Method and device for identifying anti-counterfeit label, computing equipment and program product

Abstract

The embodiment of the invention relates to a method and device for identifying an anti-counterfeit label, computing equipment and a computer program product. According to the method, under the condition of lighting, a lighting image of the anti-counterfeit label is obtained, and the lighting image comprises a laser assembly and a coding pattern of the anti-counterfeit label. Then, according to the coding pattern in the lighting image, a base map of the corresponding anti-counterfeit label is obtained, and the base map is also collected under the lighting condition; furthermore, according to a matching result of the color lines reflected by the laser assembly in the lighting image and the color lines reflected by the laser assembly in the base map, a message that the anti-counterfeit label is true is generated.

Description

Technical Field

[0001] The embodiments of the present specification generally relate to the field of computers, and more specifically to a method, apparatus, computing device, and computer program product for identifying anti-counterfeiting labels. Background Art

[0002] The label of an item is a printed material used to mark the classification, content and other information of the item. It is generally made of paper or other materials and can be pasted or hung on the surface of an object. Labels include coded labels, such as barcode labels, QR code labels, etc., which have coded patterns on their surfaces. In many traceability scenarios, coded patterns are pasted or printed on the surface of items for anti-counterfeiting and traceability.

[0003] Since the coding pattern in the coding label is easy to forge, anti-counterfeiting information can be added to the coding label to obtain an anti-counterfeiting coding label. In this way, during the circulation of items, users can use the anti-counterfeiting coding label to check the authenticity of the items and distinguish the quality of the items. Therefore, accurate identification of anti-counterfeiting information is crucial for the use of coding labels. Summary of the invention

[0004] The embodiments of this specification provide a method, an apparatus, a computing device, and a computer program product for identifying an anti-counterfeiting label.

[0005] In the first aspect of the present specification, a method for identifying an anti-counterfeiting label is provided, comprising: obtaining a first image of the anti-counterfeiting label captured under illumination, the anti-counterfeiting label including a laser component and a coding pattern; based on the coding pattern in the first image, obtaining a base image of the anti-counterfeiting label captured under illumination; and in response to a match between colored lines reflected by the laser component in the first image and colored lines reflected by the laser component in the base image, generating a message that the anti-counterfeiting label is authentic.

[0006] In the second aspect of the present specification, a device for identifying an anti-counterfeiting label is provided, comprising: a first image acquisition module, configured to acquire a first image of the anti-counterfeiting label captured under lighting, the anti-counterfeiting label including a laser component and a coding pattern; a base map acquisition module, configured to acquire a base map of the anti-counterfeiting label captured under lighting based on the coding pattern in the first image; and a message generation module, configured to generate a message indicating that the anti-counterfeiting label is authentic in response to a match between colored lines reflected by the laser component in the first image and colored lines reflected by the laser component in the base map.

[0007] In a third aspect of the present specification, a computing device is provided. The computing device includes a memory. The computing device also includes a memory coupled to a processor, the memory having instructions stored therein, and when the instructions are executed by the processor, the computing device executes the method according to the first aspect of the present specification.

[0008] In a fourth aspect of the present specification, a computer program product is provided, wherein the computer program product comprises a computer program, and the computer program is executed by a processor to implement the method according to the first aspect of the present specification.

[0009] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present specification, nor are they intended to limit the scope of the present invention. Other features of the present specification will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present specification will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram illustrating an example environment in which some embodiments of the present specification may be implemented;

[0012] Figure 2 A flowchart showing a method for identifying an anti-counterfeit label according to some embodiments of the present specification;

[0013] Figure 3A A front view of a laser assembly of some embodiments of the present specification is shown;

[0014] Figure 3B A side view of a laser assembly of some embodiments of the present specification is shown;

[0015] Figure 4 A front view of a laser assembly including a laser pattern according to some embodiments of the present specification is shown;

[0016] Figure 5A A schematic diagram showing an anti-counterfeiting label including multiple laser components according to some embodiments of the present specification;

[0017] Figure 5B A schematic diagram showing another anti-counterfeiting label including a plurality of laser components according to some embodiments of the present specification;

[0018] Figure 6 A schematic diagram showing an anti-counterfeiting label including multiple laser components and a coding pattern according to some embodiments of the present specification;

[0019] Figure 7 A schematic diagram showing a process of identifying anti-counterfeiting labels according to some embodiments of this specification;

[0020] Figure 8A schematic diagram showing another process of identifying an anti-counterfeit label according to some embodiments of the present specification; and

[0021] Fig. 9 A schematic block diagram of a computing device is shown that illustrates some embodiments of the present description.

