Method and system for determining authenticity of printed matter images

Abstract

The present invention provides a method and system for determining the authenticity of printed images, relating to the field of anti-counterfeiting technology. The method comprises sampling a detection area of ​​an image printed on a first authentic product; calculating the coordinates of feature points of each sample image and a set of feature point values, POI1; comparing every two sample images from the first to the mth sample images to obtain at least one number of similar points; multiplying the maximum number of similar points by a true determination coefficient, a gray coefficient, and a false determination coefficient, respectively, to obtain a true determination threshold, a gray threshold, and a false determination threshold; performing the above steps at least once to calculate and store the set of coordinates and feature point values, POI1, of at least one set of feature points, and the corresponding at least one true determination threshold, at least one gray threshold, and at least one false determination threshold, so as to determine the authenticity of the printed product to be detected based on the relationship between the number of similar points between the image of the printed product to be detected and the sample image and the at least one true determination threshold, at least one gray threshold, and at least one false determination threshold.

Description

Technical Field

[0001] The present invention relates to the field of anti-counterfeiting technology, and in particular to a method and system for determining the authenticity of a printed matter image. Background Art

[0002] Currently, counterfeiting and high-definition reproduction of printed materials, such as physical product packaging, tickets, and handicrafts, is a widespread phenomenon. Common methods of reproduction include high-definition reproduction with manual fine-tuning and copying the original design. There are three main approaches to this type of anti-counterfeiting technology. The first involves material-based anti-counterfeiting, which employs specialized substances or materials to achieve this goal. Generally speaking, material-based anti-counterfeiting methods are quite expensive. For example, the production equipment for security thread paper is expensive and the production process is very complex. The security thread itself is quite expensive to produce. Consequently, its reproduction is very costly, making it suitable for banknote production. While security inks are less expensive than security paper, they are still expensive and difficult to obtain, thus providing some degree of protection against counterfeiting. Moiré-like patterns rely on printing design and require certain printing equipment. Furthermore, moiré patterns, with their limited parameters, can be simulated using computers. In short, material-based anti-counterfeiting methods often incur high costs, primarily due to the high cost of counterfeiting, forging, and replicating printed materials. While this type of anti-counterfeiting technology is well-suited for currency, certificates, and various valuable documents, it's difficult to popularize it. Furthermore, with economic development and technological advancements, the exclusivity and uniqueness of these solutions have declined. Furthermore, most material anti-counterfeiting applications are difficult to pin down to individual objects, resulting in limited individualization. While RFID anti-counterfeiting technology can identify individual objects and boasts strong recognition capabilities, it suffers from poor anti-interference capabilities and may not function in environments with static electricity, strong magnetic fields, or high temperatures.

[0003] The second category involves digital information anti-counterfeiting technologies, primarily employing information encoding and hiding, leveraging the inherent effects of printing and copying on pixels. For example, information encoding, such as QR codes, can be added directly to packaging in reserved areas for reading and anti-counterfeiting detection. Hidden information, such as secret codes and printed watermarks, offers the best anti-counterfeiting effectiveness. These technologies embed robust information into the printed electronic image during pre-printing. During detection, image processing and extraction algorithms are used to automatically calculate the hidden information based on a set threshold. Currently, the main challenges with these two technologies are that they alter the appearance of printed materials, particularly when adding easily locatable graphics, such as QR codes (CN114580589B, "A Dual-Channel QR Code and Control Method for Anti-Copying and Information Hiding") and microdot codes (CN115423063B, "Anti-Copy Shading Anti-Counterfeiting Method and Apparatus Based on Microdot Codes"). These technologies also increase production processes and costs, rely on high-precision image acquisition equipment for sampling and detection, and present complex user operations, low identification accuracy, and a poor user experience. These challenges stem from the underlying technical principles.

[0004] The third type does not add any information to the original image, and relies on random high-definition detail collection during the production process. The disadvantages are that the collection cost is too high, including equipment cost and storage cost; it cannot achieve efficient and low-cost sampling, and there are also problems with complex user operations and low accuracy during detection. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for determining the authenticity of printed matter images, which can determine the authenticity of printed matter efficiently, simply and at low cost without affecting the appearance and increasing the original printing process and cost.

