Identification method of gradient color anti-counterfeiting mark, electronic equipment and storage medium

Abstract

The invention discloses an identification method of a gradient color anti-counterfeiting mark, electronic equipment and a storage medium, and relates to the technical field of anti-counterfeiting printing identification, and the identification method comprises the steps: sequentially obtaining first image information of anti-counterfeiting marks in all products in the same batch; identifying the first image information, and constructing a gradient feature data set about a corresponding batch; according to the gradient feature data set, determining a predicted printing change rule of the products in the corresponding batch about the anti-counterfeiting mark; and obtaining an authenticity identification result according to the predicted printing change rule and a preset factory printing change rule. An anti-counterfeiting mark in a product is obtained through printing of gradient color anti-counterfeiting mark printing equipment, the driving assembly is controlled to drive the ink fountain partition plate to move on the ink inlet inclined plate according to the factory printing change rule, and the rolling brush structure is controlled to conduct rolling coating on the product in sequence. According to the invention, the anti-counterfeiting performance and the accuracy of anti-counterfeiting identification can be improved.

Description

Technical Field

[0001] This application relates to the technical field of anti-counterfeiting printing identification, and particularly to a method for identifying a gradient anti-counterfeiting label, an electronic device, and a storage medium. Background Art

[0002] At present, with the booming development of the commodity economy, anti-counterfeiting technology, as a key means to protect brands and maintain market order, is becoming increasingly important. Currently, some anti-counterfeiting label printing technologies use the method of partitions to achieve the color gradient effect. This technology has improved the anti-counterfeiting performance to a certain extent and increased the product recognition rate with a unique gradient color design. However, from the perspective of anti-counterfeiting means, due to the fixed position of the partitions, the gradient effect is relatively fixed, and the anti-counterfeiting gradient position lacks variation. Lawbreakers can easily imitate a similar anti-counterfeiting gradient effect through simple observation, measurement, and replication means.

[0003] On the other hand, in the identification of anti-counterfeiting labels, manual identification is easily affected by subjective factors. Different people have different perception and judgment standards for colors and pattern details. For example, different visual sensitivities and levels of experience will lead to different judgment results for the same anti-counterfeiting label, and it is difficult to comprehensively and accurately observe and analyze the details in the anti-counterfeiting label. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. Therefore, this application provides a method for identifying a gradient anti-counterfeiting label, an electronic device, and a storage medium, which can improve the anti-counterfeiting performance and the accuracy of anti-counterfeiting identification.

[0005] In a first aspect, this application provides a method for identifying a gradient anti-counterfeiting label, including:

[0006] Sequentially obtaining the first image information of the anti-counterfeiting labels in all products of the same batch;

[0007] Identifying the first image information to construct a gradient feature data set for the corresponding batch;

[0008] Determining the predicted printing change rule of the products in the corresponding batch regarding the anti-counterfeiting label according to the gradient feature data set;

[0009] Obtaining the authenticity identification result according to the predicted printing change rule and the preset factory printing change rule;

[0010] Among them, the anti-counterfeiting label is printed by a gradient anti-counterfeiting label printing device. The gradient anti-counterfeiting label printing device includes an ink inlet structure and a rolling brush structure. The ink inlet structure includes an ink inlet inclined plate, an ink tank partition plate, a driving component, and at least two ink supply cartridges of different colors. The ink tank partition plate is arranged on the ink inlet inclined plate to divide the ink inlet inclined plate into two ink inlet areas. The driving end of the driving component is connected to the ink tank partition plate. The two ink supply cartridges are respectively located above the two ink inlet areas. The ink inlet end of the rolling brush structure is butted against the ink outlet end of the ink inlet inclined plate;

[0011] The anti-counterfeiting label is printed through the following steps:

[0012] Obtain the preset printing change rule for factory production;

[0013] Open the ink supply cartridges to enable the ink to flow to the corresponding ink inlet areas, and control the driving component to drive the ink tank partition plate to move on the ink inlet inclined plate according to the printing change rule for factory production;

[0014] Control the rolling brush structure to roll-coat the products in sequence, so as to form the anti-counterfeiting label at the target position of each product.