[0022] Throughout the drawings, the same or similar reference numbers denote the same or similar elements. DETAILED DESCRIPTION

[0023] The embodiments of the present specification will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present specification are shown in the accompanying drawings, it should be understood that the present specification can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present specification. It should be understood that the drawings and embodiments of the present specification are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0024] In the description of the embodiments of this specification, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0025] As mentioned above, accurate identification of anti-counterfeiting labels is crucial for the use of coded labels. In the process of goods circulation, merchants, platforms and other institutions will paste or hang anti-counterfeiting labels on the surface or outer packaging of goods to prevent counterfeiting of goods, prevent counterfeiting of goods, scan codes to obtain virtual resources and other scenarios. In these usage scenarios, counterfeiters can often attack by means of batch generation of counterfeit, same-size copy counterfeit, enlarged size copy attack, and screen scanning, as follows:

[0026] Batch generation and counterfeiting: The counterfeiter first infers other code values ​​in batches based on the code values ​​of the existing QR code labels of the items, or the counterfeiter can obtain the code values ​​that have been leaked in batches. Then, the counterfeiter infers the anti-counterfeiting information and process based on the anti-counterfeiting pattern on the QR code label, and directly generates batches of images of QR code labels containing anti-counterfeiting information. Finally, the counterfeiter reprints the counterfeit QR code label or directly scans the image of the QR code label across the screen. In general, QR code labels without anti-counterfeiting patterns are most likely to be batch generated and counterfeited. In addition, for anti-counterfeiting QR code labels whose anti-counterfeiting patterns are anchored to batch code values, it is relatively easy to be batch generated and counterfeited because the anti-counterfeiting patterns are not unique. For anti-counterfeiting QR code labels whose anti-counterfeiting patterns are anchored to a code value, their anti-counterfeiting patterns are unique, so they are difficult to be batch generated and counterfeited. It should be understood that the more complex the anti-counterfeiting process, the greater the difficulty of batch generation and counterfeiting.

[0027] Copying and counterfeiting with the same size: Counterfeiters use a scanner to scan the QR code, obtain the QR code pattern and the anti-counterfeiting pattern in the QR code area, such as the background pattern, random pattern, etc., and use a printing machine to reprint the QR code label of the same size for counterfeiting. The more complex the anti-counterfeiting pattern and process, the higher the accuracy requirements of the scanner and printing machine, and the more difficult it is to counterfeit.

[0028] Enlarged size copy forgery: Counterfeiters use scanners to scan the QR code, obtain the QR code pattern and the anti-counterfeiting pattern in the QR code area, such as shading, random patterns, etc., and use a printing machine to enlarge the size and reprint or copy the QR code. Since anti-counterfeiting patterns such as shading and random patterns do not lose too much texture information at a large size, the attack can also be achieved by directly scanning the enlarged version of the QR code label. Scanning the code across the screen: Counterfeiters take photos of the QR code label and display them on the screen of a mobile phone or personal computer, and then use the mobile phone to scan the photo on the screen to achieve the attack.

[0029] In the related technologies, the anti-counterfeiting of QR code labels is generally carried out through scratch-off silver technology, anti-counterfeiting shading technology, holographic anti-counterfeiting technology, invisible digital technology, quantum cloud code technology, etc. Among them, the scratch-off silver anti-counterfeiting label is also called the scratch-off digital anti-counterfeiting label. This technology is realized by superimposing numbers and coatings (such as silver ink that can be scratched) on the basis of the QR code. The user can scan the QR code to open the verification website, then scratch off the coating to obtain the number and enter the verification website for verification. The anti-counterfeiting shading technology is to regularly connect various different curves or straight lines under the ordinary QR code layer to form an anti-counterfeiting shading. The stripes of the anti-counterfeiting shading are thin and the color is not obvious, so it is not easy to be copied or forged.

[0030] Holographic anti-counterfeiting technology is based on laser anti-counterfeiting labels, that is, anti-counterfeiting labels made using color hologram platemaking technology and mold embossing replication technology. The anti-counterfeiting label can be observed with the naked eye, or the internal engraving features can be observed through a microscope to identify the authenticity. The top layer of the QR code label used in invisible digital technology is printed with a varnish layer or a solid color layer. When the varnish layer is photochemically dried, it will change the optical properties of the varnish layer, and produce random defects of 10-500 microns on its surface to form micropores. When verifying the authenticity, the optical characteristics of the random defects can be detected by flashing. Quantum cloud code technology generates random black code points outside the black and white code element areas on the QR code label according to certain rules. When verifying the authenticity, the authenticity can be identified by detecting the rules of the code points.