[0006] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for determining the authenticity of a printed image, the method comprising: performing a first image sampling on a detection area of ​​an image printed on a first authentic product to obtain a first sample image and a detection area mask; performing a second to m-th image sampling on the detection area of ​​the image printed on the first to n-th authentic products according to the detection area mask to obtain second to m-th sample images; calculating the coordinates of the feature points of each sample image in the first to m-th sample images and a set POI1 of feature point values ​​by a feature point recognition algorithm; comparing every two sample images in the first to m-th sample images according to the coordinates of the feature points of each sample image and the set POI1 of feature point values ​​to obtain at least one similarity point; and comparing the coordinates of the feature points of each sample image and the set POI1 of feature point values ​​to obtain at least one similarity point. The maximum number of similar points among the number of similar points less one is multiplied by the true determination coefficient, the gray coefficient and the false determination coefficient respectively to obtain the true determination threshold, the gray threshold and the false determination threshold; the above steps are performed at least once to calculate and store the coordinates of at least one group of feature points and the set POI1 of feature point values ​​from at least two sample images and the corresponding at least one true determination threshold, at least one gray threshold and at least one false determination threshold, so as to calculate the number of true determinations and the number of false determinations according to the number of similar points between the image of the printed product to be detected and the sample image, and the size relationship between the at least one true determination threshold, the at least one gray threshold and the at least one false determination threshold, and compare them with the true determination preset value and the false determination preset value to determine the authenticity of the printed product to be detected.

[0007] Preferably, the feature point value is an attribute value of the feature point image. When the attribute value is a grayscale value, the grayscale value is obtained by the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, B are color channels, a, b, c are grayscale ratios, and a+b+c=1.

[0008] Preferably, each image sampling in the first to mth image sampling includes continuously collecting u frames of images, and the method also includes: calculating the coordinates of the feature points of each frame image in the collected u frames of images and the set POI1 of feature point values ​​through a feature point recognition algorithm; and using the image with the largest number of feature points in the POI1 as the sample image of the current sampling.

[0009] Preferably, the method also includes: calculating the set POI1 of coordinates and feature point values ​​of the at least one group of feature points and the corresponding at least one true judgment threshold, at least one gray threshold and at least one false judgment threshold through a hash algorithm to obtain a corresponding feature number; and associating the feature number with the print number of the sampled printed matter.

[0010] Preferably, the set POI1 of coordinates and feature point values ​​of the feature points of each sample image is used to compare every two sample images from the first to the mth sample images to obtain at least one number of similar points, including: comparing the feature point values ​​of each pair of feature points with the closest positions in the two sample images, and when the comparison result is within a threshold range, judging the compared feature points as similar points to obtain the number of similar points of the two compared images, and the comparison method includes calculating any one of absolute value difference, square difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF and PSNR of the feature point values; performing the above steps for every two sample images to obtain the at least one number of similar points.

[0011] Preferably, the method of calculating the number of true judgments and the number of false judgments based on the number of similarities between the image of the printed matter to be detected and the sample image, and the relationship between the number of similarities between the at least one true judgment threshold, the at least one gray threshold, and the at least one false judgment threshold, and comparing the number of true judgments and the number of false judgments with the true judgment preset value and the false judgment preset value to determine the authenticity of the printed matter to be detected includes: calculating the coordinates of the feature points of the u-frame image of the printed matter to be detected and the feature point value set POI2 by a feature point recognition algorithm; calculating the coordinates of the feature points of the u-frame image of the printed matter to be detected and the feature point value set POI2 according to the coordinates of the feature points of the u-frame image of the printed matter to be detected and the feature point value set POI2 and the coordinates of the at least one set of feature points and the feature point value set POI I1, compare each frame image of the printed product to be detected with the coordinates of all feature points and the sample images corresponding to the feature point value set POI1. When the number of similar points is greater than or equal to the corresponding true judgment threshold, the number of true judgments is added by 1, and the comparison of the current frame of the printed product to be detected is completed; in the comparison of any frame image of the printed product to be detected with all sample images, if the number of similar points is greater than the corresponding false judgment threshold and less than or equal to the corresponding gray threshold, the number of false judgments is added by 1, until the number of true judgments is greater than the preset value for true judgment, the printed product to be detected is determined to be true; or when the number of false judgments is greater than the preset value for false judgment, the printed product to be detected is determined to be false.

