured form. By accurately locating the target area, calculating the residual image offset and enhancing the processing, regional quality assessment and intelligent splicing, the recognition accuracy of the nameplate text information is significantly improved, and the accuracy of obtaining the electric equipment information is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present invention will be further described below in conjunction with the accompanying drawings.

[0051] Figure 1 A flowchart of a method for structured extraction of nameplate information of electric equipment is provided for an embodiment of the present invention;

[0052] Figure 2 A structural schematic diagram of a system for extracting structured nameplate information of electric equipment is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the present invention, the description of "first", "second", etc. is only used for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0054] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0055] The embodiment of the present invention provides a method for extracting structured nameplate information of electric equipment. Figure 1 , Figure 1 A flowchart of a method for extracting structured nameplate information of electric equipment provided by an embodiment of the present invention. The method comprises the following steps:

[0056] S101, obtaining an original image set of electric power equipment, and determining a target area of ​​a nameplate for any original image.

[0057] S102, calculating the offset of the residual image area relative to the main area, determining the enhancement weight of the residual image area according to the offset, and performing an optimization operation on the target area to obtain a target image.

[0058] S103, dividing each target image into regions to obtain a target region set, performing quality assessment on the regions in the target image set, retaining the regions that meet preset conditions and splicing them to obtain an enhanced image.

[0059] S104, extracting the nameplate text information in the enhanced image, and storing the nameplate text information in a structured form.

[0060] The target area includes: the main area and the residual image area.

[0061] A structured extraction method for nameplate information of electric equipment provided in an embodiment of the present invention significantly improves the recognition accuracy of nameplate text information and the accuracy of obtaining electric equipment information by accurately locating the target area, calculating the residual image offset and enhancing the processing, regional quality assessment and intelligent splicing.

[0062] In one implementation, there are a main area and an afterimage area. The main area is an image area with obvious pixel values, but the edges of the image area become blurred due to jitter; the pixel values ​​of the afterimage area are poor, but the edges are clearer; the nameplate is generally white text on a black background or black text on a white background, but it may turn yellow due to long-term use. Converting it into a grayscale image can avoid this defect.

[0063] In one implementation, the positioning anchor point is the installation point or fixed point of the nameplate of the power equipment, which has significant features on the image and is easy for the machine to recognize. The target area of ​​the nameplate is determined for any original image, and the position of the nameplate can be determined by identifying the positioning anchor point.

[0064] In one implementation, the original image set of the power equipment is generally taken by a camera; the main area and the residual image area will only undergo horizontal displacement, wherein the horizontal displacement only includes: up and down displacement and left and right displacement.

[0065] In one implementation, an optimization operation is performed on the target area to obtain a target image. The optimization operation may be sharpening filtering, histogram equalization, contrast enhancement, and frequency domain enhancement.

[0066] In one implementation, these scattered but critical information on the nameplate are converted into a structured data format that can be understood by computers through technical means, such as OCR recognition and natural language processing. This process not only improves the efficiency of data processing, but also makes these data more convenient to use in equipment management, troubleshooting, data analysis and other aspects. Through structured extraction, power companies can establish detailed equipment archives and realize the full life cycle management of equipment. At the same time, based on these structured data, companies can also conduct data analysis, explore potential problems in equipment operation, optimize equipment maintenance strategies, and improve the reliability and economy of equipment operation. The structured extraction of power equipment nameplate information is an important part of the modernization and intelligence of power equipment management, and is of great significance to improving the level of power equipment management and ensuring the safe and stable operation of the power grid.

[0067] In one embodiment, step S102 includes:

[0068] Identify the positioning anchor points in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area.

[0069] The number of afterimage areas is determined based on the coordinates of the positioning anchor point.

[0070] In one implementation method, any positioning anchor point in the main area is used as the coordinate origin, and the displacement of the positioning anchor point on the horizontal plane, that is, the position of the positioning anchor point in the afterimage area, is calculated. The offset is obtained by calculating the distance between the two positioning anchor points, that is, the distance between the positioning anchor point in the afterimage area and the coordinate origin in the main area. The two positioning anchor points must be one-to-one corresponding.