[0015] The method for identifying a gradient anti-counterfeiting label according to an embodiment of the first aspect of the present application has at least the following beneficial effects: When printing an anti-counterfeiting label on a product, first obtain a preset factory printing change rule, which stipulates the movement mode of the ink tank partition during the printing process. Open at least two ink supply cartridges of different colors, and let the ink flow onto the ink inlet inclined plate into two ink inlet areas separated by the ink tank partition. At the same time, the driving component drives the ink tank partition to move on the ink inlet inclined plate according to the preset factory printing change rule, so as to change the mixing ratio of the ink in the two ink inlet areas and achieve different color gradient effects. The ink inlet end of the roller brush structure is docked with the ink outlet end of the ink inlet inclined plate. After obtaining the mixed ink, the product is roller-coated in sequence to form an anti-counterfeiting label with a specific gradient effect at the target position of each product. During the anti-counterfeiting label identification process, first image information of the anti-counterfeiting labels on all products in the same batch is obtained in sequence, and the obtained first image information is identified and processed, so as to be sorted into a gradient feature data set corresponding to the batch. Subsequently, based on the constructed gradient feature data set, the change trend of the gradient features of the anti-counterfeiting labels in the same batch of products is analyzed, so as to determine the predicted printing change rule of the products in the corresponding batch regarding the anti-counterfeiting label. Compare the determined predicted printing change rule with the preset factory printing change rule. If the two are consistent or the difference is within an acceptable range, it is determined that the anti-counterfeiting label of the product is genuine; otherwise, it is determined to be fake. In the printing of the anti-counterfeiting label of the product of the present application, a movable ink tank partition is adopted, and the partition is driven to move according to the preset factory printing change rule, so that the gradient effect of the anti-counterfeiting labels of the same batch of products has a certain variability. This dynamic change increases the complexity and non-replicability of the anti-counterfeiting label and improves the anti-counterfeiting performance. In addition, for such a dynamically changing anti-counterfeiting label, based on the methods of image processing and data analysis, the features of the anti-counterfeiting label can be extracted more accurately. By comparing the predicted printing change rule with the factory printing change rule, the accuracy of anti-counterfeiting label identification is improved, and the possibility of misjudgment is reduced.

[0016] According to some embodiments of the first aspect of the present application, the identifying the first image information and constructing a gradient feature data set corresponding to the batch includes:

[0017] Performing grayscale processing on the first image information to obtain grayscale image information;

[0018] Performing noise reduction and enhancement processing on the grayscale image information to obtain target image information;

[0019] Determining gradient edge features according to the target image information;

[0020] Determining gradient region features corresponding to the anti-counterfeiting label according to the gradient edge features;

[0021] Generate the gradient feature dataset according to all the gradient region features of the same batch in the detection order of the product.

[0022] According to some embodiments of the first aspect of the present application, the determining the gradient edge feature according to the target image information includes:

[0023] Calculate the color change gradient corresponding to each pixel point according to the target image information;

[0024] Perform screening processing on the pixel points according to the color change gradient to determine the true edge points;

[0025] Form a number of candidate edge features according to the continuous true edge points;

[0026] Screen the candidate edge features according to a preset regional reference width and length integrity threshold to determine the gradient edge feature.

[0027] According to some embodiments of the first aspect of the present application, the performing screening processing on the pixel points according to the color change gradient to determine the true edge points includes:

[0028] When the color change gradient of the pixel point is less than a preset first gradient threshold, mark the corresponding pixel point as a non-edge point;

[0029] When the color change gradient of the pixel point is greater than or equal to the first gradient threshold and less than a preset second gradient threshold, mark the corresponding pixel point as a weak edge point;

[0030] When the color change gradient of the pixel point is greater than or equal to the second gradient threshold, mark the corresponding pixel point as a strong edge point;

[0031] Take the pixel points corresponding to the marked strong edge points as the true edge points;

[0032] When there are no pixel points marked as strong edge points within a preset number of pixels around the pixel points marked as weak edge points, mark the pixel points as non-edge points;

[0033] When there are pixel points marked as strong edge points within a preset number of pixels around the pixel points marked as weak edge points, take the pixel points as the true edge points.

[0034] According to some embodiments of the first aspect of the present application, the screening the candidate edge features according to a preset regional reference width and length integrity threshold to determine the gradient edge feature includes:

[0035] Determine the regional reference width according to the width of the ink groove partition;

[0036] Calculate the edge length of each of the candidate edge features in the first direction;

[0037] Delete the candidate edge features whose edge lengths are less than the length integrity threshold;

[0038] Calculate the average distance between the remaining candidate edge features and other candidate edge features in a direction perpendicular to the first direction, and determine boundary candidate pairs based on the regional reference width;

[0039] Take the two candidate edge features in the boundary candidate pair as the gradient edge features.

[0040] According to some embodiments of the first aspect of the present application, the taking the two candidate edge features in the boundary candidate pair as the gradient edge features includes:

[0041] When there are two or more boundary candidate pairs, calculate the color change standard value of each boundary candidate pair according to the color change gradient of all pixel points in the edge candidate pair;

[0042] Determine the edge parallelism according to the two candidate edge features in the boundary candidate pair;

[0043] Determine the scoring value of each boundary candidate pair according to the color change standard value and the edge parallelism;

[0044] Take the two candidate edge features in the boundary candidate pair with the highest scoring value as the gradient edge features.

