Intelligent electricity meter recycling method and system

Abstract

The invention relates to the technical field of electricity meter recovery, in particular to an electricity meter intelligent recovery method and system, and the system comprises scanning equipment, an image collection unit, an image cutting module, a text detection model and a storage module. According to the identification of the digital code of the electric meter, the front picture of the electric meter is cut by using the first sliding window and the second sliding window to obtain a third sub-picture, and only the third sub-picture needs to be subjected to text identification; according to the method, the identification area of the to-be-identified electric meter image during image identification is reduced, the calculation amount is reduced, the identification code on the third sub-image occupies a large area of the image, and the identification difficulty is also greatly reduced. Template matching is reversely utilized, worn and incomplete digits are used as template images, complete single-digit images are used as target images to analyze digits on the serial numbers of the to-be-identified electric meters, and only external conditions such as light and angles need to be considered during template matching.

Description

Technical Field

[0001] The present application relates to the technical field of electric meter recycling, and in particular to an electric meter intelligent recycling method and system. Background Art

[0002] The statements in this section merely provide background technical information related to the present application and do not necessarily constitute prior art.

[0003] The unique identification code of an electric meter is usually marked on the front of the meter body by a barcode and the numbers below it. When the electric meter is recycled, the identification code needs to be stored and recorded; however, the identification code on the recycled electric meter is often seriously damaged, especially the barcode occupies a large area, which is often difficult to identify. Therefore, the recycled electric meter is often supplemented with the digital code below it for identification. However, if the digital code is damaged, it will bring difficulties to the staff in the meter recycling work. Summary of the invention

[0004] Based on this, in order to solve the above technical problems, the present application provides an electric meter intelligent recycling method and system.

[0005] The technical solution adopted by this application to solve the problems existing in the prior art is:

[0006] This application proposes a smart recycling method for electric meters, comprising the following steps:

[0007] S0: Scan the barcodes on the front pictures of the electric meters to be recycled in sequence with a scanning device to obtain and store the identification codes of each electric meter; if the identification code cannot be found, proceed to step S1;

[0008] S1: Acquire a front image of the electric meter to be recycled through an image acquisition unit;

[0009] S2: using the first sliding window to sequentially crop the front image of the electric meter from left to right, and each time a first sub-image is obtained by cropping, the first sub-image is recognized by the text detection model, and the cropping is stopped when a digital image containing the electric meter identification code is recognized in the first sub-image. The number of cropping is n;

[0010] Wherein: the width of the first sliding window is equal to the width of the front image of the electric meter;

[0011] The length of the first sliding window = δ, when the width of a single digit of the meter identification code is ≤ the digit spacing of the meter identification code, δ < the width of a single digit of the meter identification code; when the width of a single digit of the meter identification code is > the digit spacing of the meter identification code, δ < the digit spacing of the meter identification code;

[0012] S3: Select the remaining front image of the electric meter after cutting n-1 times in step S1, and cut it sequentially from bottom to top using the second sliding window. Each time a second sub-image is cut, it is recognized by the text detection model. When a digital image containing the electric meter identification code is recognized in the second sub-image, the cutting is stopped. The number of cutting times is m.

[0013] Wherein: the length of the second sliding window is equal to the length of the front picture of the electric meter;

[0014] The width of the second sliding window = β, β < the digital height value of the meter identification code;

[0015] S4: Select the front image of the electric meter remaining after cutting m-1 times in step S2, and use the third sliding window to cut the lower left corner of the image once to obtain a third sub-image; recognize the text in the third sub-image to obtain an identification code of the electric meter to be recycled, and store the identification code in a storage unit;

[0016] in:

[0017] The width of the third sliding window = γ, γ = the digital height value of the meter identification code + β;

[0018] The length of the third sliding window = α, α = the length of the meter identification code + δ;

[0019] The length of the meter identification code=the width of a single digit of the meter identification code×the number of digits of the meter identification code+the digit spacing of the meter identification code×(the number of digits of the meter identification code-1).

[0020] Preferably,

[0021] The digital image of the meter identification code includes a partial image of a single digit of the meter identification code.