[0012] An embodiment of the present invention further provides a system for determining the authenticity of printed images, the system comprising: a first sampling unit, a second sampling unit, and a processing unit, wherein the first sampling unit is used to perform a first image sampling on a detection area of ​​an image printed on a first authentic product to obtain a first sample image and a detection area mask; the second sampling unit is used to perform a second to m-th image sampling on the detection area of ​​an image printed on a first to n-th authentic product based on the detection area mask to obtain second to m-th sample images; the processing unit is used to: calculate the coordinates of the feature points of each sample image in the first to m-th sample images and a set of feature point values ​​POI1 by a feature point recognition algorithm; compare each two sample images in the first to m-th sample images according to the coordinates of the feature points of each sample image and the set of feature point values ​​POI1 Sample images are obtained to obtain at least one number of similar points; the largest number of similar points in the at least one number of similar points is multiplied by the true judgment coefficient, the gray coefficient and the false judgment coefficient respectively to obtain the true judgment threshold, the gray threshold and the false judgment threshold; the above steps are performed at least once to calculate and store the coordinates of at least one group of feature points and the set POI1 of feature point values ​​from at least two sample images and the corresponding at least one true judgment threshold, at least one gray threshold and at least one false judgment threshold, so as to calculate the number of true judgments and the number of false judgments based on the number of similar points between the image of the printed product to be detected and the sample image and the relationship between the at least one true judgment threshold, the at least one gray threshold and the at least one false judgment threshold, and compare them with the true judgment preset value and the false judgment preset value to determine the authenticity of the printed product to be detected.

[0013] Preferably, the feature point value is an attribute value of the feature point image. When the attribute value is a grayscale value, the grayscale value is obtained by the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, B are color channels, a, b, c are grayscale ratios, and a+b+c=1.

[0014] Preferably, each image sampling in the first to mth image samplings includes continuously acquiring u frames of images, and the first sampling unit and the second sampling unit are further used to: calculate the coordinates of the feature points of each frame image in the acquired u frames of images and the set POI1 of feature point values ​​through a feature point recognition algorithm; and use the image with the largest number of feature points in the POI1 as the sample image for the current sampling.

[0015] Preferably, the processing unit is used to: compare the feature point values ​​of each pair of feature points with the closest positions in the two sample images, and when the comparison result is within a threshold range, judge the compared feature points as similar points to obtain the number of similar points in the two compared images, and the comparison method includes calculating any one of the absolute value difference, square difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF and PSNR of the feature point values; perform the above steps for every two sample images to obtain the at least one number of similar points.

[0016] Through the above technical solution, the printed matter image authenticity determination method and printed matter image authenticity determination system provided by the present invention are adopted, without the need to pre-hide information in the printed packaging image. The authenticity of the printed matter can be determined efficiently, simply and at low cost without affecting the appearance and without increasing the original printing process and cost.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0019] Figure 1 This is a flow chart of a method for determining the authenticity of a printed matter image provided by one embodiment of the present invention;

[0020] Figure 2 This is a sampling schematic diagram of a method for determining the authenticity of a printed matter image provided by an embodiment of the present invention;

[0021] Figure 3 is a flow chart of a method for determining the authenticity of a printed matter image provided by another embodiment of the present invention;

[0022] Figure 4 This is a structural block diagram of a printed matter image authenticity determination system provided by one embodiment of the present invention.

[0023] Description of Reference Numerals

[0024] 1-First sampling unit 2-Second sampling unit

[0025] 3-Processing Unit DETAILED DESCRIPTION

[0026] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0027] Figure 1 FIG. 1 is a flow chart of a method for determining the authenticity of a printed image provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0028] Step S101, performing a first image sampling on a detection area of ​​an image printed on a first authentic product to obtain a first sample image and a detection area mask;

[0029] Specifically, the detection area can be a square area with a central side length of R pixels, such as 480, 640, 960, 1080, 1280, 1920, 2160, 2560, 3840, 4096, and other common image narrow side lengths, preferably 480. Of course, the square area is only a preferred embodiment, and those skilled in the art will appreciate that the detection area can also be set as a rectangular area, and the side length can also be set as needed.