[0045] According to some embodiments of the first aspect of the present application, the determining the predicted printing change rule of the product regarding the anti-counterfeiting mark in the corresponding batch according to the gradient feature dataset includes:

[0046] Calculate the gradient center coordinates of each gradient region feature in the gradient feature dataset;

[0047] Construct a coordinate system regarding the product and the position of the corresponding gradient region feature;

[0048] Generate a predicted change curve graph in the coordinate system according to the gradient center coordinates corresponding to each product and the detection order of the product, and take the predicted change curve graph as the predicted printing change rule of the product regarding the anti-counterfeiting mark in the corresponding batch.

[0049] According to some embodiments of the first aspect of the present application, the obtaining the authenticity identification result according to the predicted printing change rule and the preset factory printing change rule includes:

[0050] Calculate the change similarity between the predicted change curve graph corresponding to the predicted printing change rule and the factory change curve graph of the factory printing change rule;

[0051] When the change similarity is greater than or equal to a preset similarity threshold, determine that the authenticity identification result of the products in the same batch is true;

[0052] When the change similarity is less than the similarity threshold, determine that the authenticity identification result of the products in the same batch is false.

[0053] In a second aspect, the present application further provides an electronic device, including:

[0054] At least one memory;

[0055] At least one processor;

[0056] At least one program;

[0057] The program is stored in the memory, and the processor executes at least one of the programs to implement the identification method of the gradient color anti-counterfeiting mark as described in any embodiment of the first aspect.

[0058] In a third aspect, the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer-executable signal, and the computer-executable signal is used to execute the identification method of the gradient color anti-counterfeiting mark as described in any embodiment of the first aspect.

[0059] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Additional aspects and advantages of the present application will become apparent and be readily understood in conjunction with the following description of the embodiments with reference to the accompanying drawings, where:

[0061] Figure 1 is a schematic structural diagram of a gradient color anti-counterfeiting mark printing device provided by an embodiment of the present application;

[0062] Figure 2 is a schematic structural diagram of a gradient color anti-counterfeiting mark printing device provided by another embodiment of the present application;

[0063] Figure 3 is a flowchart of an identification method of a gradient color anti-counterfeiting mark provided by an embodiment of the present application.

[0064] The reference numerals in the drawings are as follows:

[0065] Ink inlet inclined plate 100; Ink tank partition 200; Driving assembly 300. Detailed implementation manners

[0066] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and should not be construed as a limitation to the present application.

[0067] In the description of the present application, it should be understood that for the orientation description, such as up, down, front, back, left, right, etc., the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0068] In the description of the present application, if the first and second are described only for the purpose of distinguishing technical features, they should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence of the indicated technical features.

[0069] In the description of the present application, unless otherwise clearly defined, words such as setting, installing, and connecting should be understood in a broad sense. Those skilled in the art can reasonably determine the specific meanings of the above words in the present application in combination with the specific content of the technical solution.

[0070] At present, with the booming development of the commodity economy, anti-counterfeiting technology, as a key means to protect brands and maintain market order, is becoming increasingly important. At present, some anti-counterfeiting label printing technologies use the method of partitions to achieve the color gradient effect. This technology improves the anti-counterfeiting performance to a certain extent and increases the recognition of products with a unique gradient color design. However, from the perspective of anti-counterfeiting means, due to the fixed position of the partition, the gradient effect is relatively fixed, and the anti-counterfeiting gradient position lacks variation. Lawbreakers can easily imitate a similar anti-counterfeiting gradient effect through simple observation, measurement, and replication means.

[0071] On the other hand, in the identification of anti-counterfeiting labels, manual identification is easily affected by subjective factors. Different people have different perception and judgment criteria for colors and pattern details. For example, different visual sensitivities and levels of experience will lead to different judgment results for the same anti-counterfeiting label, and it is difficult to comprehensively and accurately observe and analyze the details in the anti-counterfeiting label.

[0072] Based on this, the present application provides a method for identifying a gradient color anti-counterfeiting label, an electronic device, and a storage medium.

[0073] In a first aspect, referring to Figure 1, this application provides a method for identifying a gradient anti-counterfeiting label, which may include but is not limited to the following steps:

[0074] Step S110: Sequentially obtain the first image information of the anti-counterfeiting labels on all products in the same batch.

[0075] Step S120: Identify the first image information and construct a gradient feature data set for the corresponding batch.

[0076] Step S130: Determine the predicted printing change rule of the products in the corresponding batch regarding the anti-counterfeiting label according to the gradient feature data set.

[0077] Step S140: Obtain the authenticity identification result according to the predicted printing change rule and the preset factory printing change rule.