[0071] In one implementation, the number of afterimage areas is determined based on the coordinates of the positioning anchor point. Since each positioning anchor point in the main area can be used as a coordinate origin, an afterimage area can be located through the coordinates of the positioning anchor point. When there are different coordinates, the position and number of the afterimage areas can be determined based on the number of coordinates. For example, the coordinates (-1, 2), (3, 4) represent that there are two afterimage areas.

[0072] In one implementation method, if the afterimage area overlaps too much with the main area, resulting in the positioning anchor point of the afterimage area being unable to be identified, the afterimage area can be discarded. If only a portion overlaps, the recognizable positioning anchor point is calculated, and the corresponding positioning anchor point in the main area is calculated to obtain the offset.

[0073] In one embodiment, step S102 includes:

[0074] Each afterimage area is converted into a grayscale image, and the pixel gradient area of ​​the grayscale image is identified. If there is a continuous area in the pixel gradient area, the area is determined to be an edge area.

[0075] The pixel difference of the edge area is calculated. If the pixel difference meets the gradient threshold, the residual image area is retained to obtain the edge area set.

[0076] The image weights in the edge region set are determined according to the offset, and the edge is enhanced according to the image weights to obtain a repaired image.

[0077] In one implementation, the pixel gradient region in the grayscale image refers to the region where the grayscale value of the pixels in the grayscale image changes significantly, that is, the region with a large grayscale gradient; for example, in a grayscale image, the edge is where the grayscale value of the pixel changes suddenly, that is, the region with a large grayscale gradient. Therefore, the pixel gradient region often corresponds to the edge, texture and other feature regions of the image, which is conducive to machine recognition and judgment of the edge region in the grayscale image.

[0078] In one implementation, there is a continuous area in the pixel gradient area, which is the judgment condition for the edge area. If it is discontinuous, it may be a noise point, causing machine recognition errors; the continuous area must meet the preset length and be an uninterrupted linear interval and have a pixel gradient.

[0079] In one implementation, the image weight in the edge region set is determined based on the offset. The larger the offset, the smaller the weight. Edges farther away are more blurred and do not have good enhancement conditions. On the contrary, the smaller the offset, the greater the weight.

[0080] In one embodiment, step S102 further includes:

[0081] The edge enhancement coefficient of the main area is determined according to the repaired image, and the edge enhancement range of the main area is corrected according to the edge enhancement coefficient.

[0082]

[0083] Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

[0084] In one implementation, because the camera takes multiple original images, there are also many repaired images, and the number of repaired images is determined by the number of original images; d1 is the edge distance of the main area, that is, the distance of the area with blurred edges in the main area, for example: the pixel value of this area has flexible changes, and it is generally a gradient image in human vision, and the length of this area is the edge distance of the main area.

[0085] In one implementation, the sharpening parameters can be adjusted through the edge enhancement coefficient, for example: correcting the sharpening radius. The larger the sharpening radius, the wider the area affected by the sharpening, and the more intuitive the edge clarity effect. However, too large a radius may cause a halo effect on the edge, blurring the image details, so it needs to be corrected.

[0086] In one embodiment, step S103 includes:

[0087] Obtain information recognition data and perform quality assessment on the area in the target image set using a quality assessment formula; the information recognition data includes: meaningless information data, invalid information extraction times, and total information extraction times.

[0088] Quality assessment formula:

[0089]

[0090] Among them, PSNR X is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

[0091] In one implementation, PSNR is a commonly used image quality assessment indicator, namely peak signal-to-noise ratio, which is used to measure the quality of image restoration; PSNR X is the modified peak signal-to-noise ratio, S is the number of invalid information extraction times, that is, the number of times the machine cannot recognize the information; W is the proportion of meaningless information, that is, the recognized information is garbled and has no meaning or valid meaning.

[0092] In one implementation, MSE is the mean square error, and the formula is Where M and N are the width and height of the image, respectively. qp is the pixel value of the original image at position (q, p), K qp is the pixel value at position (q, p) after the image is enhanced.