[0030] Considering that consecutive frames may experience image jitter and loss of focus, in one embodiment, it is preferable to continuously acquire u frames of images during each image sampling. u can take any value between 1 and 100, with u=10 being the preferred value. In this case, the sampling time is in seconds, and the user hardly needs to wait. When continuously acquiring u frames of images during each image sampling, u images are obtained. In one embodiment, a feature point recognition algorithm can be used to calculate the feature points and feature point value set POI1 for each of the u frames of images collected. The image with the largest number of feature points in POI1 is then used as the sample image for the current sampling. If an image has two feature points, its POI=[(x1, y1, h1), (x2, y2, h2)], where x1, x2, y1, y2 are the coordinates of the feature points, and h1 and h2 are the feature point values. It should be noted that the feature point recognition algorithm may be a corner detection algorithm, such as SIFT corner detection, Harris corner detection, SUSAN corner detection, or a corner detection algorithm derived from machine learning, or may be other recognition algorithms for identifying POIs in images. The embodiment of the present invention provides an algorithm with the following specific steps:

[0031] Step 1: Multi-scale image pyramid generation: Perform Gaussian pyramid downsampling on the input image to generate at least two image layers with different resolutions;

[0032] Step 2: Dynamic threshold candidate point detection: For each layer of the image, calculate the grayscale difference of the annular neighborhood around the pixel point, and dynamically adjust the difference threshold according to the grayscale standard deviation of the local window to screen candidate corner points;

[0033] Step 3: Edge constraint filtering: Perform edge detection on the current layer image. If the candidate point is on the edge line or in its neighborhood, the candidate point is eliminated.

[0034] Step 4: Cross-scale response aggregation: Map the candidate points of each layer to the original image coordinate system, and retain the corner points with the maximum response value through non-maximum suppression.

[0035] In addition, the feature point value can be the attribute value of the image such as the brightness value, grayscale value, etc. of the feature point. Taking the grayscale value as an example, the grayscale value can be obtained by calculating the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, and B are color channels, a, b, and c are 0 to 1, and a+b+c=1. It is preferred to take the known grayscale ratios of 0.3, 0.6, and 0.1.

[0036] In one embodiment, the detection area mask is generated based on the last image in the collected u-frame image. Specifically, during the first image sampling, a screenshot is automatically taken of the detection area of ​​the last sample image, and a semi-transparent mask perceptible to the human eye is generated and uploaded to the cloud for use in subsequent sampling and contour alignment. It will be understood that the above is merely a preferred method. When no u-frame image is collected, the detection area mask can also be directly generated using the detection area during the first image sampling. Alternatively, when collecting u-frame images, the detection area mask can also be generated using the first or other frame image in the u-frame image. This is not limited in the present embodiment.

[0037] Step S102, performing second to m-th image sampling on the inspection areas of the images printed on the first to n-th authentic products according to the inspection area mask to obtain second to m-th sample images;

[0038] Specifically, if Figure 2 As shown in the example image (half of the five rings), the right-hand color image is the image to be sampled, and the left-hand black and white image is the semi-transparent detection area mask. During sampling, the left detection area mask must be aligned with the right-hand image to be sampled. For the second to mth sampling, the semi-transparent detection area mask is loaded, and the acquisition device is moved to adjust the image to be sampled to a position close to the detection area mask image, ensuring that the horizontal and vertical coordinate deviations of the upper left corner are less than K pixels (preferably 0 ≤ K ≤ 20). This yields the second to mth sample images.

[0039] It should be noted that in one embodiment, sampling can be performed for the first through m times on only one authentic product. However, even if all products are genuine, there will be variations in pattern position, shape, and color within a certain range. These variations can produce differences in image details that can be calculated and captured by the program. Therefore, another embodiment can select representative authentic products as candidate samples, and perform sampling for the first through m times on multiple authentic products. For optimal efficiency, two candidate samples can be selected, and sampling can be performed only twice.

[0040] Step S103, calculating the coordinates of the feature points and the set of feature point values ​​POI1 of each sample image from the first to the mth sample images by a feature point recognition algorithm;

[0041] Specifically, after obtaining the first to mth sample images by the above method, the coordinates of the feature points of each sample image and the set POI1 of feature point values ​​can be obtained by the feature point recognition algorithm described above.

[0042] Step S104 , comparing every two sample images from the first to the mth sample images according to the coordinates of the feature points of each sample image and the feature point value set POI1 to obtain at least one number of similar points;

[0043] Specifically, for two sample images, A and B, for each feature point in sample image A, the feature point with the largest value is found among several feature points above, below, left, and right of the same coordinate in sample image B. This point is then compared with the feature point in sample image A to obtain a comparison result, allowing for a coordinate offset range (e.g., ±5 pixels). Comparison methods can calculate the absolute value difference, squared difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF, PSNR, and other methods for the feature point values.

[0044] When the comparison result is within the threshold range (preferably greater than 0.8), the compared feature points are determined to be similar points. After performing the above comparison on all feature points in sample image A, the number of similar points in the compared sample images A and B is obtained.