[0078] The anti-counterfeiting label in step S110 is printed by a gradient anti-counterfeiting label printing device. Referring to Figure 3 , the gradient anti-counterfeiting label printing device includes an ink feeding structure and a rolling brush structure. The ink feeding structure includes an ink feeding inclined plate 100, an ink groove partition 200, a driving component 300, and at least two ink supply cartridges of different colors. The ink groove partition 200 is arranged on the ink feeding inclined plate 100 to divide the ink feeding inclined plate 100 into two ink feeding areas. The driving end of the driving component 300 is connected to the ink groove partition 200. The two ink supply cartridges are respectively located above the two ink feeding areas. The ink inlet end of the rolling brush structure is butted against the ink outlet end of the ink feeding inclined plate 100.

[0079] Based on the above-provided gradient anti-counterfeiting label printing device, the printing method of the anti-counterfeiting label may include but is not limited to the following steps:

[0080] Step S150: Obtain the preset factory printing change rule.

[0081] Step S160: Open the ink supply cartridge to make the ink flow to the corresponding ink feeding area, and control the driving component to drive the ink groove partition to move on the ink feeding inclined plate according to the factory printing change rule.

[0082] Step S170: Control the rolling brush structure to roll-coat the products in sequence so as to form an anti-counterfeiting label at the target position of each product.

[0083] In steps S150 to S170, when printing anti-counterfeiting marks on the product, first obtain the preset printing change rule for factory production. This printing change rule for factory production stipulates the moving mode of the ink tank partition 200 during the printing process. Open at least two ink supply cartridges of different colors, and let the ink flow onto the ink inlet inclined plate 100 into two ink inlet areas separated by the ink tank partition 200. At the same time, the driving component 300 drives the ink tank partition 200 to move on the ink inlet inclined plate 100 according to the preset printing change rule for factory production, so as to change the mixing ratio of the ink in the two ink inlet areas and achieve different color gradient effects. The ink inlet end of the roller brush structure is docked with the ink outlet end of the ink inlet inclined plate 100. After obtaining the mixed ink, the product is roller-coated in sequence to form an anti-counterfeiting mark with a specific gradient effect at the target position of each product. If one of the ink supply cartridges contains yellow ink and the other ink supply cartridge contains blue ink, the color printed at the position of the corresponding ink tank partition 200 is green, that is, the anti-counterfeiting mark is a pattern that fades from yellow to blue.

[0084] In addition, referring to Figure 2 , according to different anti-counterfeiting mark requirements, there can be multiple ink tank partitions 200 on the ink inlet inclined plate 100, and different colors of ink can be poured into each ink inlet area. The number of ink tank partitions 200 is not limited in this application.

[0085] In steps S110 to S140, during the anti-counterfeiting mark recognition process, first obtain the first image information of the anti-counterfeiting marks on all products in the same batch in sequence, and perform recognition processing on the obtained first image information, so as to organize it into a gradient feature data set for the corresponding batch. Subsequently, based on the constructed gradient feature data set, analyze the change trend of the gradient features of the anti-counterfeiting marks in the products of the same batch, so as to determine the predicted printing change rule of the products in the corresponding batch regarding the anti-counterfeiting marks. Compare the determined predicted printing change rule with the preset printing change rule for factory production. If the two are consistent or the difference is within an acceptable range, it is determined that the anti-counterfeiting mark of the product is genuine; otherwise, it is determined to be fake.

[0086] In the above steps, for the printing of the anti-counterfeiting marks of the products in this application, a movable ink tank partition is adopted, and the partition is driven to move according to the preset printing change rule for factory production, so that the gradient effects of the anti-counterfeiting marks of the products in the same batch have a certain variability. This dynamic change increases the complexity and non-replicability of the anti-counterfeiting mark and improves the anti-counterfeiting performance. In addition, for this dynamically changing anti-counterfeiting mark, based on the methods of image processing and data analysis, the features of the anti-counterfeiting mark can be extracted more accurately. By comparing the predicted printing change rule and the printing change rule for factory production, the accuracy of anti-counterfeiting mark recognition is improved, and the possibility of misjudgment is reduced.

[0087] It can be understood that in step S120, it may include but is not limited to the following steps:

[0088] Step S210: Grayscale the first image information to obtain grayscale image information.

[0089] Step S220: Denoise and enhance the grayscale image information to obtain target image information.

[0090] Step S230: Determine the gradient edge features based on the target image information.

[0091] Step S240: Determine the gradient region features corresponding to the anti-counterfeiting mark according to the gradient edge features.

[0092] Step S250: Generate a gradient feature dataset according to all the gradient region features of the same batch in the detection order of the products.

[0093] In step S210, the first image information is usually a color image. Grayscaling is to convert the color image into a grayscale image, retaining only the information of one channel, reducing the data dimension, and simplifying subsequent processing.

