CN110533704B - Method, device, equipment and medium for identifying and verifying ink label - Google Patents
Method, device, equipment and medium for identifying and verifying ink label Download PDFInfo
- Publication number
- CN110533704B CN110533704B CN201910663611.7A CN201910663611A CN110533704B CN 110533704 B CN110533704 B CN 110533704B CN 201910663611 A CN201910663611 A CN 201910663611A CN 110533704 B CN110533704 B CN 110533704B
- Authority
- CN
- China
- Prior art keywords
- ink
- ink label
- label
- color change
- verification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/37—Determination of transform parameters for the alignment of images, i.e. image registration using transform domain methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Abstract
The invention discloses an identification and counterfeit detection method of an ink label, which relates to the technical field of counterfeit prevention and is used for realizing commodity counterfeit detection based on the ink label, and the method comprises the following steps: acquiring an ink label image, and identifying the ink label image to extract ink characteristic information; acquiring a verification template, and performing feature comparison on the ink feature information and the verification template to obtain a feature comparison result; and returning a false checking result according to the characteristic comparison result. The invention also discloses an identification and counterfeit detection device of the ink label, electronic equipment and a computer storage medium. The invention realizes the commodity authentication by respectively extracting and comparing the ink characteristics and the laser characteristics of the ink label.
Description
Technical Field
The invention relates to the technical field of anti-counterfeiting, in particular to a method, a device, equipment and a medium for identifying and verifying an ink label.
Background
The packaging and printing industry of China is rapidly developed, the anti-counterfeiting label is more and more popularized to use, and the anti-counterfeiting label is particularly and generally applied to the packaging of high-end products such as medicines, cigarettes and the like so as to achieve the anti-counterfeiting effect.
However, after the anti-counterfeit label is popularized, counterfeiters on the market forge the anti-counterfeit label by a high-simulation means so as to forge high-end products; furthermore, the outer package of the high-end commodity is directly recycled for reprocessing, so that the consumer is deceived by counterfeiting and the market order is disturbed. However, common consumers lack professional identification capability for the anti-counterfeiting labels, and the phenomenon that the anti-counterfeiting labels are applied to commodity anti-counterfeiting is also common, and people generally cannot carefully distinguish whether the commodities printed with the anti-counterfeiting labels are genuine products in daily life.
The anti-counterfeiting label generally applied to the market comprises a laser label and an ink label, the existing laser patterns are generally transferred to packaging paper to form the laser label by the processes of bonding, compounding and the like of a laser film printed with the patterns, but the existing laser patterns are easily copied due to the wide application of the laser transfer film, so that the anti-counterfeiting effect is greatly reduced.
Therefore, the ink label is used for realizing commodity anti-counterfeiting, a better effect is achieved, the ink layer printed by the ink label generally at random is formed, the depth and the shape of the formed ink pattern are uncertain, and the ink label has randomness and uniqueness, so that the identification and verification processes of the ink label are relatively complex, if the ink layer of the ink label is superposed with the laser layer, static and dynamic anti-counterfeiting patterns can be formed, and a stronger anti-counterfeiting effect is achieved. Therefore, after the ink label is put on the market, a method for identifying and verifying the ink label needs to be provided to complete the identification and verification of the anti-counterfeiting pattern in the ink label.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide an identification and counterfeit checking method for an ink label, which performs feature extraction on an ink label image to obtain ink feature information of the ink label, and performs counterfeit checking by using the extracted ink feature information, thereby completing counterfeit checking on a product and further maintaining consumer benefits.
One of the purposes of the invention is realized by adopting the following technical scheme:
an identification and counterfeit verification method for an ink label comprises the following steps:
acquiring an ink label image, and identifying the ink label image to extract ink characteristic information;
acquiring a verification template, and performing feature comparison on the ink feature information and the verification template to obtain a feature comparison result;
and returning a false checking result according to the characteristic comparison result.
Further, the verification template is obtained through the unique identifier of the ink label, wherein the unique identifier of the ink label is as follows: and the bar code information or the label number of the ink label is bound with the verification template of the ink label.
Further, the ink label image is identified to extract ink characteristic information, and the specific extraction step comprises the following steps:
preprocessing the ink label image, determining the position of a positioning graph from the preprocessed ink label image according to graph positioning characteristics,
determining an anti-counterfeiting area according to the target characteristics and the position of the positioning graph;
correcting the anti-counterfeiting area through affine transformation;
carrying out binarization processing on the corrected anti-counterfeiting area to obtain a binary image;
equally dividing the binary image into a plurality of blocks, calculating the proportion of the ink in each block, setting the value of each block as 0 if the proportion is greater than or equal to a threshold value, and otherwise setting the value of each block as 1; and combining the values of the plurality of blocks into a binary number in sequence, wherein the binary number is the ink characteristic information.