[0045] For each pair of sample images, perform the steps of comparing sample images A and B to obtain at least one number of similar points. If there are only two sample images, A and B, then there is only one similar point. If there are three sample images, A, B, and C, then according to the permutations and combinations, there should be three similar points.

[0046] Step S105, multiplying the maximum number of similar points among the at least one number of similar points by the true determination coefficient, the gray coefficient, and the false determination coefficient, respectively, to obtain a true determination threshold, a gray threshold, and a false determination threshold;

[0047] Specifically, the true determination coefficient is preferably 0.85, and the true determination threshold is obtained by multiplying the maximum number of similar points by 0.85; the gray coefficient is preferably 0.7, and the gray threshold is obtained by multiplying the maximum number of similar points by 0.7; and the false determination coefficient is preferably 0.5, and the false determination threshold is obtained by multiplying the maximum number of similar points by 0.5. Of course, in other embodiments, the true determination coefficient, gray coefficient, and false determination coefficient can also be other values ​​and can be set according to different scenarios.

[0048] Step S106, executing the above steps at least once to calculate and store the coordinates of at least one set of feature points from at least two sample images, and a set POI1 of feature point values, as well as the corresponding at least one true judgment threshold, at least one gray threshold, and at least one false judgment threshold, so as to calculate the number of true judgments and the number of false judgments based on the number of similarities between the image of the printed product to be inspected and the sample image, and the relationship between the at least one true judgment threshold, the at least one gray threshold, and the at least one false judgment threshold, and compare them with the true judgment preset value and the false judgment preset value to determine the authenticity of the printed product to be inspected.

[0049] Specifically, executing steps S101-S105 once obtains a set of feature point coordinates and feature point value sets POI1, as well as a true threshold, a gray threshold, and a false threshold. Repeating steps S101-S105 multiple times can obtain multiple sets of feature point coordinates and feature point value sets POI1, as well as corresponding true thresholds, gray thresholds, and false thresholds. Subsequently, a hash algorithm can be used to calculate the corresponding feature number for at least one set of feature point coordinates and feature point value sets POI1, as well as the corresponding at least one true threshold, gray threshold, and false threshold.

[0050] Associate the feature number with the print number of the sampled print, and upload all collected sample images, detection area masks, feature point coordinates and feature point value set POI1, true judgment threshold, gray threshold, false judgment threshold, and feature number and the print number of the sampled print to the local or cloud database of the detection client software.

[0051] When the user needs to detect the authenticity of the printed matter to be detected, the associated feature number is loaded from the local or cloud database of the detection client software according to the print number of the printed matter selected by the user, so as to obtain the sample image, detection area mask, coordinates of the feature point and the set of feature point values ​​POI1, true judgment threshold, gray threshold, false judgment threshold, etc. to judge the image of the current printed matter.

[0052] First, the coordinates of the feature points of the u-frame image of the printed product to be detected and the set of feature point values ​​POI2 are calculated by the feature point recognition algorithm. Then, according to the comparison method described above, the u-frame image of the printed product to be detected and the set of feature point values ​​POI2 and the set of feature point coordinates and feature point values ​​POI1 of at least one group of feature points are compared. The specific method is as follows: Figure 3 shown.

[0053] like Figure 3As shown, first, a comparison is performed on any unmatched frame image of the printed product to be tested. Take the coordinates and feature point value set POI2 of a frame image of the printed product to be tested that has not been compared, and take the coordinates and feature point value set POI1 of a sample image that has not been compared for comparison. There are three cases:

[0054] (1) When the number of similar points is greater than or equal to the corresponding true judgment threshold, the number of true judgments is added by 1. At this time, it is determined whether the number of true judgments is greater than the preset value (which can be 1, preferably 5). When the number of true judgments is greater than the preset value, the printed matter to be tested is directly determined to be true; when the number of true judgments is not greater than the preset value, the comparison of the current frame of the printed matter to be tested is completed, and another frame image of the printed matter to be tested that has not been compared is selected and compared with the sample image corresponding to the set of coordinates and feature point values ​​of all feature points POI1;

[0055] (2) When the number of similar points is greater than the corresponding false judgment threshold and less than or equal to the corresponding gray threshold, the number of sample false positives is added by 1, and the coordinates of the feature points and the set of feature point values ​​POI1 of the next unmatched sample image are taken for comparison;

[0056] (3) When the number of similar points is less than or equal to the corresponding false judgment threshold, or greater than the corresponding gray threshold and less than the corresponding true judgment threshold, they are not counted, and the coordinates and feature point value set POI1 of the next unmatched sample image are taken for comparison.

