Banknote authenticity verification method, device and electronic device based on the national emblem of banknotes

Abstract

The present invention provides a banknote authenticity verification method, device and electronic device based on the national emblem of banknotes; the above method includes: respectively preprocessing the banknote to be recognized and a plurality of genuine banknote samples to obtain binary images; confirming vertices according to the original coordinates and pixel values of the pixel points in the binary images, and reconfirming the sampling coordinates (x, y) of the national emblem edge according to a first coordinate system with the vertices as the origin; fitting to obtain a standard feature curve equation of the national emblem edge according to the sampling coordinates of the sample binary image; substituting the sampling coordinates of the binary image to be recognized into the standard feature curve equation, and if the error is less than a preset error threshold, determining that the banknote to be recognized is a genuine coin. This application intercepts the national emblem image on the banknote, performs image processing, and then fits and calculates the feature curve of the upper half of the national emblem, so as to perform secondary identification on the national emblem part to improve the accuracy rate.

Description

Technical Field

[0001] The present invention relates to the technical field of banknote authenticity verification, and in particular, to an authenticity verification method, device, and electronic device based on the national emblem of a banknote. Background Art

[0002] With the continuous development of science and technology, banks at home and abroad have become increasingly strict with the technology of machine identification of banknote authenticity. The traditional authenticity verification method is to use multi-spectral image detection technology to analyze the authenticity of banknotes by using ultraviolet images, infrared images, etc. However, the means of counterfeiting banknotes are constantly improving, and the authenticity verification technology still needs to be improved. The authenticity of banknotes should be detected from multiple aspects to improve the accuracy of authenticity verification. Summary of the Invention

[0003] Based on this, the object of the present invention is to propose an authenticity verification method, device, and electronic device based on the national emblem of a banknote. On the basis of the existing technology, this application intercepts the national emblem image on the banknote, performs image processing, and then fits and calculates the characteristic curve of the upper half of the national emblem, so as to perform secondary identification on the national emblem part. This method can also avoid the error of authenticity verification results caused by the differences between different machines and improve the accuracy.

[0004] In a first aspect, an embodiment of the present invention provides an authenticity verification method based on the national emblem of a banknote. The method includes: S1: Preprocess the banknote to be identified and multiple genuine banknote samples respectively to obtain binary images, where the binary images include: the binary image to be identified and multiple sample binary images; S2: Confirm the vertices according to the original coordinates and pixel values of the pixel points in the binary image, and reconfirm the sampling coordinates (x, y) of the national emblem edge according to the first coordinate system with the vertex as the origin; S3: Fit the standard characteristic curve equation of the national emblem edge according to the sampling coordinates of the sample binary images; S4: Substitute the sampling coordinates of the binary image to be identified into the standard characteristic curve equation. If the error is less than the preset error threshold, it is determined that the banknote to be identified is a genuine banknote, otherwise it is a counterfeit banknote, where the preset error threshold includes a horizontal error threshold and a vertical error threshold.

[0005] Further, step S2 includes: S2-1: Establish an initial coordinate system with the pixel point in the upper left corner of the binary image as the coordinate origin, and traverse each pixel point row by row from left to right from top to bottom; S2-2: When the pixel value of the first traversed pixel point is less than the preset first threshold, use this pixel point as the vertex;

[0006] S2-3: Establish a first coordinate system with the vertex as the origin; S2-4: Confirm the sampling coordinates of the national emblem edge according to the first coordinate system and the pixel values of each pixel point in the binary image.

[0007] Further, step S2-4 includes: starting from the X-axis of the first coordinate system, traversing each pixel point row by row from left to right. For each row, when a pixel point with a pixel value less than the first threshold first appears, the coordinates of this pixel point are stored as one of the sampling coordinates in the sampling library; when the pixel values of Q consecutive pixel points in this row are all greater than or equal to the first threshold, and the abscissas of the sampling coordinates of the Q pixel points are all greater than c, the pixel point before the Q consecutive pixel points is stored as one of the sampling coordinates in the sampling library.