[0093] In one implementation, the original image set contains multiple original images, and the optimized target images also have the same number. For example, if there are five original images, then there are also five target images. Each target image is cut and divided in equal proportion to obtain a target region set. A position label is added to each image during the division to facilitate subsequent stitching operations. When stitching, if there are multiple optimal regions for each region, the region with the highest score is used. If the score of any region does not meet the preset conditions, the region with the highest score is retained.

[0094] Based on the same inventive concept, the embodiment of the present invention also provides a system for extracting structured nameplate information of electric equipment. Figure 2 , Figure 2 A schematic diagram of the structure of a system for extracting structured nameplate information of electric equipment provided by an embodiment of the present invention includes: an image acquisition module, an image enhancement module, an image stitching module and an information storage module:

[0095] The image acquisition module is used to acquire the original image set of the power equipment and determine the target area of ​​the nameplate for any original image; the target area includes: a main body area and an afterimage area.

[0096] The image enhancement module is used to calculate the offset of the residual image area relative to the main area, determine the enhancement weight of the residual image area according to the offset, and perform optimization operations on the target area to obtain the target image.

[0097] The image stitching module is used to divide each target image into regions to obtain a target region set, perform quality assessment on the regions in the target image set, retain the regions that meet the preset conditions and stitch them together to obtain an enhanced image.

[0098] The information storage module is used to extract the nameplate text information in the enhanced image and store the nameplate text information in a structured form.

[0099] A system for extracting structured nameplate information of electric equipment provided in an embodiment of the present invention significantly improves the recognition accuracy of nameplate text information and the accuracy of obtaining electric equipment information by accurately locating the target area, calculating the residual image offset and enhancing the processing, regional quality assessment and intelligent splicing.

[0100] In one embodiment, the image enhancement module includes: an offset calculation module and an afterimage quantity determination module:

[0101] The offset calculation module is used to identify the positioning anchor point in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area.

[0102] The afterimage quantity determination module is used to determine the quantity of afterimage areas according to the coordinates of the positioning anchor point.

[0103] In one embodiment, the image enhancement module includes: an edge judgment module, an edge screening module and an edge enhancement module:

[0104] The edge judgment module is used to convert each residual image area into a grayscale image, identify the pixel gradient area of ​​the grayscale image, and if there is a continuous area in the pixel gradient area, the area is judged as an edge area.

[0105] The edge screening module is used to calculate the pixel difference of the edge area. If the pixel difference meets the gradient threshold, the residual image area is retained to obtain the edge area set.

[0106] The edge enhancement module is used to determine the image weight in the edge region set according to the offset, and to perform edge enhancement according to the image weight to obtain a repaired image.

[0107] In one embodiment, the image enhancement module includes: an edge coefficient enhancement module:

[0108] The edge coefficient enhancement module is used to determine the edge enhancement coefficient of the main area according to the repaired image, and to correct the edge enhancement range of the main area according to the edge enhancement coefficient.

[0109]

[0110] Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

[0111] In one embodiment, the image stitching module includes: a quality assessment module:

[0112] The quality assessment module is used to obtain information recognition data and perform quality assessment on the area in the target image set through a quality assessment formula; the information recognition data includes: meaningless information data, invalid information extraction times and total information extraction times.

[0113] Quality assessment formula:

[0114]

[0115] Among them, PSNR X is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

[0116] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for extracting structured nameplate information of electric power equipment, characterized in that: The method comprises: Acquire an original image set of the electric power equipment, and determine a target area of ​​the nameplate for any original image; The target areas include: main body area and residual image area; Calculating the offset of the residual image area relative to the main area, determining the enhancement weight of the residual image area according to the offset, and performing an optimization operation on the target area to obtain a target image; Divide each target image into regions to obtain a target region set, perform quality assessment on the regions in the target image set, retain the regions that meet preset conditions and splice them to obtain an enhanced image; The nameplate text information in the enhanced image is extracted, and the nameplate text information is stored in a structured form.

2. A method for extracting structured nameplate information of electric power equipment according to claim 1, characterized in that: Calculating the offset of the residual image area in the target area relative to the main area, the method includes: Identify the positioning anchor point in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area; The number of afterimage areas is determined based on the coordinates of the positioning anchor point.