[0057] When the image comparison of this frame is completed (i.e., all sample images have been compared with this frame image), if there are no true judgment times but there are sample false times, no matter how many sample false times there are, the false judgment times are increased by 1, and another frame image of the printed matter to be tested that has not been compared is selected and compared with the sample image corresponding to the set of all feature point coordinates and feature point values ​​POI1;

[0058] When the comparison of this frame image is completed (that is, all sample images have been compared with this frame image), if there are no true judgment times and no false sample times, another frame image of the printed product to be tested that has not been compared is directly selected and compared with the sample image corresponding to the set POI1 of all feature point coordinates and feature point values.

[0059] In this way, each frame image is compared with all sample images, and the number of true judgments and false judgments in the comparison process is accumulated until the number of true judgment thresholds is greater than the preset value, the printed product to be tested is judged to be true; or when the number of false judgments is greater than the preset value, the printed product to be tested is judged to be false.

[0060] If the conditions for judging authenticity or falsehood are not met within the specified time (preferably 10 seconds, but not limited to this), the user will be prompted to retry aligning the reference pattern outline. If authenticity cannot be judged after multiple alignments, it is suspected to be a fake.

[0061] Those skilled in the art should understand that the process of determining the authenticity of the printed matter to be inspected provided in the above embodiment is only an example, and reasonable changes and modifications can be made therein, such as the counting method of the number of true judgments and the number of false judgments, etc., which can also be used to determine the authenticity of the printed matter to be inspected, and will not be repeated here.

[0062] The embodiment of the present invention does not need to pre-hide information in the printed packaging image, and can determine the authenticity of printed materials efficiently, simply and at low cost without affecting the appearance and increasing the original printing process and cost.

[0063] Figure 4 FIG. 1 is a structural block diagram of a printed matter image authenticity determination system provided by an embodiment of the present invention. Figure 4 As shown, the system includes: a first sampling unit 1, a second sampling unit 2 and a processing unit 3, wherein the first sampling unit 1 is used to perform a first image sampling on the detection area of ​​the image printed on the first authentic product to obtain a first sample image and a detection area mask; the second sampling unit 2 is used to perform a second to m-th image sampling on the detection area of ​​the image printed on the first to n-th authentic products according to the detection area mask to obtain second to m-th sample images; the processing unit 3 is used to: calculate the coordinates of the feature points and the feature point value set POI1 of each sample image in the first to m-th sample images by a feature point recognition algorithm; compare every two sample images in the first to m-th sample images according to the coordinates of the feature points and the feature point value set POI1 of each sample image, and obtain the second to m-th sample images. less one similar point; multiplying the largest number of similar points among the at least one number of similar points by the true determination coefficient, the gray coefficient and the false determination coefficient respectively to obtain the true determination threshold, the gray threshold and the false determination threshold; performing the above steps at least once to calculate and store the coordinates of at least one group of feature points and the set POI1 of feature point values ​​from at least two sample images and the corresponding at least one true determination threshold, at least one gray threshold and at least one false determination threshold, so as to calculate the number of true determinations and the number of false determinations according to the number of similar points between the image of the printed product to be detected and the sample image, and the relationship between the at least one true determination threshold, the at least one gray threshold and the at least one false determination threshold, and compare with the true determination preset value and the false determination preset value to determine the authenticity of the printed product to be detected.

[0064] Preferably, the feature point value is an attribute value of the feature point image. When the attribute value is a grayscale value, the grayscale value is obtained by the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, B are color channels, a, b, c are grayscale ratios, and a+b+c=1.

[0065] Preferably, each image sampling in the first to mth image samplings includes continuously acquiring u frames of images, and the first sampling unit 1 and the second sampling unit 2 are further used to: calculate the coordinates of the feature points of each frame image in the acquired u frames of images and the set POI1 of feature point values ​​through a feature point recognition algorithm; and use the image with the largest number of feature points in the POI1 as the sample image for the current sampling.

[0066] Preferably, the processing unit 3 is used to: compare the feature point values ​​of each pair of feature points with the closest positions in the two sample images, and when the comparison result is within the threshold range, judge the compared feature points as similar points to obtain the number of similar points in the two compared images, and the comparison method includes calculating any one of the absolute value difference, square difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF and PSNR of the feature point values; perform the above steps for every two sample images to obtain the at least one number of similar points.