[0022] Preferably,

[0023] Recognizing the text in the third sub-image in step S4 includes the following steps:

[0024] S41: using the fourth sliding window to sequentially crop the third sub-image from left to right to obtain f fourth sub-images; i is used to represent the sequence number of the i-th cropped fourth sub-image, i≤f, f represents the number of digits of the meter identification code, i∈N+;

[0025] The length of the fourth sliding window = the digit spacing of the meter identification code + the width of a single digit of the meter identification code;

[0026] The width of the fourth sliding window = the width of the third sliding window;

[0027] S42: performing text recognition on each fourth sub-image using a text detection model;

[0028] If the number on the i-th fourth sub-image is recognized, [i, DTi] is stored in the storage unit, i is the sequence number corresponding to the fourth sub-image, and DTi is the number on the i-th fourth sub-image;

[0029] If the number on the fourth sub-picture cannot be recognized, proceed to step S43;

[0030] S43: Select a fourth sub-image without a recognized number as a template image, and use the single-digit images saved in advance as target images one by one, perform template matching to obtain a result matrix, if the value of the result matrix is ​​greater than λ, the number on the fourth sub-image is the number on the single-digit image, and store [i, DTi] in a storage unit, where i is the sequence number corresponding to the fourth sub-image;

[0031] Then select the remaining fourth sub-pictures that have not been recognized as numbers and repeat this step, and record the final number as [i, DTi] and store it in the storage unit, where i is the sequence number corresponding to the fourth sub-picture;

[0032] Where: λ is the set threshold;

[0033] If all identifications are completed, the digital numbers in the order of DT1, DT2, ···, DTi, ···, DTf are the identification codes of the electric meters to be recycled;

[0034] If there is still a fourth sub-picture whose number cannot be recognized, proceed to step S44;

[0035] S44: Clear the data in the storage unit, issue an unrecognizable alarm message and switch to manual recognition, and return to step S0.

[0036] Preferably,

[0037] The text detection model is the PPOCRv4 text detection model.

[0038] Preferably,

[0039] The single digital image includes ten images, each of which has a number, and the font, size and color of each number are the same as the number on the digital identification code of the electric meter to be tested;

[0040] There are ten numbers 1, 2, 3, 4, 5, 6, 7, 8, 9, and 0 on the ten images respectively.

[0041] Preferably,

[0042] The template matching is implemented by OpenCV library.

[0043] Preferably,

[0044] The template matching is performed through the matchTemplate function in the OpenCV library, and the calculation formula for the relevant matching is:

[0045]

[0046] in:

[0047] T(x′, y′) is the pixel value of the fourth sub-image, i.e., the template image, where no digits are recognized. I(x+x′, y+y′) is the pixel value of the corresponding position in the target image. (x, y) is the current position of the template in the target image.

[0048] Preferably,

[0049] The method to determine λ is as follows:

[0050] S431: using the ten single-digit images as template images and the third sub-image as the target image to perform template matching;

[0051] S432: Obtain the matching result image src through the template matching function cv2.matchTemplate; the image src contains the matching score of each possible position in the template and the target image;

[0052] S433: Use cv2.minMaxLoc function to find the maximum value maxVal in the matching result image src;

[0053] S434: Calculate λ:

[0054] λ=k u ×maxVal

[0055] Where: k u is the proportionality coefficient.

[0056] Preferably,

[0057] 0 <k u ≤1.

[0058] An electric meter intelligent recycling system, based on the above-mentioned electric meter intelligent recycling method, comprises:

[0059] Scanning equipment for identifying the barcode of the electricity meter to be recycled;

[0060] An image acquisition unit, used to obtain a front image of the electric meter to be recycled;

[0061] An image cropping module, used to crop the front image of the electric meter acquired by the image acquisition unit;

[0062] The text detection model is used to perform text recognition on the images cropped by the image cropping module;

[0063] The storage module is used to sequentially store the identification codes of the electric meters to be recycled and store the data processed by the image processing module.