[0094] In step S220, the grayscale image information may contain noises such as salt-and-pepper noise and Gaussian noise. These noises will affect the extraction of subsequent edge and region features. Common denoising methods include median filtering, Gaussian filtering, etc. At the same time, in order to highlight the features in the image, it is necessary to enhance the denoised image. For example, the histogram equalization method is used. By adjusting the grayscale distribution of the image, the contrast of the image is enhanced, making the boundaries and features of the gradient region more obvious.

[0095] In steps S230 to S250, based on the target image information, the gradient edge features are determined. Subsequently, through the gradient edge features, the region enclosed by these edges is found, which is the gradient region of the anti-counterfeiting mark. The gradient region features of all products in the same batch are sorted according to the detection order of the products. The gradient region feature of each product is used as a record in the dataset, and the sorted data is stored in a suitable data structure such as an array, a list, or a database table to form a gradient feature dataset for the corresponding batch.

[0096] It can be understood that in step S230, it may include but is not limited to the following steps:

[0097] Step S310: Calculate the color change gradient corresponding to each pixel point according to the target image information.

[0098] Step S320: Screen the pixel points according to the color change gradient to determine the real edge points.

[0099] Step S330: Form several candidate edge features according to the continuous real edge points.

[0100] Step S340: Screen the candidate edge features according to a preset regional reference width and a length integrity threshold to determine the gradient edge features.

[0101] In steps S310 to S340, for each pixel point in the target image information, calculate the color change gradient between it and adjacent pixel points through a specific algorithm. The color change gradient can determine the severity of the color change at the pixel point. Subsequently, screen the pixel points according to the calculated color change gradient to determine the true edge points. From the determined true edge points, find continuous sequences of true edge points, and these continuous points form several candidate edge features. Finally, screen and determine the gradient edge features, and further screen the candidate edge features with the preset regional reference width and length integrity threshold. If the width of the candidate edge feature is within the range of the regional reference width and the length meets the length integrity threshold, then it is determined as the final gradient edge feature. Through the above steps, some incomplete or non-compliant edges caused by noise or other interferences can be removed to obtain more accurate anti-counterfeiting label gradient edge features.

[0102] It can be understood that in step S320, it may include but is not limited to the following steps:

[0103] Step S410: When the color change gradient of a pixel point is less than a preset first gradient threshold, mark the corresponding pixel point as a non-edge point.

[0104] Step S420: When the color change gradient of a pixel point is greater than or equal to the first gradient threshold and less than a preset second gradient threshold, mark the corresponding pixel point as a weak edge point.

[0105] Step S430: When the color change gradient of a pixel point is greater than or equal to the second gradient threshold, mark the corresponding pixel point as a strong edge point.

[0106] Step S440: Take the pixel points corresponding to the marked strong edge points as the true edge points.

[0107] Step S450: When there are no pixel points marked as strong edge points within a preset number of pixels around a pixel point marked as a weak edge point, mark this pixel point as a non-edge point.

[0108] Step S460: When there are pixel points marked as strong edge points within a preset number of pixels around a pixel point marked as a weak edge point, take this pixel point as a true edge point.

[0109] In steps S410 to S430, for each pixel point in the target image, it is classified and marked according to its color change gradient. If the color change gradient of a certain pixel point is less than a preset first gradient threshold, it indicates that the color change in the area where this pixel point is located is gentle and it is unlikely to be an edge, and it is marked as a non-edge point. When the color change gradient of the pixel point is greater than or equal to the first gradient threshold but less than a preset second gradient threshold, it indicates that the pixel point has a certain color change, but the degree of change is not enough to be determined as a strong edge, and it is marked as a weak edge point. If the color change gradient of the pixel point is greater than or equal to the second gradient threshold, it means that the color change at this pixel point is drastic and it is very likely to be a real edge, and it is marked as a strong edge point.

[0110] In steps S440 to S460, the pixel points marked as strong edge points are directly determined as real edge points. For the pixel points marked as weak edge points, check whether there are pixel points marked as strong edge points within a preset number of pixels around them. For example, check whether there are pixel points of strong edge points in the 8 neighborhoods of this pixel point, that is, the 8 adjacent pixel points of up, down, left, right, upper left, upper right, lower left, and lower right.

[0111] In an image, noise may cause some pixel points to have false color change gradients. By setting the first gradient threshold and marking the pixel points with a color change gradient less than this threshold as non-edge points, most noise points can be effectively filtered out, avoiding them being misidentified as edges and improving the accuracy of edge detection. Introducing the second gradient threshold to distinguish strong edge points and weak edge points and further judging the weak edge points can more accurately identify real edges. Strong edge points are usually the main part of the edge, while weak edge points may be some details or transition parts of the edge. By checking whether there are strong edge points around the weak edge points, the weak edge points that truly belong to the edge can be retained, while excluding those isolated and false weak edge points, making the edge detection result more complete and accurate. The above edge detection method based on double thresholds and neighborhood judgment can adapt to images of different qualities and complex image backgrounds. For images with uneven illumination, noise, or texture interference, this method can still more accurately detect edges, improving the robustness and stability of edge detection.