[0031] However, in the related art, for the scratch-off silver technology, counterfeiters can get a real QR code label by scratching off the scratch-off silver layer to get the number, and then reprint the QR code. Due to the low cost of reprinting, the threshold for counterfeiting of this technology is relatively low. In addition, the counterfeiting verification method can only identify the authenticity by manually scratching off the scratch-off silver layer, and the machine counterfeiting verification method can only scan the code to identify the code value, which cannot achieve the purpose of identifying the authenticity. For the anti-counterfeiting shading technology, the process requirements for printing the anti-counterfeiting shading are relatively high. General printing factories cannot print clear and complete anti-counterfeiting shading, so the production difficulty of its anti-counterfeiting shading is relatively high. However, when users verify counterfeiting, they generally use mobile phone cameras to shoot, so it is not easy to clearly shoot the small and dim shading under the QR code layer, resulting in the QR code image taken by the user and the standard QR code image in the server. It is not easy to match, resulting in the failure of the verification. The verification method can be to observe the shading by human eyes to identify the authenticity, or it can be verified by scanning the code by machine, but the recognition is difficult.

[0032] For holographic anti-counterfeiting technology, invisible digital technology, and quantum cloud code technology, the production cost of the QR code labels is relatively high, requiring special equipment and technology, which makes the price of the QR code labels relatively expensive. Moreover, in general, the patterns on the QR code labels are the same. Once they are all cracked, the QR codes of all batches of code segments will be easily forged. In addition, the counterfeiting stage is achieved through human eye observation, and the recognition accuracy is low. Based on this, the anti-counterfeiting label recognition technology in the related art has the problems of low counterfeiting threshold, high production and recognition costs, and low recognition accuracy.

[0033] To this end, a method for identifying anti-counterfeiting labels is proposed in an embodiment of the present specification. Under lighting conditions, a lighting image of the anti-counterfeiting label is obtained, wherein the lighting image contains a laser component and a coding pattern of the anti-counterfeiting label. Then, based on the coding pattern in the lighting image, a base map of the corresponding anti-counterfeiting label is obtained, wherein the base map is also collected under lighting conditions. Further, based on the matching results of the colored lines reflected by the laser component in the lighting image and the colored lines reflected by the laser component in the base map, a message is generated that the anti-counterfeiting label is authentic. In this way, it is possible to identify whether the anti-counterfeiting label is counterfeit through the lighting image and the colored lines of the laser component in the base map, which has a low recognition cost and a high recognition accuracy compared to the solutions in the related art. Moreover, the laser component can increase the threshold for counterfeiting of anti-counterfeiting labels and reduce production costs.

[0034] Figure 1 A schematic diagram of an example environment 100 is shown in which some embodiments of the present specification may be implemented. Figure 1 , the example environment 100 includes a terminal 102, a server 104, and an anti-counterfeiting label 106. The terminal 102 includes but is not limited to client devices such as mobile phones, tablet computers, and personal computers, and the server 104 includes but is not limited to a computing system, a single server, a distributed server, or a cloud-based server. The anti-counterfeiting label 106 includes a laser component 108 and a coding pattern 110, wherein the laser component 108 may include multiple laser unit gratings, and the coding pattern 110 includes but is not limited to a barcode pattern, a two-dimensional code pattern, and the like.

[0035] In some embodiments, in the case of lighting, the terminal 102 obtains a lighting image (which may be referred to as a first image) of the anti-counterfeiting label 106. Then, the terminal 102 sends the lighting image to the server 104, which obtains the lighting image and identifies the coding pattern 110 in the lighting image, thereby obtaining the base image of the anti-counterfeiting label 106. Further, the server 104 compares the colored lines reflected by the laser component 108 in the lighting image with the colored lines reflected by the laser component 108 in the base image to determine whether the colored lines of the two match. If they match, the server 104 generates a message that the anti-counterfeiting label 106 is true and sends it to the terminal 102. If they do not match, the server 104 generates a message that the anti-counterfeiting label 106 is false and sends it to the terminal 102. After receiving the message, the terminal 102 displays the message on the screen.