[0064] Compared with the prior art, the beneficial effects of this application are:

[0065] 1. When the barcode of the meter number cannot be recognized, it is recognized through the digital code; the recognition of the digital code uses the first sliding window and the second sliding window to crop the front image of the meter, and then uses the third sliding window to crop it to the third sub-image, and only the third sub-image needs to be recognized for text recognition; this method reduces the recognition area of ​​the meter image to be recognized during image recognition, reduces the amount of calculation, and the recognition code on the third sub-image occupies a larger area of ​​the image, and the recognition difficulty is greatly reduced.

[0066] 2. The traditional method of using a sliding window to crop the meter image to obtain the meter identification code image requires cropping in a full-coverage manner according to the size of the front image of the meter. The present application omits the cropping of the right side of the meter image identification code and the upper side of the identification code, thus simplifying the processing process and reducing the calculation process.

[0067] 3. Reversely use template matching, use the worn and incomplete digits as template images, and use the complete single digit image as the target image to analyze the digits on the meter number to be identified. When matching the template, only external conditions such as light and angle need to be considered. When calculating λ, use ten single digit images as template images and the third sub-image as the target image for template matching to better determine maxVal and thus determine the appropriate λ. DETAILED DESCRIPTION

[0068] The present application will be further described below in conjunction with embodiments.

[0069] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0070] In the present disclosure, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom" and the like indicating directions or positional relationships are merely relational words determined for the convenience of describing the structural relationships of the various parts or elements of the present disclosure, and do not specifically refer to any part or element in the present disclosure and should not be understood as limitations on the present disclosure.

[0071] When an electric meter is scrapped or no longer in use, it needs to be returned to the warehouse. Since each electric meter has a unique identification code, the identification code of the recycled electric meter needs to be scanned and filed.

[0072] The identification code of an electric meter generally consists of a barcode on the top and a string of digital codes on the bottom. The barcode occupies a larger area, while the digital code on the bottom of the barcode occupies a smaller area. For electric meters to be recycled, since electric meters to be recycled are often unusable after a period of use, the barcode on the top will be somewhat worn, making it difficult for staff to scan the code. Compared with the digital code, the digital code occupies a smaller area and is less susceptible to external damage, so it is relatively well preserved. Therefore, for some electric meters to be recycled whose barcodes are worn, identifying their digital codes becomes a very important means; however, there will always be some digital codes that are worn, and for some digital codes that are partially worn, it is still difficult to perform text recognition on them.

[0073] The present application provides an intelligent recycling method for electric meters, which is used to identify digital codes of recycled electric meters and save the digital codes, including the following steps:

[0074] S0: Scan the barcodes on the front pictures of the electric meters to be recycled in sequence with a scanning device, obtain the identification code of each electric meter and store it; if it cannot be identified, go to step S1; the scanning device is generally a scanner;

[0075] S1: Obtain a front picture of the electric meter to be recycled through an image acquisition unit; in some embodiments, the image acquisition unit is a camera, and the front picture of the electric meter to be recycled is taken through the camera;

[0076] S2: using the first sliding window to sequentially crop the front image of the electric meter from left to right, and each time a first sub-image is obtained by cropping, the first sub-image is recognized by the text detection model, and the cropping is stopped when a digital image containing the electric meter identification code is recognized in the first sub-image. The number of cropping is n;

[0077] Wherein: the width of the first sliding window is equal to the width of the front image of the electric meter;

[0078] The length of the first sliding window = δ, when the width of a single digit of the meter identification code is ≤ the digit spacing of the meter identification code, δ < the width of a single digit of the meter identification code; when the width of a single digit of the meter identification code is > the digit spacing of the meter identification code, δ < the digit spacing of the meter identification code;

[0079] S3: Select the remaining front image of the electric meter after cutting n-1 times in step S1, and cut it sequentially from bottom to top using the second sliding window. Each time a second sub-image is cut, it is recognized by the text detection model. When a digital image containing the electric meter identification code is recognized in the second sub-image, the cutting is stopped. The number of cutting times is m.