[0112] It can be understood that in step S340, it may include but is not limited to the following steps:

[0113] Step S510: Determine the regional reference width according to the width of the ink tank partition.

[0114] Step S520: Calculate the edge length of each candidate edge feature in the first direction.

[0115] Step S530: Delete the candidate edge features whose edge lengths are less than the length integrity threshold.

[0116] Step S540: Calculate the average distance between the remaining candidate edge features and other candidate edge features in the direction perpendicular to the first direction, and determine boundary candidate pairs based on the regional reference width.

[0117] Step S550: Take the two candidate edge features in the boundary candidate pair as the gradient edge features.

[0118] In steps S510 to S550, since the anti-counterfeiting label is printed by a gradient color anti-counterfeiting label printing device, a suitable regional reference width is determined according to the width of the ink tank partition, combined with the actual printing process and the characteristics of anti-counterfeiting label design. For each candidate edge feature, calculate the edge length of each candidate edge feature in the first direction, and preset a length integrity threshold. Delete the candidate edge features whose edge lengths are less than this threshold because these edges may be incomplete, caused by noise, or have no practical significance for determining the gradient area, which reduces the workload of subsequent processing and improves the quality of edge features at the same time. For the remaining candidate edge features, calculate the average distance between each candidate edge feature and other candidate edge features in the direction perpendicular to the first direction. Based on the previously determined regional reference width, screen out the candidate edge feature pairs whose average distances are close to this regional reference width, and take these pairs as boundary candidate pairs, so as to determine the two candidate edge features in the boundary candidate pair as the gradient edge features. By calculating the edge length and comparing it with the length integrity threshold, and determining the boundary candidate pairs based on the regional reference width, incomplete edge features are deleted, avoiding the interference of noise and irrelevant edges on subsequent analysis, and accurately finding the edge pairs that define the gradient area.

[0119] It can be understood that in step S550, it may include but is not limited to the following steps:

[0120] Step S610: When there are two or more boundary candidate pairs, calculate the color change standard value of each boundary candidate pair according to the color change gradient of all pixel points in the edge candidate pair.

[0121] Step S620: Determine the edge parallelism according to the two candidate edge features in the boundary candidate pair.

[0122] Step S630: Determine the scoring value of each boundary candidate pair according to the color change standard value and the edge parallelism.

[0123] Step S640: Take the two candidate edge features in the boundary candidate pair with the highest scoring value as the gradient edge features.

[0124] In steps S610 to S640, when there are two or more boundary candidate pairs, for each boundary candidate pair, obtain the color change gradients of all the pixel points therein, and then calculate the color change standard value for each boundary candidate pair according to these color change gradients. The color change standard value reflects the overall characteristics of the color changes of the pixel points included in the boundary candidate pair. For the two candidate edge features in each boundary candidate pair, by analyzing their directions and relative positional relationships, calculate an index representing their degree of parallelism, that is, the edge parallelism. Considering the color change standard value and the edge parallelism comprehensively, according to a certain weight assignment, combine and calculate these two indices to obtain the scoring value for each boundary candidate pair. The higher the scoring value, the more the boundary candidate pair meets the requirements of the gradient edge feature in terms of color change and edge parallelism. Select the boundary candidate pair with the highest scoring value, and determine the two candidate edge features in this boundary candidate pair as the final gradient edge features.

[0125] Determining the gradient edge feature by comprehensively considering the color change standard value and the edge parallelism can more comprehensively evaluate the characteristics of the boundary candidate pair. The color change standard value reflects the color change law of the edge region, while the edge parallelism considers the geometric characteristics of the edge. The combination of the two can more accurately screen out the edges that truly represent the gradient region of the anti-counterfeiting label, reduce the possibility of misjudgment and missed judgment, and improve the accuracy of recognition.

[0126] It can be understood that in step S130, it may include but is not limited to the following steps:

[0127] Step S710: Calculate the gradient center coordinates of each gradient region feature in the gradient feature dataset;

[0128] Step S720: Construct a coordinate system regarding the product and the position of the corresponding gradient region feature;

[0129] Step S730: Generate a predicted change curve graph in the coordinate system according to the gradient center coordinates corresponding to each product and the detection order of the products, and use the predicted change curve graph as the predicted printing change law of the products in the corresponding batch regarding the anti-counterfeiting label.