Further, when the ink label contains the laser layer, the color change of the ink label image is also analyzed to judge whether the color change rule of the ink label is met, and the method comprises the following steps:
obtaining multiple frames of the ink label images, and converting the ink label images into HSV color space;
recording HSV color space of a plurality of frames of the ink label images, analyzing the color change of each pixel in the plurality of frames of the ink label images, and conforming to the color change rule of the ink label when the number and the distribution of the pixels with the color change meet set conditions, otherwise, not conforming to the color change rule of the ink label;
wherein the color change is analyzed by a VIBE algorithm, a Gaussian mixture model, or a deep learning model.
And further, forming a candidate anti-counterfeiting area by arranging and combining the positions of the positioning patterns, and determining the anti-counterfeiting area from the candidate area according to the target characteristics.
Further, the extracted ink characteristic information is used for carrying out verification comparison, and the verification comparison process comprises the following steps: comparing the ink characteristic information with a pre-stored verification template corresponding to the ink label, and if the comparison is successful, verifying to pass; otherwise, the verification fails.
Further, the extracted ink characteristic information is used for carrying out verification comparison, and the verification comparison process comprises the following steps: comparing the ink characteristic information with a pre-stored verification template corresponding to the ink label, and if the comparison is successful and the comparison accords with the color change rule, verifying that the ink label passes; otherwise, the verification fails.
The invention also aims to provide a device for identifying and verifying the ink label, which respectively identifies and verifies the ink pattern and the laser pattern of the ink label so as to verify the commodity.
The second purpose of the invention is realized by adopting the following technical scheme:
an ink label identification and counterfeit verification device, comprising:
the image acquisition module is used for acquiring an ink label image and identifying the ink label image to extract ink characteristic information;
the verification module is used for acquiring a verification template and comparing the characteristics of the ink with the verification template to obtain a characteristic comparison result;
and the result output module is used for returning a false-checking result according to the characteristic comparison result.
It is a further object of the present invention to provide an electronic device for performing one of the above objects, comprising a processor, a storage medium, and a computer program, wherein the computer program is stored in the storage medium, and when the computer program is executed by the processor, the method for identifying and verifying an ink label is realized.
It is a fourth object of the present invention to provide a computer-readable storage medium storing one of the objects of the present invention, having a computer program stored thereon, which when executed by a processor, implements the above-described method for verifying the identification of an ink label.
Compared with the prior art, the invention has the beneficial effects that:
the invention can verify the ink label by identifying and extracting the characteristics of the ink in the ink label and finally comparing the extracted ink characteristic information with the predefined verification template, so as to realize the product verification and further achieve the purpose of maintaining the benefits of consumers.
Drawings
FIG. 1 is a flow chart of a method of identifying an ink label of the present invention;
FIG. 2 is a flow chart of a method of identifying and verifying an ink label of example 2;
FIG. 3 is a block diagram showing the structure of an identification and forgery verification apparatus for an ink label of example 3;
fig. 4 is a block diagram of the electronic apparatus of embodiment 4.
Detailed Description
The present invention will now be described in more detail with reference to the accompanying drawings, and it is to be understood that the following description of the invention with reference to the drawings is illustrative and not restrictive. The various embodiments may be combined with each other to form other embodiments not shown in the following description.
Example 1
The embodiment provides an identification and verification method of an ink label, which aims to realize the extraction of ink characteristics by collecting an ink label image, then identifying the ink label image, and comparing the extracted ink characteristics with a predefined verification template so as to complete the identification and verification of the ink label, wherein binary numbers are adopted to describe the ink characteristics, and when the ink characteristics are compared, verification can be completed only by comparing numerical values, so that the cost of the comparison process is low.
Based on the above principle, as shown in fig. 1, an identification and counterfeit verification method for an ink label includes the following steps:
acquiring an ink label image, and identifying the ink label image to extract ink characteristic information;
obtaining a verification template, and performing characteristic comparison on the ink characteristic information and the verification template to obtain a characteristic comparison result;
and returning a false checking result according to the characteristic comparison result.
In this embodiment, the ink label without the laser layer superimposed thereon is identified and verified, the ink label includes an ink area and a non-ink area, and only the ink characteristic information of the ink label needs to be extracted to perform characteristic comparison.
The embodiment of the invention adopts the ink label images directly collected by the camera, and can also scan the ink labels in real time to obtain the scanning video of the ink labels, extract the frames of the scanning video to obtain a plurality of ink label images, and perform subsequent identification and feature extraction on the ink label images. And extracting frames of the scanning video, reading the scanning video by adopting MATLAB, and then performing image separation to obtain the scanning video.