[0036] Alternatively or additionally, in the case of lighting, the terminal 102 obtains the lighting image of the anti-counterfeiting label 106. Then, the terminal 102 sends the lighting image to the server 104, and the server 104 obtains the lighting image and identifies the coding pattern 110 in the lighting image, thereby obtaining the base map of the anti-counterfeiting label 106. Further, the server 104 sends the base map to the terminal 102, and the terminal 102 compares the colored lines reflected by the laser component 108 in the lighting image with the colored lines reflected by the laser component 108 in the base map to determine whether the colored lines of the two match. If they match, the terminal 102 generates a message that the anti-counterfeiting label 106 is true and displays it on the screen. If they do not match, the server 104 generates a message that the anti-counterfeiting label 106 is false and displays it on the screen.

[0037] In this way, the anti-counterfeiting label 106 can be identified as forged by the colored lines of the laser component 110 in the lighting image and the base image, thereby reducing the identification cost and improving the accuracy of identification. In addition, the laser component 108 can increase the forgery threshold of the anti-counterfeiting label 106 and reduce the production cost.

[0038] The following will combine Figures 2 to 9 The process according to the embodiment of this specification is described in detail. For ease of understanding, the specific data mentioned in the following description are exemplary and are not intended to limit the scope of protection of this specification. It should be understood that the embodiments described below may also include additional actions not shown and / or may omit the actions shown, and the scope of this specification is not limited in this respect.

[0039] Figure 2 A flowchart of a method 200 for identifying an anti-counterfeiting label according to some embodiments of the present specification is shown. Figure 1 In the example environment 100 shown in FIG. 1 , the method 200 may be executed by the server 104. It should be understood that although the following content is described with the server 104 as the execution subject, the method 200 may also be executed by other devices, such as the terminal 102. The method 200 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present specification is not limited in this respect.

[0040] At 202, a first image of the anti-counterfeiting label captured under lighting is obtained, and the anti-counterfeiting label includes a laser component and a coding pattern. In some embodiments, under lighting, the server 104 can obtain a lighting image (which can be called a first image) from the terminal 102. The lighting image can be obtained by the terminal 102 shooting the anti-counterfeiting label 106 under lighting, and the anti-counterfeiting label 106 includes a laser component 108 and a coding pattern 110.

[0041] At 204, based on the coding pattern in the first image, a base image of the anti-counterfeiting label collected under lighting is obtained. In some embodiments, after obtaining the lighting image, the server 104 identifies the coding pattern 110 in the lighting image, thereby obtaining the base image of the anti-counterfeiting label 106 according to the coding pattern 110. The base image may be an image of the anti-counterfeiting label 106 taken after lighting during the production process.

[0042] At 206, if the colored lines reflected by the laser component in the first image match the colored lines reflected by the laser component in the base image, a message is generated that the anti-counterfeiting label is authentic. In some embodiments, the server 104 compares the colored lines reflected by the laser component 108 in the illuminated image with the colored lines reflected by the laser component 108 in the base image to determine whether the colored lines of the two match. If they match, the server 104 generates a message that the anti-counterfeiting label 106 is authentic.

[0043] In this way, it is possible to identify whether the anti-counterfeiting label is forged by the colored lines of the laser component in the illuminated image and the base image, which has a low identification cost and a high identification accuracy compared to the solutions in the related art. In addition, the laser component can increase the forgery threshold of the anti-counterfeiting label and reduce the production cost.

[0044] Figure 3A-3B The front view 300A and the top view 300B of the laser assembly 108 of some embodiments of the present specification are respectively shown. Figure 3A The laser assembly 108 includes a plurality of circular laser unit gratings with the same center, such as the outermost laser unit grating 302, and the plurality of laser unit gratings form a stepped grating structure. The grating refers to an optical device composed of a large number of parallel slits of equal width and spacing, which is generally made by engraving a large number of parallel grooves on a glass sheet. The grooves are opaque parts, and the smooth part between the two grooves can transmit light, which is equivalent to a slit. The stepped grating structure is a stepped reflective surface engraved on the substrate to form a stepped structure.

[0045] refer to Figure 3B , wherein the laser unit grating, for example, the laser unit grating 302, can set three parameters, including grating depth h, grating constant d, and blaze angle α. By modulating the above three parameters, the color of the color line reflected by the laser component 108 can be adjusted. Among them, the direction of the color line reflected by the laser component 108 can be adjusted by the blaze angle α. In some embodiments, by modulating the above three parameters of each laser unit grating, the concentric step grating structure can be transformed into a Fresnel lens.