[0130] In steps S710 to S730, for each gradient region feature in the gradient feature dataset, the gradient center coordinates are calculated. The gradient center coordinates can be obtained based on the center points of two gradient edges. A coordinate system is constructed based on the product and the position of the corresponding gradient region feature. According to the gradient center coordinates corresponding to each product and the detection order of the products, the gradient center coordinates are marked in the constructed coordinate system. As the number of detected products increases, these marked points will form a certain distribution trend. By connecting these points, a predicted change curve graph can be generated. This curve graph intuitively shows the position change law of the gradient region feature of the anti-counterfeiting label with the change of the product detection order in the corresponding batch of products. By generating the predicted change curve graph, the change situation of the gradient region feature of the anti-counterfeiting label in the batch of products can be shown in an intuitive graphical way.

[0131] It can be understood that in step S140, it may include but is not limited to the following steps:

[0132] Step S810: Calculate the change similarity between the predicted change curve graph corresponding to the predicted printing change law and the factory change curve graph of the factory printing change law.

[0133] Step S820: When the change similarity is greater than or equal to the preset similarity threshold, determine that the authenticity recognition result of the products in the same batch is true.

[0134] Step S830: When the change similarity is less than the similarity threshold, determine that the authenticity recognition result of the products in the same batch is false.

[0135] In steps S810 to S830, obtain the predicted change curve graph corresponding to the predicted printing change rule obtained according to the previous steps, and the factory change curve graph corresponding to the preset factory printing change rule. Compare multiple aspects such as the shape of the curves, slopes, and positions of key feature points, and calculate the change similarity. If the change similarity is greater than or equal to the similarity threshold, it indicates that the predicted printing change rule is relatively similar to the factory printing change rule. Thus, the authenticity identification result of the products of the same batch can be determined to be true, that is, it is considered that the anti-counterfeiting label printing of this batch of products meets the expectations, and the authenticity identification result of the products of the same batch is determined to be true. If the change similarity is less than the similarity threshold, it indicates that there is a large difference between the predicted printing change rule and the factory printing change rule. Then, the authenticity identification result of the products of the same batch is determined to be false, that is, it is suspected that there may be problems with this batch of products, and they may be counterfeit products. Judging the authenticity of products by quantitatively comparing the similarity between the predicted change curve graph and the factory change curve graph provides a relatively objective, accurate, and efficient method. Compared with manual judgment based on experience, this identification method based on data and algorithms can reduce the influence of subjective factors, improve the accuracy and reliability of authenticity identification, and quickly screen the authenticity of a large number of products.

[0136] In a second aspect, the present application also provides an electronic device, including: at least one memory; at least one processor; at least one program; the program is stored in the memory, and the processor executes at least one program to implement the identification method of the gradient anti-counterfeiting label according to any one of the embodiments of the first aspect.

[0137] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and signals, such as the program instructions / signals corresponding to the processing module in the embodiments of the present application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and signals stored in the memory, that is, implements the identification method of the gradient anti-counterfeiting label in the above method embodiments.

[0138] The memory can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store relevant data of the above identification method of the gradient anti-counterfeiting label, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory can optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processing module through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise internal network, a local area network, a mobile communication network, and combinations thereof.

[0139] One or more signals are stored in a memory and, when executed by one or more processors, perform the method for identifying a gradient color anti-counterfeiting mark in any of the above method embodiments.

[0140] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which when executed by one or more processors, enables the one or more processors to perform the method for identifying a gradient color anti-counterfeiting mark in the above method embodiments.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] Through the description of the above embodiments, those of ordinary skill in the art can understand that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable signals, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium generally includes computer-readable signals, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0143] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Here, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item) of the following" or a similar expression means any combination of these items, including any combination of a single item or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0144] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0145] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0147] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0148] The embodiments of the present application have been described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the above embodiments. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can also be made without departing from the purpose of the present application.

Claims

1. A method for identifying a gradient color anti-counterfeiting mark, characterized in that, Including: Successively obtain the first image information of the anti-counterfeiting marks on all products in the same batch; Identify the first image information and construct a gradient feature dataset for the corresponding batch; Determine the predicted printing change rule of the products in the corresponding batch regarding the anti-counterfeiting mark according to the gradient feature dataset; Obtain the authenticity identification result according to the predicted printing change rule and the preset factory printing change rule; Among them, the anti-counterfeiting mark is printed by a gradient color anti-counterfeiting mark printing device. The gradient color anti-counterfeiting mark printing device includes an ink feeding structure and a rolling brush structure. The ink feeding structure includes an ink feeding inclined plate, an ink tank partition plate, a driving component, and at least two ink supply cartridges of different colors. The ink tank partition plate is arranged on the ink feeding inclined plate to divide the ink feeding inclined plate into two ink feeding areas. The driving end of the driving component is connected to the ink tank partition plate. The two ink supply cartridges are respectively located above the two ink feeding areas. The ink inlet end of the rolling brush structure is butted against the ink outlet end of the ink feeding inclined plate; The anti-counterfeiting mark is printed through the following steps: Obtain the preset factory printing change rule; Open the ink supply cartridge to make the ink flow to the corresponding ink feeding area, and control the driving component to drive the ink tank partition plate to move on the ink feeding inclined plate according to the factory printing change rule; Control the rolling brush structure to roll-coat the products in sequence so as to form the anti-counterfeiting mark at the target position of each product.