Preferably, the verification template is obtained by a unique identification of an ink label, the unique identification of the ink label being: and the bar code information or the label number of the ink label is bound with the verification template of the ink label.
In other embodiments of the invention, the acquisition of the verification template is realized by adopting a bar code matched with the ink label, the bar code adopts a one-dimensional code or a two-dimensional code for data storage, and by taking the two-dimensional code as an example, two-dimensional code information is obtained by identifying the two-dimensional code, the two-dimensional code information is the unique identifier of the ink label, and the two-dimensional code information is bound with the verification template of the ink label in advance; acquiring a verification template from a server according to two-dimension code information for feature comparison, then acquiring an ink label image, identifying the ink label image and extracting feature information, then comparing the feature information with the verification template, and obtaining a false verification result according to the comparison result, namely, performing false verification comparison by using the extracted ink feature information, wherein the false verification comparison process comprises the following steps: comparing the ink characteristic information with a pre-stored verification template corresponding to the ink label, and if the comparison is successful, verifying to pass; otherwise, the verification fails. In other embodiments of the invention, if the comparison is successful, the verification is returned, and the commodity information using the ink label is returned, so that the tracing to the commodity is realized.
In another embodiment of the present invention, the unique identifier of the ink label is a label number printed on the ink label, and when the ink label image is identified, the label number in the ink label image is extracted by an OCR technology.
The ink label identification and verification method provided by the embodiment can be applied to a terminal or a server, the terminal comprises but is not limited to electronic products such as a mobile phone and a tablet personal computer which can perform video acquisition, image acquisition and network transmission, when the ink label identification and verification method is used on the terminal, the image identification is performed after the ink label image is directly acquired through the terminal, so that the characteristic information of the ink label is extracted, then the verification template is obtained from the database and is compared with the characteristic information, the verification result is obtained, and the verification result is displayed on the terminal. When the ink label identification and verification method is used on a server, the server acquires an ink label image from a verification end and then performs image identification, so that the characteristic information of the ink label is extracted, then acquires a verification template from a database of the server and compares the verification template with the characteristic information, and the obtained verification result is returned to the verification end to be displayed.
If the server obtains the ink label image from the verification end by acquiring the video stream of the ink label, after the server receives the unique identifier of the ink label, the server sends a video stream pushing URL to the verification end, the verification end creates a stream pushing thread through a monitoring thread of an RTMP protocol, so that a real-time ink label scanning video is collected through the stream pushing thread and is pushed to the video stream pushing URL, the server end pulls corresponding video stream information from the video stream URL, and frames of the video stream information are taken to be converted into the ink label image.
Preferably, the specific steps of identifying the ink label image to extract the ink characteristic information are introduced, and include:
preprocessing the ink label image, determining the position of a positioning graph from the preprocessed ink label image according to graph positioning characteristics,
determining an anti-counterfeiting area according to the target characteristics and the position of the positioning graph;
correcting the anti-counterfeiting area through affine transformation;
carrying out binarization processing on the corrected anti-counterfeiting area to obtain a binary image;
the binary image is divided into a plurality of blocks, and the sizes of the blocks can be equal or unequal. Calculating the proportion of the ink in each block, if the proportion is larger than a threshold value, setting the value of the block as 0, otherwise, setting the value of the block as 1; and combining the values of the plurality of blocks into a binary number in sequence, wherein the binary number is the ink characteristic information. It can be understood that the more the number of blocks dividing the binary image, the more binary numbers obtained by the binary image, and the more accurate the comparison.
In this embodiment, the operation of preprocessing the ink label image is as follows: the ink label image is converted into a grayscale image using MATLAB function rgb2gray (). And (3) carrying out edge detection on the preprocessed ink label image, wherein MATLAB edge detection operators are adopted for realizing the edge detection, and Sobel operators, canny operators, prewitt operators, roberts operators, laplacian operators and the like can be selected as an edge detection algorithm.
The position of discontinuous change of the gray scale can be positioned through edge detection, so that the boundary line between the anti-counterfeiting pattern and the background in the ink label image is obtained. And obtaining the position of the positioning graph in the ink label image after the edge detection according to the characteristics of the positioning graph.
And obtaining candidate anti-counterfeiting areas by arranging and combining the positions of the obtained positioning patterns, screening out the anti-counterfeiting areas according to target characteristics, and correcting the anti-counterfeiting areas through affine transformation to enable the anti-counterfeiting areas to be standard rectangles so as to facilitate subsequent characteristic information extraction.
The target feature and the positioning graphic feature are standard features of a predefined anti-counterfeiting area, and are used as reference standards for extracting the anti-counterfeiting area from the ink label, and the standard features are used for determining the anti-counterfeiting area during identification and verification.