[0046] Figure 4Multiple front views 400 of laser components including laser patterns in some embodiments of the present specification are shown. In some embodiments, the laser pattern can be integrated into the stepped grating structure of the laser component, wherein the laser pattern includes but is not limited to pattern information such as numbers and letters, and the integration method includes but is not limited to the integration methods such as covering, hollowing out, and internal inclusion. Figure 4 , for the laser component 108 and the laser pattern 404, they can be combined based on the covering method to form the laser component 406. For the laser component 108 and the laser pattern 408, they can be combined based on the hollowing method to form the laser component 410. For the laser component 108 and the laser pattern 412, they can be combined based on the internal fusion method to form the laser component 414.

[0047] Figure 5A A schematic diagram of an anti-counterfeiting label 500 including multiple laser components of some embodiments of the present specification is shown. Among them, the anti-counterfeiting label 500 includes multiple laser components, such as laser component 502, and each laser component can be set based on the above-mentioned step grating structure, so that the illuminated image taken under the illuminated condition can display the color line corresponding to each laser component. By adjusting the blaze angle α of the laser unit grating in the laser component, the direction of the color line reflected by the laser component can be set. In addition, the laser component can also include a laser pattern, such as laser pattern 504 (number 1). In some embodiments, the direction of the color line of the laser component can be randomly set, the laser pattern of the laser component can also be randomly set, and the position of each laser component can also be randomly set. In this way, it can be ensured that the final anti-counterfeiting label 500 has a high degree of randomness.

[0048] In some embodiments, the direction of the colored line reflected by the laser assembly refers to the light passing through the center of the circle, including white light, red light, green light, blue light, etc. Among them, white light is the light reflected after lighting, which can be called the 0th order main maximum stripe, and red light, green light, blue light, etc. are diffracted 1st or 2nd order stripes. Figure 5B A schematic diagram of another anti-counterfeiting label including multiple laser components in some embodiments of the present specification is shown. In some embodiments, Figure 5A Based on the anti-counterfeiting label 500 shown, the center of the laser component can be set as the vertex or center of the hexagon, so that the laser components can be evenly distributed based on the hexagon. Among them, the light direction of each laser component on the vertex or center of the hexagon is random. In this way, it can be ensured that the numbers in the laser components can be evenly distributed.

[0049] Figure 6 FIG. 6 is a schematic diagram of an anti-counterfeiting label 600 including multiple laser components and a coding pattern according to some embodiments of the present specification. Figure 6The anti-counterfeiting label 600 may include a laser component area 602 and a coding pattern area 604, wherein the laser component area 602 may be based on Figure 5A or Figure 5B In some embodiments, the position and overlapping manner of the laser component area 602 and the coding pattern area 604 can be randomly set, thereby further ensuring the randomness of the anti-counterfeiting label 600.

[0050] In some embodiments, a laser material for cold stamping is made by using a embossing technique to print a laser format, and a laser pattern is cold stamped on the substrate in sequence to print a QR code. Since cold stamping the laser pattern and printing the QR code are two independent processes, the QR code and laser pattern information will not be aligned. Even if the same QR code is printed, the laser pattern information will be different. After the anti-counterfeiting label is manufactured, the base image of the finished QR code label can be photographed by the camera of the printing production line under lighting conditions and saved to a non-transient storage medium for subsequent identification of the anti-counterfeiting label.

[0051] Figure 7 A schematic diagram of a process 700 for identifying an anti-counterfeiting label in some embodiments of the present specification is shown. Figure 1 In the example environment 100 shown in FIG. 1 , the process 700 may be executed by the server 104. It should be understood that although the following content is described with the server 104 as the execution subject, the process 700 may also be executed by other devices, such as the terminal 102. The process 700 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present specification is not limited in this respect.

[0052] In some embodiments, the server 104 obtains a lighting image 702 (which may be referred to as a first image) from the terminal 102. The lighting image 102 may be taken by the terminal 102 under lighting conditions, for example, by a user's mobile phone with the flash turned on. Then, the server 104 decodes the corresponding code value 704 based on the coding pattern in the lighting image 702. The code value is a string parsed from the coding pattern, including but not limited to English, numbers, Chinese, symbols and other characters. Then, the server 104 retrieves the base map 706 corresponding to the code value 704 in the database based on the code value 704. After the production of the anti-counterfeiting label is completed, the base map 706 is taken by the camera of the production line under lighting conditions, and the base map 706 and the corresponding code value are associated and saved in the database. In this way, the search efficiency of the base map 706 can be improved based on the code value 704.

[0053] After acquiring the base image 706, the server 104 determines whether the colored lines reflected by the laser components in the illuminated image 702 and the base image 706 match, thereby obtaining a result of light matching 708. Then, if the result of light matching 708 is yes, the server 104 generates a recognition success message 710 and sends it to the terminal 102 to inform the user that the anti-counterfeiting label is authentic. If the result of light matching 708 is no, the server 104 generates a recognition failure message 712 and sends it to the terminal 102 to inform the user that the anti-counterfeiting label is fake.