[0008] Further, step S2-4 also includes: for a row where it is impossible to collect Q consecutive pixel points with pixel values all greater than or equal to the first threshold and the abscissas of the sampling coordinates of the Q pixel points are all greater than c, the sampling coordinates below this row are not collected.

[0009] Further, step S3 includes: S3-1: According to the sampling coordinates of the sample binary image, confirm the preliminary parabola equation. One sampling coordinate corresponds to one parabola equation, and each parabola equation corresponds to a coefficient p; S3-2: Average the multiple coefficients p of the preliminary parabola equation to obtain the coefficient of the special curve of this sample binary image; S3-3: Execute steps S3-1 and S3-2 for all sample binary images to obtain the coefficients of the special curves of each sample binary image, and then take the average value of the coefficients of the special curves of all sample binary images as the standard feature coefficient, and fit to obtain the standard feature curve equation of the national emblem edge.

[0010] Further, step S4 includes: S4-1: Substitute the abscissa x of the sampling coordinates of the binary image to be recognized into the above standard feature curve equation respectively to obtain the corresponding Y; S4-2: Substitute the ordinate y of the sampling coordinates of the binary image to be recognized into the above standard feature curve equation respectively to obtain the corresponding X; S4-3: Compare Y with the corresponding y of the sampling coordinates of the binary image to be recognized respectively to obtain multiple first differences. At the same time, compare X with the corresponding x of the sampling coordinates of the binary image to be recognized respectively to obtain multiple second differences; S4-4: If there are more than a first differences less than the vertical error threshold; and there are more than b second differences less than the horizontal error threshold, then the banknote to be recognized is a genuine banknote.

[0011] Further, step S1 includes: S1-1: Calculate the tilt angles of the initially collected genuine banknote samples and the banknote to be identified respectively, and rotate and correct the genuine banknote samples and the banknote to be identified according to the tilt angles to obtain their respective corrected banknote images; S1-2: Roughly intercept in the corrected banknote image according to the coordinates of the preset rectangular area to obtain a roughly cut image; cut the roughly cut image again to obtain a finely cut image, where the finely cut image is used to reflect the shape of the upper half curve of the national emblem; S1-3: Binarize and denoise the above-mentioned finely cut image to obtain a binarized image, where the binarized image includes: a to-be-identified binarized image and multiple sample binarized images.

[0012] In a second aspect, an authenticity verification device based on the national emblem of a banknote provided by an embodiment of the present application includes: a preprocessing module, configured to preprocess the banknote to be identified and multiple genuine banknote samples respectively to obtain a binarized image, where the binarized image includes: a to-be-identified binarized image and multiple sample binarized images; a sampling coordinate confirmation module, configured to confirm vertices according to the original coordinates and pixel values of the pixel points in the binarized image, and reconfirm the sampling coordinates (x, y) of the national emblem edge according to a first coordinate system with the vertex as the origin; a standard curve fitting module, configured to fit a standard feature curve equation of the national emblem edge according to the sampling coordinates of the sample binarized images; an authenticity verification module, configured to substitute the sampling coordinates of the to-be-identified binarized image into the standard feature curve equation, and if the error is less than a preset error threshold, determine that the to-be-identified banknote is a genuine currency, otherwise it is a counterfeit currency, where the preset error threshold includes a horizontal error threshold and a vertical error threshold.

[0013] In a third aspect, an electronic device provided by an embodiment of the present application includes: a processor, a storage medium, and a bus, where the storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the authenticity verification method based on the national emblem of a banknote according to any one of claims 1 to 7.

[0014] The beneficial effects of the embodiments of the present invention are as follows:

[0015] The purpose of the present invention is to propose an authenticity verification method, device, and electronic device based on the national emblem of a banknote. On the basis of the existing technology, the present application intercepts the national emblem image on the banknote, performs image processing, and then fits and calculates the feature curve of the upper half of the national emblem, so as to perform secondary identification on the national emblem part. This method can also avoid the error of the authenticity verification result caused by the differences between different machines and improve the accuracy rate.

[0016] Other features and advantages of the present invention will be set forth in the following description, or can be learned by inference from the description, or can be learned by implementing the above technologies of the present invention without ambiguity.