When the unique identification of the ink label is two-dimensional code information, 3 'Hui' type areas on the two-dimensional code can be used as the characteristics of the positioning graph for positioning the ink label, the positioning graph has determined black and white intervals, the specific position of the positioning graph is obtained according to the combination of a plurality of continuous black and white interval distances, and the positions of the obtained positioning graph are arranged and combined in a sampling mode without being replaced, so that the candidate anti-counterfeiting area is obtained.
Because the extracted ink characteristic information is binary number, when the ink characteristic is compared, only numerical value comparison is needed, and the specific shape, size and distribution of an ink area are not required to be extracted, so that the operation is simpler, the technical complexity of ink characteristic extraction can be reduced, and the system overhead generated in the comparison process is small.
And (3) carrying out self-adaptive binarization on the corrected anti-counterfeiting area by adopting a binarization algorithm, taking a threshold value, displaying white when the value of the pixel point which is greater than the threshold value is 1, and displaying black when the value of the pixel point which is less than the threshold value is naturally assigned to be 0. Therefore, in the binary image by the adaptive binarization process in the present embodiment, the ink area is represented by 0 and the non-ink area is represented by 1.
In adaptive binarization, the quality of this threshold determination directly affects the effect. The simplest threshold determination is to take the mean of the whole picture, but other algorithms can be chosen to determine the adaptive binarization threshold, such as the adaptive threshold based on the Wall algorithm, and the basic idea is to traverse the image and calculate a moving average, and if a pixel is significantly lower than this average, it is set to black, otherwise it is set to white.
Example 2
The difference between this embodiment and the above embodiment is that this embodiment describes a method for identifying and verifying an ink label on which a laser layer is superimposed, as shown in fig. 2, the steps include:
acquiring an ink label image, and identifying the ink label image to extract ink characteristic information;
acquiring a verification template, and performing feature comparison on the ink feature information and the verification template to obtain a feature comparison result;
analyzing the color change of a plurality of frames of the ink label images, and judging whether the color change accords with the color change rule of the ink label to obtain a judgment result;
and returning a false checking result according to the characteristic comparison result and the judgment result.
The specific steps of identifying the ink label image to extract the ink characteristic information include:
preprocessing the ink label image, determining the position of a positioning graph from the preprocessed ink label image according to graph positioning characteristics,
determining an anti-counterfeiting area according to the target characteristics and the position of the positioning graph;
correcting the anti-counterfeiting area through affine transformation;
carrying out binarization processing on the corrected anti-counterfeiting area to obtain a binary image;
equally dividing the binary image into a plurality of blocks, calculating the proportion of the ink in each block, and setting the value of each block as 0 if the proportion is greater than a threshold value, otherwise setting the value of each block as 1; and combining the values of the plurality of blocks into a binary number in sequence, wherein the binary number is the ink characteristic information.
Analyzing the color change of a plurality of frames of the ink label images, judging whether the color change accords with the color change rule of the ink label or not, and obtaining a judgment result, wherein the method specifically comprises the following steps:
acquiring a plurality of frames of the ink label images, and converting the ink label images into HSV color spaces;
recording HSV color space of a plurality of frames of the ink label images, analyzing the color change of each pixel in the plurality of frames of the ink label images,
when the number and the distribution of the pixels with the changed colors meet set conditions, the color change rule of the ink label is met, otherwise, the color change rule of the ink label is not met;
wherein the color change is analyzed by a VIBE algorithm, a Gaussian mixture model, or a deep learning model.
The ink label in this embodiment is formed by overlapping an ink layer and a laser layer, and the ink label includes an ink area and a laser area, so in the binary image obtained by the adaptive binarization processing in this embodiment, the ink area is represented by 0, and the laser area is represented by 1.
In other embodiments of the present invention, the ink label image may also be converted to a CMYK color space, an HSL color space, or an HSB color space, and then each pixel may be analyzed for color changes over multiple frames of the ink label image.
The color change of each pixel in a multi-frame ink label image is analyzed, a deep learning model is adopted to summarize the color change of the multi-frame ink label image, a deep learning model of CNN (convolutional neural network) + LSTM (long short term memory network) is specifically selected to summarize the color change rule (color change characteristic) of the ink label image, when the color change characteristic meets a set condition, the color change characteristic is judged to be met, otherwise, the color change characteristic is not met, the set condition is self-defined according to an actual condition, the set condition can be a self-defined corresponding threshold value, namely, the CNN + LSTM deep learning model is utilized to judge the authenticity of the ink label through training, and the color change rule (laser rule) of the ink label is obtained.