[0054] In some embodiments, in the process of determining the result of light matching 708, the server 104 may first identify the illuminated image 702 and the base map 706 through a neural network model (which may be referred to as a first neural network model), thereby obtaining the area of ​​the coded pattern in the illuminated image 702 and the area of ​​the coded pattern in the base map 706. Then, the server 104 may segment the surrounding area of ​​the coded pattern from the illuminated image 702 as the area of ​​the laser component, and segment the surrounding area of ​​the coded pattern from the base map 706 as the area of ​​the laser component, and align the two segmented areas of the laser component. Further, the server 104 may identify the aligned area of ​​the laser component through another neural network model (which may be referred to as a second neural network model), thereby obtaining the result of light matching 708. In this way, the server 104 can first align the area of ​​the laser component through the neural network model, and then perform light recognition matching, thereby improving the accuracy of the light matching result, and then improving the accuracy of anti-counterfeiting recognition.

[0055] In some embodiments, the server 104 may first determine whether the laser pattern (e.g., numbers, letters, etc.) in the illuminated image 702 and the base map 706 matches, thereby obtaining a recognition result of the laser pattern (which may be referred to as a first recognition result). Then, the server 104 may determine whether the colored lines reflected by the laser components in the illuminated image 702 and the base map 706 match, thereby obtaining a recognition result of the colored lines (which may be referred to as a second recognition result). If both of the above recognition results are matched, a result of yes for light match 708 may be obtained. If at least one of the above two recognition results does not match, a result of no for light match 708 may be obtained. In this way, the laser pattern and light of the laser component in the anti-counterfeiting label can be combined to improve the recognition accuracy of the matching of the illuminated image 702 and the base map 706, thereby improving the accuracy of anti-counterfeiting label recognition.

[0056] For the recognition result of the laser pattern, in some embodiments, the server 104 may first determine the position of the laser pattern in the lighted image 702 and the position of the laser pattern in the base map 706. Then, the server 104 may determine whether the positions of the laser patterns in the lighted image 702 and the base map 706 match, thereby obtaining the recognition result of the laser pattern. Alternatively or additionally, the server 104 may also determine the recognition result of the laser pattern in combination with information such as the direction and shape of the laser pattern in the lighted image 702 and the base map 706.

[0057] For the recognition result of the colored line, in some embodiments, the server 104 may first determine the position of the colored line in the lighted image 702 and the position of the colored line in the base map 706. Then, the server 104 may determine whether the positions of the colored lines in the lighted image 702 and the base map 706 match, thereby obtaining the recognition result of the colored line. Alternatively or additionally, the server 104 may first determine the direction of the colored line in the lighted image 702 and the direction of the colored line in the base map 706. Then, the server 104 may determine whether the directions of the colored lines in the lighted image 702 and the base map 706 match, thereby obtaining the recognition result of the colored line. It should be understood that the server 104 may also combine the positions and directions of the colored lines in the lighted image 702 and the base map 706 at the same time to obtain the recognition result of the colored line.

[0058] Figure 8 A schematic diagram of another process 800 for identifying anti-counterfeiting labels in some embodiments of the present specification is shown. Figure 1 In the example environment 100 shown in FIG. 8 , the process 800 may be executed by the server 104. It should be understood that although the following content is described with the server 104 as the execution subject, the process 800 may also be executed by other devices, such as the terminal 102. The process 800 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present invention is not limited in this respect.

[0059] In some embodiments, the server 104 obtains an unlit image 802 (which may be referred to as a second image) and a lit image 804 (which may be referred to as a first image) from the terminal 102. The unlit image 802 may be obtained by the terminal 102 without turning on the flash, and the lit image 804 may be obtained by the terminal 102 with the flash turned on. Then, the server 104 decodes the corresponding code value 806 based on the coding pattern in the unlit image 802 or the lit image 804. Further, the server 104 retrieves the base map 808 corresponding to the code value 806 in the database based on the code value 806. After the production of the anti-counterfeiting label is completed, the base map 808 is photographed by the camera of the production line under lighting, and the base map 808 and the corresponding code value are associated and saved in the database. In this way, the search efficiency of the base map 808 can be improved based on the code value 806.