[0017] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following specifically describes preferred embodiments in conjunction with the accompanying drawings as follows. Description of the Drawings

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of a method for authenticating banknote national emblems provided by an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of a binary image provided by an embodiment of the present invention;

[0021] Figure 3 It is a schematic diagram of a roughly cut image provided by an embodiment of the present invention;

[0022] Figure 4 It is a schematic diagram of a finely cut image provided by an embodiment of the present invention;

[0023] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0024] In order to make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0026] This technology is applied to the technical scenario of authenticating banknotes. Embodiment

[0027] The present invention provides a banknote authenticity verification method based on the national emblem of banknotes. The flowchart of this method is as Figure 1 shown. This method includes:

[0028] S1: Preprocess the banknote to be identified and multiple genuine banknote samples respectively to obtain binary images, where the binary images include: the binary image to be identified and multiple sample binary images.

[0029] Specifically, for the schematic diagram of the binary image of any banknote, as Figure 2 shown.

[0030] The preprocessing process of S1 includes:

[0031] S1-1 (Rotation): Calculate the inclination angles of the initially collected genuine banknote samples and the banknote to be identified respectively, and rotate and correct the genuine banknote samples and the banknote to be identified according to the inclination angles to obtain their respective corrected banknote images.

[0032] S1-2 (Interception): Roughly intercept in the corrected banknote image according to the coordinates of the preset rectangular area to obtain a roughly cut image; cut the roughly cut image again to obtain a finely cut image, where the finely cut image is used to reflect the shape of the upper half curve of the national emblem.

[0033] Specifically, the roughly cut image can ensure the integrity of the national emblem image. The roughly cut image is as Figure 3 shown, and the finely cut image is as Figure 4 shown.

[0034] S1-3 (Binaryzation): Binaryize and denoise the above-mentioned finely cut image to obtain a binary image, where the binary image includes: the binary image to be identified and multiple sample binary images.

[0035] Specifically, the binary image is as Figure 2 shown.

[0036] Here, the binary image can separate the foreground of the national emblem from its background, avoiding the interference of the background on the accuracy of fitting the feature curve.

[0037] For the denoising process, there may be interference points near the feature curves of the preliminary binary images of individual finely cut images. Therefore, this application uses non-local means technology to denoise the edges of the feature curves of the preliminary binary images, further reducing the influence of background pixel points on fitting the national emblem feature curve, so as to obtain Figure 2 the binary image.

[0038] S2: Confirm the vertex based on the original coordinates and pixel values of the pixel points in the binarized image, and re-confirm the sampling coordinates (x, y) of the national emblem edge according to the first coordinate system with the vertex as the origin.

[0039] S2-1: Establish an initial coordinate system with the pixel point in the upper left corner of the binarized image as the coordinate origin, and traverse each pixel point row by row from top to bottom and from left to right.

[0040] S2-2: When the pixel value of the first traversed pixel point is less than the preset first threshold, take this pixel point as the vertex.

[0041] Specifically, the smaller the pixel value, the darker the color of the point. The first threshold can be 10.

[0042] In actual operation, as Figure 2 shown, there may be multiple pixel points in a certain row whose pixel values are all less than the first threshold. In this case, just take the relatively middle pixel point as the vertex.

[0043] S2-3: Establish the first coordinate system with the vertex as the origin.

[0044] S2-4: Confirm the sampling coordinates of the national emblem edge according to the first coordinate system and the pixel values of each pixel point in the binarized image.

[0045] The execution method of step S2-4 is as follows:

[0046] Start from the X-axis of the first coordinate system and traverse each pixel point row by row from top to bottom and from left to right. For each row, when the first pixel point with a pixel value less than the first threshold appears, store the coordinates of this pixel point as one of the sampling coordinates in the sampling library; when the pixel values of Q consecutive pixel points in this row are all greater than or equal to the first threshold, and the abscissas of the sampling coordinates of the above Q pixel points are all greater than c, store the previous pixel point of the Q consecutive pixel points as one of the sampling coordinates in the sampling library. Perform the same operation for each row.