The CNN + LSTM deep learning model is a machine learning model, and is a corresponding relation model obtained by a computer through mechanical learning, teaching learning, analogy learning or case learning and the like based on sample data. The more the sample data is, the more accurate the relation model obtained by machine learning is, that is, the more accurate the color change rule of the laser material used for summarizing the ink label in the example is, and the change rule of the laser material is obtained through repeated iterative training, so that the more the number of frames (the more the number) of the ink label image obtained by the method is, the more accurate the color change characteristic of the ink label obtained through learning and summarizing is. Training of the model using CNN + LSTM is common knowledge in the art, and the detailed description of the training process is omitted here.
Preferably, the extracted ink characteristic information is used for performing verification comparison, and the verification comparison process comprises the following steps: comparing the ink characteristic information with a pre-stored verification template corresponding to the ink label, and if the comparison is successful and the color change rule is met, verifying that the ink label passes; otherwise, the verification fails. Namely, after the ink label is identified and verified, two verification results of passing and failing to pass are returned. In other embodiments of the invention, when the comparison is successful and the color change rule is met, a verification passing result is returned, and product information of the commodity using the ink label is returned, so that the commodity source tracing is realized while the commodity verification is realized. Here, a binary number of the ink distribution of the ink label is described, the number of which is equal to that of the binary number of the ink characteristic information, and the divided blocks (size and number) and the sorting manner are completely corresponding.
The ink labels mentioned in examples 1 and 2 above have a substrate with a plurality of different patterns, a diffusion layer, an ink layer with random shrink text, the diffusion layer being on the substrate and the ink layer being on the diffusion layer. The substrate can be laser card paper. The ink layer may be black or other colors. The substrate can also be a non-setting adhesive substrate containing laser card paper, a diffusion coating is arranged on the substrate with patterns, an ink layer with random contraction patterns is arranged on the diffusion coating, ink contraction pictures and texts are shown at the position covered by the ink, and laser shading and/or patterns are shown at the position not covered by the ink. That is to say, the laser texture which is not covered by the ink is randomly leaked out to achieve randomness, random structural features of laser textures with different depths and different colors are presented at the same time, and the formed structural combination features are physical anti-counterfeiting features which are three-dimensional, unique and can not be copied.
The ink label exhibits the following characteristics: the base material with various patterns is combined with the ink layer with random pictures and texts, so that the randomness is high, and the repetition rate is extremely low; the anti-counterfeiting label formed after the ink is shrunk has the advantages of concave-convex feeling, three-dimensional random characteristics, increased physical property, dynamic change formed by laser shading, incapability of being forged in a copying mode and the like. The laser card paper has the advantages that various different patterns on the laser card paper and the color of the laser card paper under light rays enable the laser card paper to have three-dimensional stereo random characteristics and four-dimensional dynamic random characteristics, and due to the increased dynamic change, the copied patterns cannot be forged, the random patterns without dynamic change are overcome, and the laser card paper is easy to copy and forge in modes of photographing and the like. The ink label provided by the invention is difficult to copy, namely, after the dynamic characteristics are added, the ink label is difficult to copy, and the four-dimensional random code greatly increases the copying difficulty.
Example 3
The present embodiment discloses a device corresponding to the method for identifying and verifying an ink label in the foregoing embodiment, which is a virtual device structure in the foregoing embodiment, and please refer to fig. 3, the apparatus for identifying and verifying an ink label includes:
the image acquisition module 310 is configured to acquire an ink label image, and identify the ink label image to extract ink characteristic information and laser characteristic information;
the counterfeit checking module 320 is configured to obtain a verification template, and perform feature comparison on the ink feature information and the laser feature information with the verification template respectively to obtain a feature comparison result;
and the result output module 330 is configured to return a verification result according to the feature comparison result.
Preferably, the verification template is ink characteristic information of an ink area in the ink label. When the ink label image is identified, the anti-counterfeiting area is determined by using the graphic positioning feature and the target feature of the ink label, the feature extraction is carried out after the anti-counterfeiting area is determined, and the graphic positioning feature and the target feature are stored after being defined in advance. And respectively comparing the characteristics of the verification templates with the extracted ink characteristic information to complete the verification of the ink label, and further judging the authenticity of the commodity.
When the ink label is formed by overlapping the ink layer and the laser layer, in the counterfeit detection module 320, a plurality of frames of color changes of the ink label image are analyzed, whether the color changes accord with the color change rule of the ink label or not is judged, and a judgment result is obtained, namely whether the color change rule accords with the color change rule of the ink label or not is judged.
If the characteristics are successfully compared and the color change rule of the ink label is met, returning a result of passing the verification, and simultaneously returning product information of the commodity using the ink label for displaying to realize commodity tracing; otherwise, the result that the false verification fails is returned.