[0060] Then, the server 104 determines whether there is a change in color based on the light reflected by the laser component in the unlit image 802 and the lit image 804, thereby obtaining a result of light change 810. It should be understood that based on the grating characteristics of the laser component, the color of the light reflected by the laser component is different when it is lit and when it is not lit. If the result of light change 810 is yes, it indicates that the laser component is a step grating structure at this time, and the next step of identification can be continued. If the result of light change 810 is no, it indicates that the laser component is counterfeit at this time, and there is no step grating structure. At this time, the recognition failure result 816 can be directly generated and sent to the terminal 102. In this way, it is possible to identify whether there is a laser component with a step grating structure in the anti-counterfeiting label based on the light change of the laser component in the unlit image 802 and the lit image 804, thereby improving the accuracy of anti-counterfeiting label identification.

[0061] In some embodiments, in the process of determining the result of the light change 810, the server 104 may first identify the unlit image 802 and the lit image 804 through a neural network model (which may be referred to as a first neural network model), thereby obtaining the area of ​​the coded pattern in the unlit image 802 and the area of ​​the coded pattern in the lit image 804. Then, the server 104 may segment the surrounding area of ​​the coded pattern from the unlit image 802 as the area of ​​the laser component, and segment the surrounding area of ​​the coded pattern from the lit image 804 as the area of ​​the laser component, and align the two segmented areas of the laser component. Further, the server 104 may identify the aligned area of ​​the laser component through another neural network model (which may be referred to as a second neural network model), thereby obtaining the result of the light change 810. In this way, the server 104 can first align the area of ​​the laser component through the neural network model, and then perform light recognition matching, thereby improving the accuracy of the result of the light change 810, and further improving the accuracy of the anti-counterfeiting recognition.

[0062] In the case where the result of light change 810 is yes, the server 104 determines whether the colored lines reflected by the laser components in the illuminated image 804 and the base image 808 match, thereby obtaining the result of light matching 812. Then, if the result of light matching 812 is yes, the server 104 generates a recognition success message 814 and sends it to the terminal 102 to inform the user that the anti-counterfeiting label is true. If the result of light matching 812 is no, the server 104 generates a recognition failure message 816 and sends it to the terminal 102 to inform the user that the anti-counterfeiting label is false.

[0063] In some embodiments, the terminal 102 may be a mobile phone, and the user may start an application software or program in the mobile phone, thereby opening a camera to detect the QR code pattern and determine the clarity of the QR code pattern. When the QR code pattern is clear, the mobile phone may take a photo of the QR code pattern as an unlit image. At the same time, the mobile phone may turn on a flashlight, and then colored lines will appear on the laser component in the area surrounding the QR code pattern. At this time, the mobile phone may take a photo of the QR code pattern as a lit image. Then, the mobile phone sends the unlit image and the lit image to the server 104.

[0064] Then, after receiving the unlit image and the lit image sent by the mobile phone, the server 104 can first identify the code value of the unlit image or the lit image, and obtain the corresponding base map according to the code value. The server 104 uses a deep neural network model to locate the QR code area of ​​the unlit image, the lit image, and the base map, and aligns the QR code surrounding area in the unlit image, the lit image, and the base map according to the position of the QR code area.

[0065] Furthermore, the server 104 determines whether there is a color change in the light reflected by the laser component based on the aligned QR code surrounding areas in the unlit image and the lit image. If there is no color change, it indicates that the anti-counterfeiting label at this time is counterfeit. If there is a color change, the server 104 further uses a deep neural network model to identify the aligned QR code surrounding areas in the lit image and the base image, so as to compare whether the laser patterns and colored line directions of the laser components of the two match. If they match, the recognition is successful, otherwise if they do not match, the recognition fails, which indicates that the anti-counterfeiting label is counterfeit. After obtaining the result of successful or failed recognition, the server 104 sends the recognition result to the mobile phone, and the mobile phone displays the recognition result on the screen after receiving the recognition result.

[0066] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, computing device embodiment, and computer program product embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0067] Fig. 9 Schematically shows a block diagram of a computing device 900 suitable for implementing an embodiment of the present invention. The computing device 900 can be used to implement the terminal 102 or the server 104. Fig. 9 As shown, the computing device 900 includes a processing unit (CPU) 901, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 902 or computer program instructions loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the computing device 900 can also be stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0068] A plurality of components in the computing device 900 are connected to the I / O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, and a processing unit 901 that performs the various methods and processes described above. For example, in some embodiments, the various processes or operations described above may be implemented as a computer software program, which is stored in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the computing device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the CPU 901, the various methods and processes described above may be performed, such as performing one or more operations of the method 200. Alternatively, in other embodiments, the CPU 901 may be configured to perform the various methods and processes described above, such as performing one or more actions of the method 200, by any other appropriate means (e.g., by means of firmware).