[0047] In principle, 2 sampling coordinates, left and right, can be obtained for each row of each binarized image. However, for the rows where it is impossible to collect Q consecutive pixel points whose pixel values are all greater than or equal to the first threshold and the abscissas of the sampling coordinates of the Q pixel points are all greater than c, the sampling coordinates below this row will not be collected (for example, Figure 2 the bottom 9 rows may be those where sampling coordinates cannot be obtained).

[0048] Specifically, c is a preset threshold, and the main purpose is to exclude the error in edge selection caused by the white points in the middle part of the national emblem. This scheme can eliminate the pixel points with large errors caused by reasons such as screenshots, improve the authenticity verification accuracy, and at the same time reduce unnecessary workload.

[0049] So far, for each genuine banknote sample and the banknote to be recognized, a corresponding sampling library can be obtained, and the sampling coordinates in the sampling library are the coordinates in the first coordinate system of the edge of the national emblem.

[0050] S3: According to the sampling coordinates of the sample binary image, fit to obtain the standard feature curve equation of the edge of the national emblem.

[0051] S3 includes:

[0052] Table 1 shows 30 sampling coordinates of a certain sample binary image obtained during the experiment (in actual operation, thousands of sampling coordinates may be taken, and here is just an example for illustration).

[0053]

[0054] Table 1

[0055] S3-1: According to the sampling coordinates of the sample binary image, confirm the preliminary parabola equation. One sampling coordinate corresponds to one parabola equation, and each parabola equation corresponds to a coefficient p.

[0056] S3-2: Average the multiple coefficients p of the preliminary parabola equation to obtain the coefficient of the special curve of the sample binary image.

[0057] Specifically, if Table 1 collects 30 sampling coordinates, then 30 coefficients p can be obtained here.

[0058] S3-3: Execute steps S3-1 and S3-2 for all sample binary images to obtain the coefficients of the special curves of each sample binary image, and then take the average value of the coefficients of the special curves of all sample binary images as the standard feature coefficient, and fit to obtain the standard feature curve equation of the edge of the national emblem.

[0059] Specifically, taking Vietnamese banknotes as an example, after a large number of experiments, it is proved that the standard feature curve equation of the edge of the national emblem of Vietnamese banknotes is: .

[0060] S4: Substitute the sampling coordinates of the binary image to be recognized into the standard feature curve equation. If the error is less than the preset error threshold, it is determined that the banknote to be recognized is a genuine currency; otherwise, it is a counterfeit currency. Among them, the preset error threshold includes a horizontal error threshold and a vertical error threshold.

[0061] Specifically, Table 2 below shows 30 sampling coordinates (x, y) of a certain binary image to be recognized.

[0062]

[0063] Table 2

[0064] S4-1: Substitute the abscissa x of the sampling coordinates of the binary image to be recognized into the above standard characteristic curve equation respectively to obtain the corresponding Y.

[0065] S4-2: Substitute the ordinate y of the sampling coordinates of the binary image to be recognized into the above standard characteristic curve equation respectively to obtain the corresponding X.

[0066] S4-3: Compare Y with the y of the sampling coordinates of the corresponding binary image to be recognized respectively to obtain a plurality of first differences. At the same time, compare X with the x of the sampling coordinates of the corresponding binary image to be recognized respectively to obtain a plurality of second differences.

[0067] Specifically, here, the number of sampling coordinates is 30, so the number of both the first differences and the second differences is also 30.

[0068] S4-4: If there are more than a first differences less than the longitudinal error threshold; and more than b second differences less than the transverse error threshold, then the banknote to be recognized is a genuine banknote.

[0069] Specifically, a and b are also preset thresholds. For example, among 30 first differences, if more than 28 are less than the longitudinal error threshold (taking 3); and among 30 second differences, if more than 27 are less than the transverse error threshold (taking 3), then the banknote to be recognized in Table 2 is a genuine banknote. As long as one does not meet the condition, it is determined as a counterfeit banknote.

[0070] Through a large number of experiments, taking the longitudinal error threshold as 3 and the transverse error threshold as 3 can obtain the best anti-counterfeiting effect.