[0067] The embodiment of the printed matter image authenticity determination system described above is similar to the embodiment of the printed matter image authenticity determination method described above, and will not be described in detail here.

[0068] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0070] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0072] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0073] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0074] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0075] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0076] The above are merely 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 changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining the authenticity of a printed image, characterized in that: The method comprises: Performing a first image sampling on the detection area of ​​the image printed on the first authentic product to obtain a first sample image and a detection area mask; performing second to m-th image sampling on the inspection areas of the images printed on the first to n-th authentic products according to the inspection area mask to obtain second to m-th sample images; Calculate the coordinates of the feature points of each sample image from the first to the mth sample image and the set of feature point values ​​POI1 by a feature point recognition algorithm; Comparing every two sample images from the first to the mth sample images according to the set POI1 of the coordinates and feature point values ​​of each sample image to obtain at least one number of similar points; Multiplying the largest number of similar points among the at least one number of similar points by the true determination coefficient, the gray coefficient, and the false determination coefficient, respectively, to obtain a true determination threshold, a gray threshold, and a false determination threshold; Perform the above steps at least once to calculate and store a set POI1 of coordinates and feature point values ​​of at least one set of feature points from at least two sample images, as well as the corresponding at least one true determination threshold, at least one gray threshold, and at least one false determination threshold, so as to calculate the number of true determinations and the number of false determinations based on the number of similarities between the image of the printed product to be inspected and the sample images and the relationship between the at least one true determination threshold, the at least one gray threshold, and the at least one false determination threshold, and compare the results with the preset true determination value and the preset false determination value to determine the authenticity of the printed product to be inspected; The method further includes: calculating the set POI1 of the coordinates and feature point values ​​of the at least one set of feature points and the corresponding at least one true threshold, at least one gray threshold and at least one false threshold by a hash algorithm to obtain a corresponding feature number; Associating the feature number with the print number of the sampled print; The calculating of the number of true determinations and the number of false determinations based on the number of similarities between the image of the printed matter to be detected and the sample image and the relationship between the at least one true determination threshold, the at least one gray threshold, and the at least one false determination threshold, and comparing the numbers with the true determination preset value and the false determination preset value to determine the authenticity of the printed matter to be detected includes: Calculate the coordinates of the feature points and the feature point value set POI2 of the u-frame image of the printed matter to be detected by a feature point recognition algorithm; According to the coordinates of the feature points of the u-frame image of the printed product to be detected and the feature point value set POI2 and the coordinates of the at least one group of feature points and the feature point value set POI1, each frame image of the printed product to be detected is compared with the sample images corresponding to the coordinates of all feature points and the feature point value set POI1. When the number of similar points is greater than or equal to the corresponding true judgment threshold, the number of true judgments is increased by 1, and the comparison of the current frame of the printed product to be detected is completed; in the comparison of any frame image of the printed product to be detected with all sample images, if the number of similar points is greater than the corresponding false judgment threshold and less than or equal to the corresponding gray threshold, the number of false judgments is increased by 1, until the number of true judgments is greater than the true judgment preset value, the printed product to be detected is determined to be true; or when the number of false judgments is greater than the false judgment preset value, the printed product to be detected is determined to be false.

2. The method for determining the authenticity of a printed matter image according to claim 1, wherein: The feature point value is an attribute value of the feature point image. When the attribute value is a grayscale value, the grayscale value is obtained by the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, and B are color channels, a, b, and c are grayscale ratios, and a+b+c=1.

3. The method for determining the authenticity of a printed matter image according to claim 1, wherein: Each of the first to m-th image samplings includes continuously acquiring u frames of images, and the method further includes: Calculate the coordinates of the feature points of each frame image and the set of feature point values ​​POI1 in the collected u-frame image by using the feature point recognition algorithm; The image with the largest number of feature points in the POI1 is used as the sample image for the current sampling.

4. The method for determining the authenticity of a printed matter image according to claim 1, wherein: The step of comparing every two sample images from the first to the mth sample images based on the set POI1 of coordinates and feature point values ​​of each sample image to obtain at least one number of similar points includes: Compare the feature point values ​​of each pair of closest feature points in the two sample images. When the comparison result is within a threshold range, the compared feature points are judged to be similar points to obtain the number of similar points in the two compared images. The comparison method includes calculating any one of the absolute value difference, square difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF and PSNR of the feature point values. The above steps are performed for every two sample images to obtain the at least one number of similar points.