Example 4
Fig. 4 is a schematic structural diagram of an electronic device according to embodiment 4 of the present invention, as shown in fig. 4, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the computer device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and the bus connection is exemplified in fig. 4.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the identification and verification method of the ink tag in the embodiment of the present invention (for example, the image acquisition module 310, the verification module 320, and the result output module 330 in the identification and verification of the ink tag). The processor 410 executes various functional applications and data processing of the electronic device by executing the software programs, instructions and modules stored in the memory 420, that is, implements the identification and verification method of the ink labels of the above embodiments 1 and 2.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to an electronic device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive an input ink label image or unique identification of an ink label, etc. The output device 440 may include a display device such as a display screen.
Example 5
Embodiment 5 of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for identifying an ink label, the method comprising:
acquiring an ink label image, and identifying the ink label image to extract ink characteristic information and laser characteristic information;
obtaining a verification template, and respectively performing characteristic comparison on the ink characteristic information and the laser characteristic information with the verification template to obtain a characteristic comparison result;
and returning a false checking result according to the characteristic comparison result.
Of course, the storage medium provided by the embodiments of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the method for verifying an identification based on an ink label provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling an electronic device (which may be a mobile phone, a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the identification and counterfeit verification method device based on the ink label, the included units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (8)
1. An identification and counterfeit verification method for an ink label, wherein the ink label comprises a laser layer, and the method comprises the following steps:
acquiring an ink label image, and identifying the ink label image to extract ink characteristic information;
acquiring a verification template, and performing feature comparison on the ink feature information and the verification template to obtain a feature comparison result;
acquiring a plurality of frames of ink label images and analyzing the color change of each pixel in the plurality of frames of ink label images;
returning a false-checking result according to the characteristic comparison result and the color change rule;
the analyzing the color change of each pixel in the multi-frame ink label image comprises:
acquiring a color change rule of the ink label image by adopting a convolutional neural network and a long-short term memory network deep learning model; acquiring a plurality of frames of the ink label images, and converting the ink label images into HSV color space; recording HSV color space of a plurality of frames of the ink label images, analyzing the color change of each pixel in the plurality of frames of the ink label images, and conforming to the color change rule of the ink label when the number and distribution of the pixels with the color change meet set conditions, otherwise, not conforming to the color change rule of the ink label; the set condition is that the user self-defines according to the actual situation.
2. The method for verifying the identification of an ink label according to claim 1, wherein the verification template is obtained by a unique identification of the ink label, the unique identification of the ink label being: and the bar code information or the label number of the ink label is bound with the verification template of the ink label.
3. The method for identifying and verifying the ink label according to claim 1, wherein the step of identifying the ink label image to extract the ink characteristic information comprises the following specific steps:
preprocessing the ink label image, determining the position of a positioning graph from the preprocessed ink label image according to graph positioning characteristics,
determining an anti-counterfeiting area according to the target characteristics and the position of the positioning graph;
correcting the anti-counterfeiting area through affine transformation;
carrying out binarization processing on the corrected anti-counterfeiting area to obtain a binary image;
dividing the binary image into a plurality of blocks, calculating the proportion of ink in each block, and setting the value of each block as 0 if the proportion is greater than or equal to a threshold value, otherwise, setting the value of each block as 1; and combining the values of the plurality of blocks into a binary number in sequence, wherein the binary number is the ink characteristic information.
4. The method for identifying and verifying the ink label according to claim 3, wherein a candidate anti-counterfeiting area is formed by arranging and combining the positions of the positioning patterns, and the anti-counterfeiting area is determined from the candidate anti-counterfeiting area according to target characteristics.
5. The method for identifying and verifying the ink label according to claim 3, wherein the extracted ink characteristic information is used for verification and comparison, and the verification and comparison process comprises the following steps: comparing the ink characteristic information with a pre-stored verification template corresponding to the ink label, and if the comparison is successful and the comparison accords with the color change rule, verifying that the ink label passes; otherwise, the verification fails.
6. An identification and counterfeit detection device for an ink label is characterized by comprising:
the image acquisition module is used for acquiring an ink label image, wherein the ink label comprises a laser layer and identifies the ink label image to extract ink characteristic information; simultaneously acquiring a plurality of frames of ink label images and analyzing the color change of each pixel in the plurality of frames of ink label images;
the verification module is used for acquiring a verification template and comparing the characteristics of the ink with the verification template to obtain a characteristic comparison result;
the analyzing the color change of each pixel in the multi-frame ink label image comprises:
acquiring a color change rule of the ink label image by adopting a convolutional neural network and a long-short term memory network deep learning model; acquiring a plurality of frames of the ink label images, and converting the ink label images into HSV color space; recording HSV color space of a plurality of frames of the ink label images, analyzing the color change of each pixel in the plurality of frames of the ink label images through a VIBE algorithm, a Gaussian mixture model or a deep learning model, and conforming to the color change rule of the ink label when the number and the distribution of the pixels with the color change meet set conditions, or not conforming to the color change rule of the ink label; the set condition is that the user self-defines according to the actual situation;
and the result output module is used for returning a false checking result according to the characteristic comparison result and the color change rule.