3. A method for extracting structured nameplate information of electric power equipment according to claim 1, characterized in that: Determining the enhancement weight of the residual image area according to the offset, the method includes: Convert each residual image area into a grayscale image, identify the pixel gradient area of ​​the grayscale image, and if there is a continuous area in the pixel gradient area, determine the area as an edge area; Calculating the pixel difference of the edge area, and if the pixel difference satisfies the gradient threshold, retaining the residual image area to obtain an edge area set; The image weights in the edge region set are determined according to the offset, and the edge is enhanced according to the image weight to obtain a repaired image.

4. A method for extracting structured nameplate information of electric power equipment according to claim 1, characterized in that: Performing an optimization operation on a target area to obtain a target image, the method comprising: Determine an edge enhancement coefficient of the main body area according to the repaired image, and modify an edge enhancement range of the main body area according to the edge enhancement coefficient; Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

5. The method for extracting structured nameplate information of electric power equipment according to claim 1, characterized in that: Performing quality assessment on the area in the target image set, the method comprising: Acquire information identification data, and perform quality assessment on the area in the target image set by using a quality assessment formula; the information identification data includes: meaningless information data, invalid information extraction times, and total information extraction times; Quality assessment formula: Among them, PSNR X is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

6. A system for extracting structured nameplate information of electric power equipment, characterized in that: The system includes: an image acquisition module, an image enhancement module, an image stitching module and an information storage module: The image acquisition module is used to acquire an original image set of the electric power equipment and determine a target area of ​​the nameplate for any original image; the target area includes: a main body area and an afterimage area; The image enhancement module is used to calculate the offset of the residual image area relative to the main area, determine the enhancement weight of the residual image area according to the offset, and perform an optimization operation on the target area to obtain a target image; The image stitching module is used to divide each target image into regions to obtain a target region set, perform quality assessment on the regions in the target image set, retain the regions that meet the preset conditions and stitch them to obtain an enhanced image; The information storage module is used to extract the nameplate text information in the enhanced image and store the nameplate text information in a structured form.

7. A system for extracting structured nameplate information of electric power equipment according to claim 6, characterized in that: The image enhancement module includes: an offset calculation module and an afterimage quantity determination module: The offset calculation module is used to identify the positioning anchor point in the target area, take any positioning anchor point in the main area as the coordinate origin, and calculate the offset of the positioning anchor point in the residual image area; The afterimage quantity determination module is used to determine the quantity of the afterimage areas according to the coordinates of the positioning anchor point.

8. A system for extracting structured nameplate information of electric power equipment according to claim 6, characterized in that: The image enhancement module includes: an edge judgment module, an edge screening module and an edge enhancement module: The edge judgment module is used to convert each residual image area into a grayscale image, identify the pixel gradient area of ​​the grayscale image, and if there is a continuous area in the pixel gradient area, then the area is judged as an edge area; The edge screening module is used to calculate the pixel difference of the edge area, and if the pixel difference meets the gradient threshold, the residual image area is retained to obtain an edge area set; The edge enhancement module is used to determine the image weight in the edge region set according to the offset, and perform edge enhancement according to the image weight to obtain a restored image.

9. A system for extracting structured nameplate information of electric power equipment according to claim 6, characterized in that: The image enhancement module includes: an edge coefficient enhancement module: The edge coefficient enhancement module is used to determine the edge enhancement coefficient of the main area according to the repaired image, and to correct the edge enhancement range of the main area according to the edge enhancement coefficient; Among them, F is the edge enhancement coefficient, d1 is the edge distance of the main area, d2 is the edge distance of the repaired image, and j is the number of repaired images.

10. A system for extracting structured nameplate information of electric power equipment according to claim 6, characterized in that: The image stitching module includes: a quality assessment module: The quality assessment module is used to obtain information identification data and perform quality assessment on the area in the target image set through a quality assessment formula; the information identification data includes: meaningless information data, invalid information extraction times and total information extraction times; Quality assessment formula: Among them, PSNR X is the regional quality score, MAX is the maximum possible pixel value of the current image, MSE is the mean square error, W is the proportion of meaningless information, S is the number of invalid information extraction, and Z is the total number of information extraction.

Images