2. The identification method of the gradient color anti-counterfeiting label according to claim 1, wherein, The identifying the first image information and constructing a gradient feature dataset for the corresponding batch includes: Perform grayscale processing on the first image information to obtain grayscale image information; Perform noise reduction and enhancement processing on the grayscale image information to obtain target image information; Determine the gradient edge feature according to the target image information; Determine the gradient area feature corresponding to the anti-counterfeiting mark according to the gradient edge feature; Generate the gradient feature dataset according to all the gradient area features of the same batch in the detection order of the products.

3. The recognition method of the gradient color anti-counterfeiting label according to claim 2, characterized in that, The determining the gradient edge feature according to the target image information includes: Calculate the color change gradient corresponding to each pixel point according to the target image information; Perform screening processing on the pixel points according to the color change gradient to determine the real edge points; Form a number of candidate edge features according to the continuous real edge points; Perform screening on the candidate edge features according to the preset regional reference width and length integrity threshold to determine the gradient edge feature.

4. The recognition method of the gradient color anti-counterfeiting label according to claim 3, wherein The performing screening processing on the pixel points according to the color change gradient to determine the real edge points includes: When the color change gradient of the pixel point is less than the preset first gradient threshold, mark the corresponding pixel point as a non-edge point; When the color change gradient of the pixel point is greater than or equal to the first gradient threshold and less than the preset second gradient threshold, mark the corresponding pixel point as a weak edge point; When the color change gradient of the pixel point is greater than or equal to the second gradient threshold, mark the corresponding pixel point as a strong edge point; Take the pixel points marked as corresponding to the strong edge points as real edge points; When there are no pixel points marked as strong edge points within a preset number of pixels around the pixel points marked as weak edge points, mark the pixel points as non-edge points; When there are pixel points marked as strong edge points within a preset number of pixels around the pixel points marked as weak edge points, take the pixel points as real edge points.

5. The identification method of the gradient color anti-counterfeiting label according to claim 3, wherein The screening of the candidate edge features according to the preset regional reference width and length integrity threshold to determine the gradient edge features includes: Determine the regional reference width according to the width of the ink groove partition; Calculate the edge length of each candidate edge feature in the first direction; Delete the candidate edge features with the edge length less than the length integrity threshold; Calculate the average distance between the remaining candidate edge features and other candidate edge features in the direction perpendicular to the first direction, and determine the boundary candidate pairs based on the regional reference width; Take the two candidate edge features in the boundary candidate pairs as the gradient edge features.

6. The recognition method of the gradient anti-counterfeiting mark according to claim 5, characterized in that The taking the two candidate edge features in the boundary candidate pairs as the gradient edge features includes: When there are two or more boundary candidate pairs, calculate the color change standard value of each boundary candidate pair according to the color change gradient of all pixel points in the edge candidate pair; Determine the edge parallelism according to the two candidate edge features in the boundary candidate pair; Determine the scoring value of each boundary candidate pair according to the color change standard value and the edge parallelism; Take the two candidate edge features in the boundary candidate pair with the highest scoring value as the gradient edge features.

7. The recognition method of the gradient color anti-counterfeiting mark according to claim 2, characterized in that, The determining the predicted printing change rule of the product with respect to the anti-counterfeiting mark in the corresponding batch according to the gradient feature dataset includes: Calculate the gradient center coordinates of each gradient region feature in the gradient feature dataset; Construct a coordinate system for the product and the position of the corresponding gradient region feature; Generate a predicted change curve graph in the coordinate system according to the gradient center coordinates corresponding to each product and the detection order of the product, and take the predicted change curve graph as the predicted printing change rule of the product with respect to the anti-counterfeiting mark in the corresponding batch.

8. The identification method of the gradient color anti-counterfeiting label according to claim 7, characterized in that, The obtaining the authenticity identification result according to the predicted printing change rule and the preset factory printing change rule includes: Calculate the change similarity between the predicted change curve graph corresponding to the predicted printing change rule and the factory change curve graph of the factory printing change rule; When the change similarity is greater than or equal to the preset similarity threshold, determine that the authenticity identification result of the products in the same batch is true; When the change similarity is less than the similarity threshold, determine that the authenticity identification result of the products in the same batch is false.

9. An electronic device, characterized in that, Including: At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes at least one program to implement the identification method of the gradient color anti-counterfeiting mark as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable signals for executing the method for identifying a gradient anti-counterfeiting mark according to any one of claims 1 to 8.

Images