Ring main unit group instrument reading method based on image processing

Abstract

The present invention relates to the field of image processing technology, and more specifically, to a ring main unit group meter reading method based on image processing, the method comprising: collecting a dial image, dividing the dial image into a plurality of blocks; obtaining the degree of influence of edge sawtooth noise on each block according to the grayscale value change degree in each block and the grayscale value of each pixel point on the grayscale change sequence of each block; obtaining the degree of abnormality of the pixel points in each block according to the representative pixel points of each block and the degree of influence of the edge sawtooth noise on each block; adjusting the grayscale value of each pixel point in each block according to the abnormality of the pixel points in each block to obtain the corrected grayscale value of each pixel point in each block; obtaining an enhanced image and identifying data in the dial according to the corrected grayscale value of each pixel point in each block. The present invention corrects the edge sawtooth noise in the dial image and improves the accuracy of dial reading.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more specifically, to a ring main unit group meter reading method based on image processing. Background Art

[0002] The ring main unit group instrument reading method based on image processing is a technology that uses computer vision technology to automatically identify and read the readings of various instruments in the ring main unit. This method has many advantages and functions in the power industry. Traditional instrument readings usually rely on manual inspection and recording, which is not only time-consuming and labor-intensive, but also prone to errors. Through image processing technology, the instrument readings can be accurately identified to improve accuracy and reliability, avoiding errors that may occur during manual readings, especially in complex or low-light environments. This technology can improve the accuracy of readings and can realize real-time monitoring of the status of each instrument in the ring main unit and timely detect abnormal situations. Therefore, a ring main unit group instrument reading method based on image processing is proposed.

[0003] The patent application document with the publication number CN104939859A discloses a CT image correction method. The method uses a neighboring point difference algorithm to correct bad pixels and establishes an image tailing attenuation model.

[0004] In the ring main unit group meter reading, in order to make the reading more accurate and the data on the dial more accurate, the adjacent point difference algorithm in the above method is used to enlarge the RGB image of the dial to obtain the dial image to identify the data on the dial. However, since the nearest point interpolation method does not take into account the change trend of the surrounding pixels when determining the new pixel value, the pixel transition at the edge of the obtained dial image is unnatural, resulting in edge jagged noise, which reduces the accuracy of the reading and makes it impossible to detect abnormal situations in time, which is not conducive to preventing accidents and ensuring the safety of the power grid. Summary of the invention

[0005] In order to solve the problem that the nearest point interpolation method does not take into account the change trend of surrounding pixels when determining the new pixel value, resulting in edge jagged noise in the obtained dial image, which reduces the accuracy of the reading, the present invention proposes a ring main unit group meter reading method based on image processing, which includes the following steps:

[0006] Collect the dial image; divide the dial image into multiple blocks; obtain the degree of influence of edge jagged noise on each block; obtain the degree of abnormality of the pixel points in each block , Represents the degree of abnormality of the pixel in the i-th block; Represents the number of pixels in the i-th block; Represents the degree to which the i-th block is affected by edge jagged noise; Represents the mean of the absolute values ​​of the grayscale differences between all adjacent representative pixels of the i-th block; Represents the gray value of the jth pixel in the i-th block; Represents the grayscale value of the first pixel of the jth pixel in the ith block in the gradient change direction of the ith block; norm() represents the normalization function; || represents the absolute value symbol; Get the corrected grayscale value of each pixel in each block:

[0007] , represents the corrected gray value of the jth pixel in the i-th block; Represents the reference grayscale value of the i-th block; represents the degree of abnormality of the jth pixel in the ith block; the image composed of the corrected grayscale value of each pixel in each block is used as the enhanced image; edge detection is performed on the enhanced image to identify the data in the dial.

[0008] The innovation of the present invention lies in dividing the dial image into multiple blocks, obtaining the degree of abnormality of each pixel in each block, correcting the grayscale value of each pixel in each block, and obtaining the corrected grayscale value of each pixel in each block, thereby correcting the edge aliasing noise generated at the edge of the dial image, improving the accuracy of subsequent readings, and facilitating timely detection of abnormal situations, which is beneficial to accident prevention and protection of power grid safety; further, the degree of abnormality of each pixel in each block is obtained based on the degree to which each block is affected by the edge aliasing noise, and can accurately reflect the degree to which each pixel in the dial image is affected by the edge aliasing noise.