7. An electronic device comprising a processor, a storage medium, and a computer program, the computer program being stored in the storage medium, wherein the computer program, when executed by the processor, implements the method of ink tag identification according to any one of claims 1 to 5.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method of authenticating an ink label according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910663611.7A CN110533704B (en) | 2019-07-22 | 2019-07-22 | Method, device, equipment and medium for identifying and verifying ink label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910663611.7A CN110533704B (en) | 2019-07-22 | 2019-07-22 | Method, device, equipment and medium for identifying and verifying ink label |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533704A CN110533704A (en) | 2019-12-03 |
| CN110533704B true CN110533704B (en) | 2022-11-11 |
Family
ID=68661778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910663611.7A Active CN110533704B (en) | 2019-07-22 | 2019-07-22 | Method, device, equipment and medium for identifying and verifying ink label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533704B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160331A (en) * | 2020-01-13 | 2020-05-15 | 杭州沃朴物联科技有限公司 | Anti-counterfeit label authentication method, device, medium and template graph generation method |
| CN112164057A (en) * | 2020-10-09 | 2021-01-01 | 珠海格力电器股份有限公司 | Qualified label detection method, storage medium and electronic equipment |
| CN115423771B (en) * | 2022-09-01 | 2023-06-30 | 西安电子科技大学 | Quasi-dynamic laser anti-counterfeit label identification method based on feature non-uniformity |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201993996U (en) * | 2011-01-31 | 2011-09-28 | 山东泰宝防伪技术产品有限公司 | Environment-friendly variable-laser digital anti-counterfeiting mark |
| CN202171817U (en) * | 2011-08-18 | 2012-03-21 | 陈毕峰 | Variable two-dimension code with laser holographic effect |
| CN203773868U (en) * | 2014-03-24 | 2014-08-13 | 深圳市坤弘科技有限公司 | Anti-counterfeiting label containing photochromic ink |
| CN104320561A (en) * | 2014-10-31 | 2015-01-28 | 上海出版印刷高等专科学校 | Multi-level printing system control method based on optimum ink utilization |
| WO2016206173A1 (en) * | 2015-06-23 | 2016-12-29 | 杭州沃朴物联科技有限公司 | Chaotic graphic tag-based anti-counterfeit system and method |
| CN107093259A (en) * | 2017-03-09 | 2017-08-25 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of forge or true or paper money and its device |
| CN109583916A (en) * | 2018-11-15 | 2019-04-05 | 无锡火眼睛睛科技发展有限公司 | A kind of electronic anti-fogery traceability system based on bar code |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1307307A (en) * | 2000-01-27 | 2001-08-08 | 徐世刚 | Dynamic anti-fake method and microcomputer-recognized intelligent anti-fake label |
| CN100367134C (en) * | 2002-04-15 | 2008-02-06 | 上海紫丹印务有限公司 | Method for producing halftone dot interference and laser holographic picture antiforging package and product thereof |
| CN102663961B (en) * | 2012-03-21 | 2014-06-04 | 杜浩燕 | Fabrication method for anti-counterfeiting film, tag of anti-counterfeiting film, anti-counterfeiting tag and anti-counterfeiting system |
| CN103745179A (en) * | 2013-03-04 | 2014-04-23 | 立德高科(北京)数码科技有限责任公司 | Image anti-counterfeiting identification method applied in labels |
| CN103426014A (en) * | 2013-07-12 | 2013-12-04 | 天津科技大学 | Anti-counterfeiting method of print pictures based on CCD detection |
| CN103559473B (en) * | 2013-10-28 | 2017-08-01 | 汝思信息技术（上海）有限公司 | The false proof method and system of stock is realized using characteristic image |
| CN104070739A (en) * | 2013-12-27 | 2014-10-01 | 湖北联合天诚防伪技术股份有限公司 | Preparation method of dual-layer holographic anti-counterfeiting film, product with dual-layer holographic anti-counterfeiting film, and recognition method |
| CN106529976A (en) * | 2016-10-28 | 2017-03-22 | 珠海丹德图像技术有限公司 | Checking system and checking method for commodity determination uniqueness |
| CN106960352A (en) * | 2017-02-14 | 2017-07-18 | 广州软码信息科技有限公司 | A kind of method for anti-counterfeit based on picture uniqueness |
| CN107092948A (en) * | 2017-05-16 | 2017-08-25 | 李峰 | A kind of anti-counterfeit structure and method for anti-counterfeit based on stereochemical structure three-dimension code |
| CN107516465A (en) * | 2017-08-30 | 2017-12-26 | 广州市挚联数码科技有限公司 | A kind of 3D three-dimensional lasers antifalsification label and its application |