[0071] Based on the use of multi-spectral image detection, this application conducts secondary anti-counterfeiting on it, realizing a dual anti-counterfeiting technology, which significantly improves the anti-counterfeiting accuracy.

[0072] Based on the prior art, this application intercepts the national emblem image on the banknote, performs image processing, and then fits and calculates the characteristic curve of the upper half of the national emblem, so as to conduct secondary identification on the national emblem part. This method can also avoid the error of anti-counterfeiting results caused by the differences between different machines and improve the accuracy. Embodiment

[0073] This embodiment provides an anti-counterfeiting device based on the national emblem of a banknote. The device includes:

[0074] A preprocessing module, configured to preprocess the banknote to be recognized and multiple genuine banknote samples respectively to obtain binary images, where the binary images include: the binary image to be recognized and multiple sample binary images.

[0075] The sampling coordinate confirmation module is used to confirm vertices according to the original coordinates and pixel values of the pixel points in the binary image, and re-confirm the sampling coordinates (x, y) of the national emblem edge based on the first coordinate system with the vertex as the origin.

[0076] The standard curve fitting module is used to fit the standard feature curve equation of the national emblem edge according to the sampling coordinates of the sample binary image.

[0077] The anti-counterfeiting module is used to substitute the sampling coordinates of the binary image to be recognized into the standard feature curve equation. If the error is less than the preset error threshold, it is determined that the banknote to be recognized is genuine; otherwise, it is counterfeit. Among them, the preset error threshold includes a horizontal error threshold and a vertical error threshold.

[0078] The anti-counterfeiting device based on the national emblem of the banknote provided by the embodiment of the present invention has the same implementation principle and technical effects as those of the anti-counterfeiting method embodiment based on the national emblem of the banknote. For the sake of brief description, for the parts not mentioned in the device embodiment, reference can be made to the corresponding content in the foregoing method embodiment. Embodiment

[0079] Figure 5 The structural schematic diagram of an electronic device provided by the embodiment of the present application is shown, including: a processor 401, a storage medium 402, and a bus 403. The storage medium 402 stores machine-readable instructions executable by the processor 401. When the electronic device runs the data extraction method in the embodiment, the processor 401 communicates with the storage medium 402 through the bus 403, and the processor 401 executes the machine-readable instructions to execute the steps in the embodiment.

[0080] In the embodiment, the storage medium 402 can also execute other machine-readable instructions to execute other methods in the embodiment. For the specific method steps and principles of execution, refer to the description of the embodiment, and details will not be elaborated here.

[0081] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A banknote authenticity verification method based on the national emblem of banknotes, characterized in that, The method includes: S1: Preprocess the banknote to be recognized and multiple genuine banknote samples respectively to obtain binary images, where the binary images include: a binary image to be recognized and multiple sample binary images; S2: Confirm vertices according to the original coordinates and pixel values of the pixel points in the binary image, and re-confirm the sampling coordinates (x, y) of the national emblem edge according to the first coordinate system with the vertices as the origin; S3: Fit the standard feature curve equation of the national emblem edge according to the sampling coordinates of the sample binary images; S4: Substitute the sampling coordinates of the binary image to be recognized into the standard feature curve equation. If the error is less than the preset error threshold, it is determined that the banknote to be recognized is genuine, otherwise it is fake. Among them, the preset error threshold includes a horizontal error threshold and a vertical error threshold; Step S2 includes: S2-1: Establish an initial coordinate system with the pixel point in the upper left corner of the binary image as the coordinate origin, and traverse each pixel point row by row from top to bottom and from left to right; S2-2: When the pixel value of the first traversed pixel point is less than the preset first threshold, take this pixel point as the vertex; S2-3: Establish a first coordinate system with the vertex as the origin; S2-4: Confirm the sampling coordinates of the national emblem edge according to the first coordinate system and the pixel values of each pixel point in the binary image.

2. The banknote authenticity verification method based on the national emblem of the banknote according to claim 1, wherein Step S2-4 includes: Traverse each pixel point row by row from left to right starting from the X-axis of the first coordinate system. For each row, when the pixel point with a pixel value less than the first threshold appears for the first time, store the coordinate of this pixel point as one of the sampling coordinates in the sampling library; when the pixel values of Q consecutive pixel points in this row are all greater than or equal to the first threshold, and the abscissas of the sampling coordinates of the Q pixel points are all greater than c, store the previous pixel point of the Q consecutive pixel points as one of the sampling coordinates in the sampling library.

3. The banknote authenticity verification method based on the national emblem of the banknote according to claim 2, wherein, Step S2-4 also includes: For the rows where it is impossible to collect pixel values of Q consecutive pixel points that are all greater than or equal to the first threshold and the abscissas of the sampling coordinates of the Q pixel points are all greater than c, do not collect the sampling coordinates below this row.

4. The banknote authenticity verification method based on the national emblem of a banknote according to claim 3, wherein, Step S3 includes: S3-1: Confirm the preliminary parabola equation according to the sampling coordinates of the sample binary image. One sampling coordinate corresponds to one parabola equation, and each parabola equation corresponds to a coefficient p; S3-2: Average the multiple coefficients p of the preliminary parabola equation to obtain the coefficient of the special curve of this sample binary image; S3-3: Execute steps S3-1 and S3-2 for all sample binary images to obtain the coefficients of the special curves of each sample binary image, and then take the average value of the coefficients of the special curves of all sample binary images as the standard feature coefficient, and fit the standard feature curve equation of the national emblem edge.

5. The banknote authenticity verification method based on the national emblem of the banknote according to claim 4, wherein, Step S4 includes: S4-1: Substitute the abscissa x of the sampling coordinates of the binary image to be recognized into the above standard feature curve equation respectively to obtain the corresponding Y; S4-2: Substitute the ordinate y of the sampling coordinates of the binary image to be recognized into the above standard feature curve equation respectively to obtain the corresponding X; S4-3: Compare Y with the y of the sampling coordinates of the corresponding binary image to be recognized respectively to obtain a plurality of first differences. At the same time, compare X with the x of the sampling coordinates of the corresponding binary image to be recognized respectively to obtain a plurality of second differences; S4-4: If there are more than a first differences less than the vertical error threshold; and more than b second differences less than the horizontal error threshold, then the banknote to be recognized is a genuine banknote.

6. The banknote authenticity verification method based on the national emblem of a banknote according to claim 5, wherein, Step S1 includes: S1-1: Calculate the inclination angles of the initially collected genuine banknote samples and the banknote to be recognized respectively, and rotate and correct the genuine banknote samples and the banknote to be recognized according to the inclination angles to obtain their respective corrected banknote images; S1-2: Roughly intercept according to the coordinates of the preset rectangular area in the corrected banknote image to obtain a rough cut image; cut the rough cut image again to obtain a fine cut image, where the fine cut image is used to reflect the shape of the upper half curve of the national emblem; S1-3: Binarize and denoise the above-mentioned fine cut image to obtain a binary image, where the binary image includes: a binary image to be recognized and a plurality of sample binary images.

7. An anti-counterfeiting device based on the national emblem of banknotes, characterized in that, The banknote authenticity verification device includes: A preprocessing module for preprocessing the banknote to be recognized and a plurality of genuine banknote samples respectively to obtain a binary image, where the binary image includes: a binary image to be recognized and a plurality of sample binary images; A sampling coordinate confirmation module for confirming vertices according to the original coordinates and pixel values of the pixel points in the binary image, and reconfirming the sampling coordinates (x, y) of the national emblem edge according to the first coordinate system with the vertex as the origin; A standard curve fitting module for fitting the standard feature curve equation of the national emblem edge according to the sampling coordinates of the sample binary images; An authenticity verification module for substituting the sampling coordinates of the binary image to be recognized into the standard feature curve equation. If the error is less than the preset error threshold, it is determined that the above-mentioned banknote to be recognized is a genuine banknote, otherwise it is a counterfeit banknote, where the above-mentioned preset error threshold includes a horizontal error threshold and a vertical error threshold.

8. An electronic device, characterized in that, Includes: A processor, a storage medium and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to execute the steps of the banknote authenticity verification method based on the national emblem of the banknote as described in any one of claims 1 to 6.

Images