5. A printed matter image authenticity determination system, characterized in that: The system comprises: A first sampling unit, a second sampling unit and a processing unit, wherein: The first sampling unit is used to perform a first image sampling on the detection area of ​​the image printed on the first authentic product to obtain a first sample image and a detection area mask; The second sampling unit is configured to perform second to m-th image sampling on the detection areas of the images printed on the first to n-th authentic products according to the detection area mask to obtain second to m-th sample images; A processing unit for: Calculate the coordinates of the feature points of each sample image from the first to the mth sample image and the set of feature point values ​​POI1 by a feature point recognition algorithm; Comparing every two sample images from the first to the mth sample images according to the set POI1 of the coordinates and feature point values ​​of each sample image to obtain at least one number of similar points; Multiplying the largest number of similar points among the at least one number of similar points by the true determination coefficient, the gray coefficient, and the false determination coefficient, respectively, to obtain a true determination threshold, a gray threshold, and a false determination threshold; Perform the above steps at least once to calculate and store a set POI1 of coordinates and feature point values ​​of at least one set of feature points from at least two sample images, as well as the corresponding at least one true determination threshold, at least one gray threshold, and at least one false determination threshold, so as to calculate the number of true determinations and the number of false determinations based on the number of similarities between the image of the printed product to be inspected and the sample images and the relationship between the at least one true determination threshold, the at least one gray threshold, and the at least one false determination threshold, and compare the results with the preset true determination value and the preset false determination value to determine the authenticity of the printed product to be inspected; The processing unit is further configured to: The set POI1 of the coordinates and feature point values ​​of the at least one set of feature points and the corresponding at least one true threshold, at least one gray threshold and at least one false threshold are calculated by a hash algorithm to obtain a corresponding feature number; Associating the feature number with the print number of the sampled print; The calculating of the number of true determinations and the number of false determinations based on the number of similarities between the image of the printed matter to be detected and the sample image and the relationship between the at least one true determination threshold, the at least one gray threshold, and the at least one false determination threshold, and comparing the numbers with the true determination preset value and the false determination preset value to determine the authenticity of the printed matter to be detected includes: Calculate the coordinates of the feature points and the feature point value set POI2 of the u-frame image of the printed matter to be detected by a feature point recognition algorithm; According to the coordinates of the feature points of the u-frame image of the printed product to be detected and the feature point value set POI2 and the coordinates of the at least one group of feature points and the feature point value set POI1, each frame image of the printed product to be detected is compared with the sample images corresponding to the coordinates of all feature points and the feature point value set POI1. When the number of similar points is greater than or equal to the corresponding true judgment threshold, the number of true judgments is increased by 1, and the comparison of the current frame of the printed product to be detected is completed; in the comparison of any frame image of the printed product to be detected with all sample images, if the number of similar points is greater than the corresponding false judgment threshold and less than or equal to the corresponding gray threshold, the number of false judgments is increased by 1, until the number of true judgments is greater than the true judgment preset value, the printed product to be detected is determined to be true; or when the number of false judgments is greater than the false judgment preset value, the printed product to be detected is determined to be false.

6. The printed matter image authenticity determination system according to claim 5, characterized in that: The feature point value is an attribute value of the feature point image. When the attribute value is a grayscale value, the grayscale value is obtained by the formula CV=aR+bG+cB, where CV is the grayscale value, R, G, and B are color channels, a, b, and c are grayscale ratios, and a+b+c=1.

7. The printed matter image authenticity determination system according to claim 5, characterized in that: Each of the first to m-th image samplings includes continuously acquiring u frames of images, and the first sampling unit and the second sampling unit are further configured to: Calculate the coordinates of the feature points of each frame image and the set of feature point values ​​POI1 in the collected u-frame image by using the feature point recognition algorithm; The image with the largest number of feature points in the POI1 is used as the sample image for the current sampling.

8. The printed matter image authenticity determination system according to claim 5, characterized in that: The processing unit is used for: Compare the feature point values ​​of each pair of closest feature points in the two sample images. When the comparison result is within a threshold range, the compared feature points are judged to be similar points to obtain the number of similar points in the two compared images. The comparison method includes calculating any one of the absolute value difference, square difference, Euclidean distance, Manhattan distance, Chebyshev distance, difference, normalized difference, gradient comparison, VIF and PSNR of the feature point values. The above steps are performed for every two sample images to obtain the at least one number of similar points.

Images