[0069] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0070] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0071] These computer-readable program instructions can be provided to a processor in a voice interaction device, a general-purpose computer, a special-purpose computer, or a processing unit of other programmable data processing devices, thereby producing a machine, so that when these instructions are executed by the processing unit of a computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other device to work in a specific manner.

[0072] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

[0074] The above are only optional embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying an anti-counterfeiting label, comprising: Acquire a first image of the anti-counterfeiting label captured under lighting, wherein the anti-counterfeiting label includes a laser component and a coding pattern; Based on the coding pattern in the first image, obtaining a base image of the anti-counterfeiting label collected under lighting; as well as In response to the color lines reflected by the laser component in the first image matching the color lines reflected by the laser component in the base image, a message is generated indicating that the anti-counterfeiting label is authentic.

2. The method according to claim 1, wherein the laser component in the anti-counterfeiting label further comprises a laser pattern, and generating the message comprises: In response to the laser pattern in the first image matching the laser pattern in the base image, determining a first recognition result; In response to the color line reflected by the laser component in the first image matching the color line reflected by the laser component in the base image, determining a second recognition result; as well as The message is generated based on the first recognition result and the second recognition result.

3. The method according to claim 2, wherein determining the first recognition result comprises: Determining a position of the laser pattern in the first image and a position of the laser pattern in the base image; as well as In response to the position of the laser pattern in the first image matching the position of the laser pattern in the base map, the first recognition result is determined.

4. The method according to claim 2, wherein determining the second recognition result comprises: Determining the position and / or orientation of the colored line in the first image and the position and / or orientation of the colored line in the base image; as well as In response to the positions of the colored lines in the first image matching the positions of the colored lines in the base map, and / or the directions of the colored lines in the first image matching the directions of the colored lines in the base map, the second recognition result is determined.

5. The method according to claim 1, further comprising: Determining, by a first neural network model, an area of ​​a coding pattern in the first image and an area of ​​a coding pattern in the base map; Based on the area of ​​the coding pattern in the first image and the area of ​​the coding pattern in the base image, aligning the area of ​​the laser component in the first image and the area of ​​the laser component in the base image; as well as Through the second neural network model, based on the aligned area of ​​the laser component in the first image and the area of ​​the laser component in the base image, it is determined whether the colored lines in the first image and the colored lines in the second image match.

6. The method of claim 1 , wherein generating the message comprises: Acquire a second image of the anti-counterfeiting label captured without illumination; In response to the color lines reflected by the laser assembly in the first image and the color lines reflected by the laser assembly in the second image being different in color, determining whether the color lines reflected by the laser assembly in the first image and the color lines reflected by the laser assembly in the base image match; and The message is generated in response to a match between the colored lines reflected by the laser assembly in the first image and the colored lines reflected by the laser assembly in the base image.

7. The method according to claim 6, further comprising: Determining, by a first neural network model, an area of ​​a coding pattern in the first image and an area of ​​a coding pattern in the second image; Aligning a region of the laser component in the first image with a region of the laser component in the second image based on a region of the coding pattern in the first image and a region of the coding pattern in the second image; as well as Through the second neural network model, based on the aligned area of ​​the laser component in the first image and the area of ​​the laser component in the second image, it is determined whether the colors of the colored lines in the first image and the colors of the colored lines in the second image are different.

8. The method according to claim 1, wherein obtaining the base map comprises: Determining a corresponding code value based on a coding pattern in the first image; as well as Based on the code value, the corresponding base map is searched in a database, and the base map and the code value are pre-associated and stored in the database.

9. The method according to any one of claims 1 to 8, wherein the laser assembly comprises a plurality of circular laser unit gratings.

10. A device for identifying an anti-counterfeit label, comprising: A first image acquisition module is configured to acquire a first image of the anti-counterfeiting label captured under lighting, wherein the anti-counterfeiting label includes a laser component and a coding pattern; A base image acquisition module, configured to acquire a base image of the anti-counterfeiting label collected under lighting conditions based on the coding pattern in the first image; as well as The message generating module is configured to generate a message indicating that the anti-counterfeiting label is authentic in response to a match between the colored lines reflected by the laser component in the first image and the colored lines reflected by the laser component in the base image.

11. A computing device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the computing device to perform the method according to any one of claims 1 to 9.

12. A computer program product comprising a computer program, the computer program being executed by a processor to implement the method according to any one of claims 1 to 9.

Images