[0009] Preferably, obtaining the degree to which each block is affected by edge jagged noise includes:

[0010] ;

[0011] In the formula, Represents the degree to which the i-th block is affected by edge jagged noise; Represents the degree of change of gray value in the i-th block; Represents the number of pixels in the mth grayscale change sequence in the i-th block; Represents the number of grayscale change sequences of the i-th block; Represents the gray value of the kth pixel in the mth grayscale change sequence in the ith block; Represents the gray value of the first pixel in the gradient direction of the k-th pixel in the m-th grayscale change sequence in the ith block; Represents the grayscale value of the first pixel in the opposite direction of the gradient direction of the kth pixel in the mth grayscale change sequence in the ith block; || represents the absolute value sign.

[0012] It is convenient to obtain the degree of abnormality of the pixel points in each block according to the degree of influence of the edge aliasing noise on each block, correct the grayscale value of the pixel points, and reduce the influence of the edge aliasing noise.

[0013] Preferably, the acquisition of the gray value change degree includes:

[0014] ;

[0015] in, Represents the degree of change of gray value in the i-th block; Represents the gray value variance of all pixels in the i-th block; Represents the gradient value of the jth pixel in the i-th block; Represents the number of pixels in the i-th block.

[0016] The greater the change in the grayscale value, the more likely the block is affected by edge aliasing noise. The degree to which each block is affected by edge aliasing noise can be obtained based on the change in the grayscale value in the block.

[0017] Preferably, the acquisition of the grayscale change sequence includes:

[0018] For any block, an empty grayscale change sequence is preset in the block, and the pixel point with the maximum gradient value is taken as the first pixel point in the grayscale change sequence. The first pixel point in the gradient direction of the most recently supplemented pixel point is selected in turn to supplement the grayscale change sequence until the most recently supplemented pixel point is no longer in the block, and the supplementation is stopped; and so on, each grayscale change sequence in the block is obtained; there are no identical pixels between the first pixels in the grayscale change sequences.

[0019] Preferably, the acquisition of the gradual change direction includes:

[0020] The mean value of the gradient directions of all pixels in the first grayscale change sequence of the ith block is taken as the gradient change direction of the ith block.

[0021] Preferably, the acquisition of the representative pixel point includes:

[0022] The blocks adjacent to the i-th block are taken as the adjacent blocks of the i-th block, the central pixel of the i-th block is obtained, the pixel points of the central pixel of the i-th block in the gradual change direction of the i-th block and the pixel points in the opposite direction of the gradual change direction of the i-th block are obtained, and are recorded as the changed pixel points of the i-th block, and the pixel points located in the adjacent blocks of the i-th block among the changed pixel points of the i-th block are recorded as the representative pixel points of the i-th block.

[0023] Preferably, the acquisition of the reference grayscale value includes:

[0024] Among the adjacent blocks of the i-th block, obtain the adjacent block with the lowest degree of abnormality as the reference block of the i-th block, obtain the distance between each pixel point in the reference block of the i-th block and the central pixel point of the i-th block, and record the grayscale value of the pixel point in the reference block of the i-th block corresponding to the minimum distance as the reference grayscale value of the i-th block.

[0025] This facilitates the subsequent correction of the grayscale value of each pixel in each block according to the reference grayscale value of each block.

[0026] Preferably, dividing the dial image into a plurality of blocks comprises:

[0027] Preset block size , divide the dial image into several pieces of size of blocks.

[0028] This is helpful for the subsequent analysis of the degree to which each block is affected by edge jagged noise.

[0029] The present invention has the following beneficial effects: the purpose of the present invention is to first divide the dial image into multiple blocks, obtain the degree of abnormality of each pixel in each block, correct the grayscale value of the pixel, obtain the corrected grayscale value of each pixel in each block, constitute an enhanced image, correct the edge aliasing noise generated at the edge of the dial image, improve the accuracy of subsequent readings, facilitate timely detection of abnormal situations, and help prevent accidents and ensure the safety of the power grid; further, the degree of abnormality of each pixel in each block is obtained according to the degree to which each block is affected by the edge aliasing noise, which can accurately reflect the degree to which each pixel in the dial image is affected by the edge aliasing noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0031] Figure 1 It is a flowchart of the steps of a ring main unit group meter reading method based on image processing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] 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 part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0034] See also Figure 1 , which shows a flowchart of a method for reading a ring main unit group meter based on image processing according to an embodiment of the present invention, the method comprising the following steps:

[0035] S001. Collect dial images.

[0036] In an embodiment of the present invention, a high-definition camera is used to capture the image of the ring main unit group instrument, a semantic segmentation algorithm is used to segment the dial area in the ring main unit group instrument image, recorded as a dial RGB image, and the nearest point difference algorithm is used to enlarge the dial RGB image, and the enlarged dial RGB image is grayed to obtain a dial image. It should be noted that the semantic segmentation algorithm and the nearest point difference algorithm are both prior arts, and in the embodiment of the present invention, they will not be described in detail.

[0037] S002. Divide the dial image into several blocks, obtain the degree of change of the grayscale value in each block, and obtain several grayscale change sequences of each block; according to the degree of change of the grayscale value in each block and the grayscale value of the pixel point in each grayscale change sequence of each block, obtain the degree of influence of the edge aliasing noise on each block.

[0038] It should be noted that in order to make the data in the dial more accurate, the dial RGB image is amplified using the neighboring point difference algorithm to obtain the dial image to identify the data in the dial. However, since the nearest point interpolation method does not take into account the changing trend of the surrounding pixels when determining the new pixel value, the pixel transition at the edge of the obtained dial image is unnatural, resulting in edge jagged noise, which reduces the accuracy of the reading and makes it impossible to detect abnormal situations in time, which is not conducive to preventing accidents and ensuring the safety of the power grid. Therefore, the purpose of the present invention is to correct the edge jagged noise in the dial image and improve the accuracy of the reading.

[0039] It should be further explained that the dial image is first divided into several blocks. If the grayscale fluctuation of the pixels in any block is relatively large and the gradient value is relatively large, it means that the grayscale value edge degree of the block is relatively large, which means that the block is more likely to be affected by edge aliasing noise.

[0040] In the embodiment of the present invention, the dial image is divided into a plurality of In the embodiment of the present invention, the size of the preset block In other embodiments, the implementer may preset The value of .

[0041] Get the degree of grayscale value change in each block:

[0042] ;

[0043] In the formula, Represents the degree of change of gray value in the i-th block; Represents the gray value variance of all pixels in the i-th block; Represents the gradient value of the jth pixel in the i-th block; Represents the number of pixels in the i-th block; The larger the value of , the greater the degree of change in the grayscale value in the i-th block, which means that the i-th block is more likely to be affected by edge jagged noise.

[0044] It should be noted that since there is a gradient indicator bar in the dial image, the grayscale value variation in the blocks located in the indicator bar area is also relatively large. That is to say, if the grayscale value variation in any block in the dial image is large, it means that the block may be affected by edge aliasing noise, or it may be because the block is in the gradient indicator bar area in the dial image. Therefore, these two situations cannot be distinguished only based on the grayscale value variation in each block.

[0045] It should be further explained that when any block is affected by edge aliasing noise, the pixels in the block will show a gradient. This gradient is due to the fact that the aliasing noise destroys the originally smooth edge, causing the pixel value to gradually transition within a certain range. For example, in a transition area from black to white, if it is affected by edge aliasing noise, the pixels in this transition area will no longer change smoothly from black to white, but will show some irregular gradients. Therefore, at the junction of a black and white area, if there is a gradient area affected by aliasing noise, then the color of the pixels in the part of this gradient area close to the junction of the black and white areas may quickly transition from white to gray and then to black. That is, the difference in grayscale values ​​between adjacent pixels is very obvious. This gradient area In the part near the non-junction, the color transition of the pixels is relatively slow, that is, the difference in grayscale values ​​between adjacent pixels is relatively small. Therefore, when any block is affected by edge aliasing noise, the change amplitude of the grayscale values ​​between the pixels in the gradient direction of the block is relatively large; when any block is not affected by edge aliasing noise, but the gradient change occurs due to the gradient color indicator bar existing in the dial image itself, the gradient change produced in this case is more regular, and the change rhythm has a uniform change trend, that is, the change amplitude of the grayscale values ​​between the pixels in the gradient direction of the block is relatively uniform; therefore, the gradient change direction of the pixels in each block and the change amplitude of the grayscale values ​​between the pixels in the gradient direction are analyzed to obtain the degree of influence of the edge aliasing noise on each block.

[0046] In the embodiment of the present invention, the pixel with the largest gradient value in the i-th block is taken as the first target pixel of the i-th block; if the first pixel in the gradient direction of the first target pixel belongs to the i-th block, the first pixel in the gradient direction of the first target pixel is recorded as the first reference point of the first target pixel; if the first pixel in the gradient direction of the first reference point of the first target pixel belongs to the i-th block, the first pixel in the gradient direction of the first reference point of the first target pixel is recorded as the second reference point of the first target pixel, and so on until the pixel does not belong to the i-th block, thereby obtaining the first grayscale change sequence of the i-th block;

[0047] If there are other pixels in the i-th block except the pixels in the first grayscale change sequence of the i-th block, obtain the pixel with the largest gradient value except the pixels in the first grayscale change sequence in the i-th block, and record it as the second target pixel. If the first pixel in the gradient direction of the second target pixel belongs to the i-th block, then the first pixel in the gradient direction of the second target pixel is recorded as the first reference point of the second target pixel. If the first pixel in the gradient direction of the first reference point of the second target pixel belongs to the i-th block, then the first pixel in the gradient direction of the first reference point of the second target pixel is recorded as the second reference point of the second target pixel. This process is repeated until the pixel does not belong to the i-th block, and the second grayscale change sequence of the i-th block is obtained.

[0048] By analogy, if there are other pixels in the i-th block except the pixels in the first grayscale change sequence and the second grayscale change sequence of the i-th block, continue to obtain the third grayscale change sequence of the i-th block until every pixel in the i-th block has its own grayscale change sequence, and then stop, and several grayscale change sequences of the i-th block are obtained.

[0049] Get the degree to which each block is affected by edge aliasing noise:

[0050]

[0051] In the formula, Represents the degree to which the i-th block is affected by edge jagged noise; Represents the degree of change of gray value in the i-th block; Represents the number of pixels in the mth grayscale change sequence in the i-th block; Represents the number of grayscale change sequences of the i-th block; Represents the gray value of the kth pixel in the mth grayscale change sequence in the ith block; Represents the gray value of the first pixel in the gradient direction of the k-th pixel in the m-th grayscale change sequence in the ith block; Represents the grayscale value of the first pixel in the opposite direction of the gradient direction of the kth pixel in the mth grayscale change sequence in the ith block; || represents the absolute value sign.

[0052] S003. Obtain the gradient change direction of each block, and obtain the representative pixel of each block according to the gradient change direction of each block and the adjacent blocks of each block; obtain the degree of abnormality of the pixel points in each block according to the representative pixel points of each block and the degree of influence of the edge jagged noise on each block.

[0053] It should be noted that the degree to which each block is affected by edge aliasing noise is obtained based on the characteristics of the individual block. However, if the edge aliasing noise in the block is not obvious, it may cause misjudgment. It is known that if any block is affected by edge aliasing noise, the surrounding area of ​​the block may be a pure color area, that is, an area of ​​a single color, and the grayscale difference between pixels in the pure color area is 0; when any block is not affected by edge aliasing noise, but a gradual change occurs due to the gradient color indicator bar existing in the dial image itself, the surrounding area of ​​the block is more likely to be an area of ​​the same type, the grayscale gradient change is consistent, and there is a certain grayscale difference between the pixels. Therefore, the present invention obtains the adjacent blocks of each block, analyzes the grayscale values ​​between the pixels in each block and its adjacent blocks, and obtains the abnormality of the pixels in each block.

[0054] In the embodiment of the present invention, the average value of the gradient directions of all pixels in the first grayscale change sequence of the i-th block is used as the gradual change direction of the i-th block.

[0055] The blocks adjacent to the ith block are taken as adjacent blocks of the ith block, the central pixel of the ith block is obtained, the pixel points of the central pixel of the ith block in the direction of the gradual change of the ith block and the pixel points in the opposite direction of the gradual change of the ith block are obtained, which are recorded as the changed pixel points of the ith block, and the pixel points of the changed pixel points of the ith block that are located in the adjacent blocks of the ith block are recorded as the representative pixel points of the ith block;

[0056] Get the degree of abnormality of the pixels in each block:

[0057]

[0058] In the formula, Represents the degree of abnormality of the pixel in the i-th block; Represents the number of pixels in the i-th block; Represents the degree to which the i-th block is affected by edge jagged noise; Represents the mean of the absolute values ​​of the grayscale differences between all adjacent representative pixels of the i-th block; Represents the gray value of the jth pixel in the i-th block; Represents the grayscale value of the first pixel of the j-th pixel in the i-th block in the gradient change direction of the i-th block; The larger the value of is, the greater the impact of edge jagged noise on the i-th block is, and the greater the degree of abnormality of the pixels in the i-th block is; The larger the value of is, the greater the change in the grayscale value of the pixel in the ith block is, which means that the ith block is more affected by the edge jagged noise and the greater the abnormality of the pixel in the ith block is. The smaller the value of is, the more likely it is that the adjacent blocks of the ith block contain pure color areas, which means that the ith block is more affected by edge jagged noise. The larger the value of , the more it indicates that the i-th block and its adjacent blocks are located in the gradient color indicator bar area that exists in the dial image itself; The larger the value of is, the more affected the i-th block is by the edge jagged noise, and the greater the abnormality of the pixels in the i-th block is.

[0059] S004. Adjust the grayscale value of each pixel in each block according to the degree of abnormality of the pixel in each block to obtain a corrected grayscale value of each pixel in each block; obtain an enhanced image according to the corrected grayscale value of each pixel in each block; and identify the data in the dial according to the enhanced image.

[0060] It should be noted that the aberration degree of the pixels in each block is known, that is, the aberration degree of each pixel in each block. When the aberration degree of any pixel in any block is larger, it means that the pixel in the block is more likely to be affected by the edge jagged noise. At this time, the grayscale value of the pixel in the block needs to be adjusted according to the aberration degree of the pixel in the block.

[0061] It should be further explained that, since pixels with small aberrations are pixels that are not affected by aliasing noise, and pixels that are closer to the block are closer to the features of the pixels in the block, a pixel with small aberrations and closer to the block is first selected from the adjacent blocks of each block as the reference grayscale value of the block. If the grayscale value of the pixel in the block is greater than the reference grayscale value of the block, the grayscale value of the pixel in the block needs to be reduced to be close to the grayscale value of a normal pixel, and the reduction range is the product of the grayscale value of the pixel in the block and its aberration. If the grayscale value of the pixel in the block is less than the reference grayscale value of the block, it means that the grayscale value of the pixel in the block needs to be increased to be close to the grayscale value of a normal pixel, and the increase range is the product of the grayscale value of the pixel in the block and its aberration. Finally, the corrected grayscale value of each pixel in each block is obtained to obtain an enhanced image, and the image in the dial can be recognized more accurately based on the enhanced image.

[0062] In the embodiment of the present invention, the degree of aberration of a pixel in the ith block is used as the degree of aberration of each pixel in the ith block; in the adjacent blocks of the ith block, the adjacent block with the lowest degree of aberration is obtained as the reference block of the ith block, the distance between each pixel in the reference block of the ith block and the central pixel of the ith block is obtained, and the gray value of the pixel in the reference block of the ith block corresponding to the minimum distance is recorded as the reference gray value of the ith block;

[0063] Get the corrected grayscale value of each pixel in each block:

[0064] ;

[0065] In the formula, represents the corrected gray value of the jth pixel in the i-th block; Represents the reference grayscale value of the i-th block; Represents the degree of abnormality of the jth pixel in the i-th block; represents the grayscale value of the jth pixel in the ith block; if the grayscale value of the jth pixel in the ith block is greater than the reference grayscale value of the ith block, it means that the grayscale value of the jth pixel in the ith block needs to be reduced to make it close to the grayscale value of the normal pixel, and the reduction range is the product of the grayscale value of the jth pixel in the ith block and its abnormality; if the grayscale value of the jth pixel in the ith block is less than the reference grayscale value of the ith block, it means that the grayscale value of the jth pixel in the ith block needs to be increased to make it close to the grayscale value of the normal pixel, and the increase range is the product of the grayscale value of the jth pixel in the ith block and its abnormality.

[0066] An image composed of the corrected grayscale value of each pixel in each block is used as an enhanced image; edge detection is performed on the enhanced image to identify the data in the dial.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A ring main unit group meter reading method based on image processing, characterized in that: include: Collecting dial images; The dial image is divided into multiple blocks; the product of the grayscale value variance of all pixels in each block and the sum of the gradient values ​​of all pixels in each block is taken as the grayscale value change degree in each block; For any block, an empty grayscale change sequence is preset in the block, and the pixel point with the maximum gradient value is taken as the first pixel point in the grayscale change sequence, and the first pixel point in the gradient direction of the latest supplemented pixel point is selected in sequence to supplement the grayscale change sequence until the latest supplemented pixel point is no longer in the block, and then the supplementation is stopped; and so on, each grayscale change sequence in the block is obtained; there is no same pixel point between the first pixel points in the grayscale change sequence; Get the degree to which each block is affected by edge aliasing noise: , Represents the degree to which the i-th block is affected by edge jagged noise; Represents the degree of change of gray value in the i-th block; Represents the number of pixels in the mth grayscale change sequence in the i-th block; Represents the number of grayscale change sequences of the i-th block; Represents the gray value of the kth pixel in the mth grayscale change sequence in the ith block; as well as Respectively represent the grayscale value of the first pixel in the gradient direction of the k-th pixel in the m-th grayscale change sequence in the ith block and the grayscale value of the first pixel in the opposite direction of the gradient direction; || represents the absolute value sign; The blocks adjacent to the ith block are taken as adjacent blocks of the ith block, the central pixel of the ith block is obtained, the pixel points of the central pixel of the ith block in the direction of the gradual change of the ith block and the pixel points in the opposite direction of the gradual change of the ith block are obtained, which are recorded as the changed pixel points of the ith block, and the pixel points of the changed pixel points of the ith block that are located in the adjacent blocks of the ith block are recorded as the representative pixel points of the ith block; Get the degree of abnormality of pixels in each block , Represents the degree of abnormality of the pixel in the i-th block; Represents the number of pixels in the i-th block; Represents the mean of the absolute values ​​of the grayscale differences between all adjacent representative pixels of the i-th block; Represents the gray value of the jth pixel in the i-th block; Represents the grayscale value of the first pixel of the jth pixel in the ith block in the gradient change direction of the ith block; norm() represents the normalization function; Get the corrected gray value of each pixel in each block , represents the corrected gray value of the jth pixel in the i-th block; Represents the reference grayscale value of the i-th block; represents the degree of abnormality of the jth pixel in the ith block; the image composed of the corrected grayscale value of each pixel in each block is used as the enhanced image; edge detection is performed on the enhanced image to identify the data in the dial.

2. The ring main unit group meter reading method based on image processing according to claim 1 is characterized in that: The acquisition of the gradual change direction includes: The mean value of the gradient directions of all pixels in the first grayscale change sequence of the ith block is taken as the gradient change direction of the ith block.

3. The ring main unit group meter reading method based on image processing according to claim 1 is characterized in that: The acquisition of the reference grayscale value includes: Among the adjacent blocks of the i-th block, obtain the adjacent block with the lowest degree of abnormality as the reference block of the i-th block, obtain the distance between each pixel point in the reference block of the i-th block and the central pixel point of the i-th block, and record the grayscale value of the pixel point in the reference block of the i-th block corresponding to the minimum distance as the reference grayscale value of the i-th block.

4. The ring main unit group meter reading method based on image processing according to claim 1 is characterized in that: The step of dividing the dial image into a plurality of blocks comprises: Preset block size , divide the dial image into several pieces of size of blocks.

Images