[0080] Wherein: the length of the second sliding window is equal to the length of the front picture of the electric meter;

[0081] The width of the second sliding window = β, β < the digital height value of the meter identification code;

[0082] S4: Select the front image of the electric meter remaining after cutting m-1 times in step S2, and use the third sliding window to cut the lower left corner of the image once to obtain a third sub-image; recognize the text in the third sub-image to obtain an identification code of the electric meter to be recycled, and store the identification code in a storage unit;

[0083] in:

[0084] The width of the third sliding window = γ, γ = the digital height value of the meter identification code + β;

[0085] The length of the third sliding window = α, α = the length of the meter identification code + δ;

[0086] The length of the meter identification code=the width of a single digit of the meter identification code×the number of digits of the meter identification code+the digit spacing of the meter identification code×(the number of digits of the meter identification code-1).

[0087] The digital image of the meter identification code includes a partial image of a single digit of the meter identification code.

[0088] Using a sliding window to crop an image is a common image processing technology, which will not be described in detail in this application.

[0089] Recognizing the text in the third sub-image in step S4 includes the following steps:

[0090] S41: using the fourth sliding window to sequentially crop the third sub-image from left to right to obtain f fourth sub-images; i is used to represent the sequence number of the i-th cropped fourth sub-image, i≤f, f represents the number of digits of the meter identification code, i∈N+;

[0091] The length of the fourth sliding window = the digit spacing of the meter identification code + the width of a single digit of the meter identification code;

[0092] The width of the fourth sliding window = the width of the third sliding window;

[0093] S42: performing text recognition on each fourth sub-image using a text detection model;

[0094] If the number on the i-th fourth sub-image is recognized, [i, DTi] is stored in the storage unit, i is the sequence number corresponding to the fourth sub-image, and DTi is the number on the i-th fourth sub-image;

[0095] If the number on the fourth sub-picture cannot be recognized, proceed to step S43;

[0096] S43: Select a fourth sub-image without a recognized number as a template image, and use the single-digit images saved in advance as target images one by one, perform template matching to obtain a result matrix, if the value of the result matrix is ​​greater than λ, the number on the fourth sub-image is the number on the single-digit image, and store [i, DTi] in a storage unit, where i is the sequence number corresponding to the fourth sub-image;

[0097] Then select the remaining fourth sub-pictures that have not been recognized as numbers and repeat this step, and record the final number as [i, DTi] and store it in the storage unit, where i is the sequence number corresponding to the fourth sub-picture;

[0098] Where: λ is the set threshold;

[0099] If all identifications are completed, the digital numbers in the order of DT1, DT2, ···, DTi, ···, DTf are the identification codes of the electric meters to be recycled;

[0100] If there is still a fourth sub-picture whose number cannot be recognized, proceed to step S44;

[0101] The method to determine λ is as follows:

[0102] S431: using the ten single-digit images as template images and the third sub-image as the target image to perform template matching;

[0103] S432: Obtain the matching result image src through the template matching function cv2.matchTemplate; the image src contains the matching score of each possible position in the template and the target image;

[0104] S433: Use cv2.minMaxLoc function to find the maximum value maxVal in the matching result image src;

[0105] S434: Calculate λ:

[0106] λ=k u ×maxVal

[0107] Where: k u is the proportionality coefficient; 0 <k u ≤1. k uThe value can be adjusted appropriately according to the actual situation, such as lighting conditions and photo angle. Generally, the larger the value, the better.

[0108] S44: Clear the data in the storage unit, issue an unrecognizable alarm message and switch to manual recognition, and return to step S0.

[0109] In some embodiments, the text detection model is the PPOCRv4 text detection model. The PPOCRv4 text detection model is the latest version in the PaddleOCR project. It is further upgraded and optimized based on PPOCRv3. For those skilled in the art, it can be deployed and used according to actual conditions, and will not be described in detail in this application.

[0110] The single digital image includes ten images, each of which is provided with a number, and the font, size and color of each number are the same as the number on the digital identification code of the electric meter to be tested; the ten images are respectively provided with ten numbers 1, 2, 3, 4, 5, 6, 7, 8, 9 and 0.

[0111] Template matching can be implemented through the OpenCV library. Specifically, template matching uses the matchTemplate function in the OpenCV library to perform relevant matching, and the calculation formula for relevant matching is:

[0112]

[0113] in:

[0114] T(x′, y′) is the pixel value of the fourth sub-image, i.e., the template image, where no digits are recognized. I(x+x′, y+y′) is the pixel value of the corresponding position in the target image. (x, y) is the current position of the template in the target image.

[0115] The present application provides an electric meter intelligent recycling system, and the above-mentioned electric meter intelligent recycling method includes:

[0116] Scanning equipment for identifying the barcode of the electricity meter to be recycled;

[0117] An image acquisition unit, used to obtain a front image of the electric meter to be recycled;

[0118] An image cropping module, used to crop the front image of the electric meter acquired by the image acquisition unit;

[0119] The text detection model is used to perform text recognition on the images cropped by the image cropping module;

[0120] The storage module is used to sequentially store the identification codes of the electric meters to be recycled and store the data processed by the image processing module.

[0121] The intelligent recycling method of electric meters provided by the present application uses a digital code to identify the barcode of the electric meter number when it cannot be identified; the identification of the digital code uses the first sliding window and the second sliding window to cut the front image of the electric meter, and then uses the third sliding window to cut it to the third sub-image, and only needs to perform text recognition on the third sub-image; this method reduces the recognition area of ​​the electric meter image to be identified during image recognition, reduces the amount of calculation, and the identification code on the third sub-image occupies a larger area of ​​the image, and the difficulty of identification is greatly reduced. The cutting of the right side of the electric meter image identification code and the upper side of the identification code is omitted, the processing process is simplified, and the calculation process is reduced.

[0122] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0123] Although the above describes the specific implementation methods of the present application, it is not intended to limit the scope of protection of the present application. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present application, various modifications or variations that can be made by technical personnel in this field without creative work are still within the scope of protection of the present application.

Claims

1. A smart recycling method for electric meters, characterized in that: The following steps are involved: S0: Scan the barcodes on the front pictures of the electric meters to be recycled in sequence through a scanning device, obtain the identification code of each electric meter and store it; If it cannot be identified, go to step S1; S1: Acquire a front image of the electric meter to be recycled through an image acquisition unit; S2: using the first sliding window to sequentially crop the front image of the electric meter from left to right, and each time a first sub-image is obtained by cropping, the first sub-image is recognized by the text detection model, and the cropping is stopped when a digital image containing the electric meter identification code is recognized in the first sub-image. The number of cropping is n; Wherein: the width of the first sliding window is equal to the width of the front image of the electric meter; The length of the first sliding window = δ, when the width of a single digit of the meter identification code is ≤ the digit spacing of the meter identification code, δ < the width of a single digit of the meter identification code; when the width of a single digit of the meter identification code is > the digit spacing of the meter identification code, δ < the digit spacing of the meter identification code; S3: Select the remaining front image of the electric meter after cutting n-1 times in step S1, and cut it sequentially from bottom to top using the second sliding window. Each time a second sub-image is cut, it is recognized by the text detection model. When a digital image containing the electric meter identification code is recognized in the second sub-image, the cutting is stopped. The number of cutting times is m; Wherein: the length of the second sliding window is equal to the length of the front picture of the electric meter; The width of the second sliding window = β, β < the digital height value of the meter identification code; S4: Select the front image of the electric meter remaining after cutting m-1 times in step S2, and use the third sliding window to cut the lower left corner of the image once to obtain a third sub-image; recognize the text in the third sub-image to obtain an identification code of the electric meter to be recycled, and store the identification code in a storage unit; in: The width of the third sliding window = γ, γ = the digital height value of the meter identification code + β; The length of the third sliding window = α, α = the length of the meter identification code + δ; The length of the meter identification code=the width of a single digit of the meter identification code×the number of digits of the meter identification code+the digit spacing of the meter identification code×(the number of digits of the meter identification code-1).

2. The method for intelligent recycling of electric meters according to claim 1, characterized in that: The digital image of the meter identification code includes a partial image of a single digit of the meter identification code.

3. The method for intelligent recycling of electric meters according to claim 1, characterized in that: Recognizing the text in the third sub-image in step S4 includes the following steps: S41: using the fourth sliding window to sequentially crop the third sub-image from left to right to obtain f fourth sub-images; i is used to represent the sequence number of the i-th cropped fourth sub-image, i≤f, f represents the number of digits of the meter identification code, i∈N+; The length of the fourth sliding window = the digit spacing of the meter identification code + the width of a single digit of the meter identification code; The width of the fourth sliding window = the width of the third sliding window; S42: performing text recognition on each fourth sub-image using a text detection model; If the number on the i-th fourth sub-image is recognized, [i, DTi] is stored in the storage unit, i is the sequence number corresponding to the fourth sub-image, and DTi is the number on the i-th fourth sub-image; If the number on the fourth sub-picture cannot be recognized, proceed to step S43; S43: Select a fourth sub-image without a recognized number as a template image, and use the single-digit images saved in advance as target images one by one, perform template matching to obtain a result matrix, if the value of the result matrix is ​​greater than λ, the number on the fourth sub-image is the number on the single-digit image, and store [i, DTi] in a storage unit, where i is the sequence number corresponding to the fourth sub-image; Then select the remaining fourth sub-pictures that have not been recognized as numbers and repeat this step, and record the final number as [i, DTi] and store it in the storage unit, where i is the sequence number corresponding to the fourth sub-picture; Where: λ is the set threshold; If all identifications are completed, the digital numbers in the order of DT1, DT2, ···, DTi, ···, DTf are the identification codes of the electric meters to be recycled; If there is still a fourth sub-picture whose number cannot be recognized, proceed to step S44; S44: Clear the data in the storage unit, issue an unrecognizable alarm message and switch to manual recognition, and return to step S0.

4. The method for intelligent recycling of electric meters according to claim 3, characterized in that: The text detection model is the PPOCRv4 text detection model.

5. The method for intelligent recycling of electric meters according to claim 3, characterized in that: The single digital image includes ten images, each of which has a number, and the font, size and color of each number are the same as the number on the digital identification code of the electric meter to be tested; There are ten numbers 1, 2, 3, 4, 5, 6, 7, 8, 9, and 0 on the ten images respectively.

6. An intelligent recycling method for electric meters according to claim 3 or 5, characterized in that: The template matching is implemented by OpenCV library.

7. The method for intelligent recycling of electric meters according to claim 6, characterized in that: The template matching is performed through the matchTemplate function in the OpenCV library, and the calculation formula for the relevant matching is: in: T(x′, y′) is the pixel value of the fourth sub-image, i.e., the template image, where no digits are recognized. I(x+x′, y+y′) is the pixel value of the corresponding position in the target image. (x, y) is the current position of the template in the target image.

8. The method for intelligent recycling of electric meters according to claim 7, characterized in that: The method to determine λ is as follows: S431: using the ten single-digit images as template images and the third sub-image as the target image to perform template matching; S432: Obtain the matching result image src through the template matching function cv2.matchTemplate; the image src contains the matching score of each possible position in the template and the target image; S433: Use cv2.minMaxLoc function to find the maximum value maxVal in the matching result image src; S434: Calculate λ: λ=k u ×maxVal Where: k u is the proportionality coefficient.

9. The method for intelligent recycling of electric meters according to claim 8, characterized in that: 0<k u ≤1。 10. An electric meter intelligent recycling system, based on the electric meter intelligent recycling method according to claim 1, characterized in that: include: Scanning equipment for identifying the barcode of the electricity meter to be recycled; An image acquisition unit, used to obtain a front image of the electric meter to be recycled; An image cropping module, used to crop the front image of the electric meter acquired by the image acquisition unit; The text detection model is used to perform text recognition on the images cropped by the image cropping module; The storage module is used to sequentially store the identification codes of the electric meters to be recycled and store the data processed by the image processing module.

Images