| CN109929270B (en) * | 2019-03-29 | 2020-10-27 | 东莞市斯缤克化工科技有限公司 | Material with temperature-sensitive change and optical angle-dependent color change and preparation method thereof |
-
2019
- 2019-07-22 CN CN201910663611.7A patent/CN110533704B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201993996U (en) * | 2011-01-31 | 2011-09-28 | 山东泰宝防伪技术产品有限公司 | Environment-friendly variable-laser digital anti-counterfeiting mark |
| CN202171817U (en) * | 2011-08-18 | 2012-03-21 | 陈毕峰 | Variable two-dimension code with laser holographic effect |
| CN203773868U (en) * | 2014-03-24 | 2014-08-13 | 深圳市坤弘科技有限公司 | Anti-counterfeiting label containing photochromic ink |
| CN104320561A (en) * | 2014-10-31 | 2015-01-28 | 上海出版印刷高等专科学校 | Multi-level printing system control method based on optimum ink utilization |
| WO2016206173A1 (en) * | 2015-06-23 | 2016-12-29 | 杭州沃朴物联科技有限公司 | Chaotic graphic tag-based anti-counterfeit system and method |
| CN107093259A (en) * | 2017-03-09 | 2017-08-25 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of forge or true or paper money and its device |
| CN109583916A (en) * | 2018-11-15 | 2019-04-05 | 无锡火眼睛睛科技发展有限公司 | A kind of electronic anti-fogery traceability system based on bar code |
Non-Patent Citations (3)
| Title |
|---|
| Inkjet-printed unclonable quantum dot fluorescent anti-counterfeiting labels with artificial intelligence authentication;Yang Liu 等;《nature communications》;20190603;第1-9页 * |
| 光学水印半色调信息隐藏防伪技术研究;任龙飞;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20180115;第2018年卷(第01期);第B024-771页 * |
| 基于 CNN+LSTM 的空间目标识别;张耀天 等;《第十二届全国信号和智能信息处理与应用学术会议论文集》;20181231;第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533704A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210383150A1 (en) | Iterative recognition-guided thresholding and data extraction | |
| Gebhardt et al. | Document authentication using printing technique features and unsupervised anomaly detection | |
| CN102663600B (en) | Anti-counterfeiting system based on digital watermarks and barcodes, anti-counterfeiting method for anti-counterfeiting system and application of anti-counterfeiting system | |
| CN110428028B (en) | Identification and verification method, device, equipment and medium based on quasi-dynamic laser label | |
| CN110533704B (en) | Method, device, equipment and medium for identifying and verifying ink label | |
| CN103761799B (en) | A kind of bill anti-counterfeit method based on texture image feature and device | |
| US9681020B2 (en) | Creation and identification of unforgeable printable image information data | |
| US8818018B2 (en) | System and method for enhancing security printing | |
| CN110766594B (en) | Information hiding method and device, detection method and device and anti-counterfeiting tracing method | |
| TW201413602A (en) | Label recognition processing method and system based on mobile terminal | |
| van Beusekom et al. | Automatic authentication of color laser print-outs using machine identification codes | |
| US20170200247A1 (en) | Systems and methods for authentication of physical features on identification documents | |
| CN116664961B (en) | Intelligent identification method and system for anti-counterfeit label based on signal code | |
| CN111160331A (en) | Anti-counterfeit label authentication method, device, medium and template graph generation method | |
| Tele et al. | Detection of fake Indian currency | |
| CN113435219B (en) | Anti-counterfeiting detection method and device, electronic equipment and storage medium | |
| CN113392664B (en) | Anti-counterfeiting two-dimensional code generation method, anti-counterfeiting method and device | |
| CN110619060B (en) | Cigarette carton image database construction method and cigarette carton anti-counterfeiting query method | |
| CN115035533A (en) | Data authentication processing method and device, computer equipment and storage medium | |
| EP3982289A1 (en) | Method for validation of authenticity of an image present in an object, object with increased security level and method for preparation thereof, computer equipment, computer program and appropriate reading means | |
| CN114241463A (en) | Signature verification method and device, computer equipment and storage medium | |
| JP2012212287A (en) | Individual identification device, individual identification method, and program | |
| Björkman | Evaluation of the effects of different preprocessing methods on ocr results from images with varying quality | |
| US20170200383A1 (en) | Automated review of forms through augmented reality | |
| WO2014177220A1 (en) | Detection of presence of a bar code in image data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |