CN110533704A - Fake method, device, equipment and medium are tested in the identification of ink label - Google Patents
Fake method, device, equipment and medium are tested in the identification of ink label Download PDFInfo
- Publication number
- CN110533704A CN110533704A CN201910663611.7A CN201910663611A CN110533704A CN 110533704 A CN110533704 A CN 110533704A CN 201910663611 A CN201910663611 A CN 201910663611A CN 110533704 A CN110533704 A CN 110533704A
- Authority
- CN
- China
- Prior art keywords
- ink
- ink label
- label
- tested
- identification
- 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.)
- Granted
Links
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 a kind of identifications of ink label to test fake method, it is related to field of anti-counterfeit technology, puppet is tested for realizing the commodity based on ink label, method includes the following steps: obtaining ink label image, the ink label image is identified to extract ink characteristic information；Validation template is obtained, the ink feature information and validation template are subjected to aspect ratio pair, obtain feature comparison result；Pseudo- result is tested as a result, returning according to the aspect ratio pair.The invention also discloses a kind of identifications of ink label to test pseudo-device, electronic equipment and computer storage medium.The present invention is extracted and is compared respectively by ink feature to ink label and radium-shine feature, and that realizes commodity tests puppet.
Description
Technical field
The present invention relates to field of anti-counterfeit technology more particularly to a kind of identification of ink label test fake method, device, equipment and
Medium.
Background technique
The packages printing industry in China is grown rapidly, antifalsification label using more more and more universal, especially in drug, cigarette
It is commonly used in the packaging of equal high-end products, to reach antifalse effect.
But with antifalsification label it is universal after, fake producer in the market carries out antifalsification label with high simulation means pseudo-
It makes, to realize the fraud to high-end product；What is more, and the outer packing for directly recycling high-end commodity goes to re-work, and is made with this
Vacation deception consumer, disrupts the market.But ordinary consumer lacks the recognition capability of profession to these antifalsification labels, and
The phenomenon that being applied to commodity counterfeit prevention to antifalsification label has also been accustomed to, and general no one goes carefully to distinguish in daily life
Whether these commodity for being printed on antifalsification label are certified products.
Commonly used antifalsification label in the market, including laser label and ink label, existing radium-shine figure line are usual
Laser label is formed using will be printed on the laser film of figure line and be transferred on wrapping paper by being bonded the processes such as compound, but due to radium-shine
The extensive utilization of transfer membrane, existing radium-shine figure line are very easy to copy, and greatly reduce its anti-fake effect.
Therefore, it goes to realize commodity counterfeit prevention using ink label, has better effect, the printing of ink label general random
Ink layer is formed, and the depth, the shape of the ink logo formed are uncertain, has randomness and uniqueness, therefore to such
The identification of ink label and verification process are relatively complicated, if the ink layer of ink label is superimposed radium-shine figure layer, will form
Static and dynamic security pattern has stronger antifalse effect.So needing to propose a kind of needle after ink label puts goods on the market
To the identification verification method of ink label, completes the identification to security pattern in ink label and verify.
Summary of the invention
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide a kind of identifications of ink label to test puppet
Method obtains the ink feature information of ink label, utilizes what is extracted by carrying out feature extraction to ink label image
Ink feature information carries out testing puppet, to complete the puppet of testing to product, and then can preferably safeguard consumer's interests.
An object of the present invention is implemented with the following technical solutions:
Fake method is tested in a kind of identification of ink label, comprising the following steps:
Ink label image is obtained, the ink label image is identified to extract ink characteristic information；
Validation template is obtained, the ink feature information and validation template are subjected to aspect ratio pair, obtain aspect ratio to knot
Fruit；
Pseudo- result is tested as a result, returning according to the aspect ratio pair.
Further, validation template, the unique identification of the ink label are obtained by the unique identification of ink label are as follows:
The tag number of the bar code information or ink label bound with the validation template of ink label.
Further, the ink label image is identified to extract ink characteristic information, it is specific to extract step
Suddenly include:
The ink label image is pre-processed, according to figure location feature, from the pretreated ink mark
The position that positioning pattern is determined in image is signed,
According to the position of target signature and the positioning pattern, anti-fake region is determined；
The anti-fake region is corrected by affine transformation；
Anti-fake region after correction is subjected to binary conversion treatment, obtains binary map；
The binary map is drawn and is divided into several piecemeals, the accounting of ink in each piecemeal is calculated, if the accounting is greater than
Or be equal to threshold value, then the value of piecemeal is set to 0, otherwise is set to 1；The value of several piecemeals is combined into binary system in order
Number, the binary number are ink feature information.
Further, when ink label includes radium-shine figure layer, the color change of the ink label image is also analyzed, with
Judge whether the color change rule for meeting the ink label comprising following steps:
Ink label image described in multiframe is obtained, the ink label image is converted into HSV color space；
The HSV color space of ink label image described in multiframe is recorded, is analyzed each in ink label image described in multiframe
The color change of pixel then meets the ink when the pixel quantity of the color change and the condition of distribution satisfaction setting
The color change rule of label, conversely, not meeting then；
Wherein, pass through color change described in VIBE algorithm, mixed Gauss model or deep learning model analysis.
Further, candidate anti-fake region is formed by the position of positioning pattern described in permutation and combination, further according to target spy
Sign determines the anti-fake region from the candidate region.
Further, it carries out testing pseudo- comparison using the ink feature information extracted, testing pseudo- comparison process includes: by institute
It states ink feature information validation template corresponding with the pre-stored ink label to be compared, when comparing successfully, then
Puppet is tested to pass through；Do not pass through conversely, testing puppet.
Further, it carries out testing pseudo- comparison using the ink feature information extracted, testing pseudo- comparison process includes: by institute
It states ink feature information validation template corresponding with the pre-stored ink label to be compared, when comparing successfully and meet
When the color change rule, then tests puppet and pass through；Do not pass through conversely, testing puppet.
The second object of the present invention is that pseudo-device is tested in the identification for providing a kind of ink label, passes through the oil of ink label
Black pattern and laser pattern carry out identifying processing and verifying respectively, to carry out testing puppet to commodity.
The second object of the present invention is implemented with the following technical solutions:
Pseudo-device is tested in a kind of identification of ink label comprising:
Image collection module identifies with extract oil the ink label image for obtaining ink label image
Black characteristic information；
Pseudo- module is tested, for obtaining validation template, the ink feature information and validation template is subjected to aspect ratio pair, obtained
To feature comparison result；
As a result output module, for testing pseudo- result as a result, returning according to the aspect ratio pair.
The third object of the present invention is to provide the electronic equipment for executing one of goal of the invention comprising processor, storage
Medium and computer program, the computer program are stored in storage medium, and the computer program is executed by processor
Fake method is tested in the identification of Shi Shixian above-mentioned ink label.
The fourth object of the present invention is to provide the computer readable storage medium of one of storage goal of the invention, store thereon
There is computer program, the computer program realizes that fake method is tested in the identification of above-mentioned ink label when being executed by processor.
Compared with prior art, the beneficial effects of the present invention are:
The present invention is by identifying the ink feature in ink label and feature extraction, the ink that will finally extract
Characteristic information is compared with validation template predetermined, so as to complete the verifying to ink label, to realize that product is tested
Puppet, and then achieve the purpose that safeguard consumer's interests, when the ink label to the radium-shine figure layer of superposition carries out identification and feature extraction
When, it will also extract radium-shine characteristic information and be compared with validation template, be able to achieve and different types of ink label is identified
Test puppet.
Detailed description of the invention
Fig. 1 is that the flow chart of fake method is tested in the identification of ink label of the present invention；
Fig. 2 is that the flow chart of fake method is tested in the identification of the ink label of embodiment 2；
Fig. 3 is that the structural block diagram of pseudo-device is tested in the identification of the ink label of embodiment 3；
Fig. 4 is the structural block diagram of the electronic equipment of embodiment 4.
Specific embodiment
Below with reference to attached drawing, the present invention is described in more detail, it should be noted that lower reference attached drawing is to this
The description that invention carries out is only illustrative, and not restrictive.It can be combined with each other between each difference embodiment, with
Constitute the other embodiments not shown in the following description.
Embodiment 1
Fake method is tested in the identification for present embodiments providing a kind of ink label, it is intended to by acquiring ink label image, so
Ink label image is identified afterwards, realizes that ink feature extracts, and the ink feature extracted is tested with predetermined
Card template is compared, to complete the identification and verifying of ink label, wherein describe ink feature using binary number, into
When row ink feature compares, it is only necessary to can complete to verify than logarithm, therefore the expense that comparison process is spent is small.
Based on principles above, as shown in Figure 1, fake method is tested in a kind of identification of ink label comprising following steps:
Ink label image is obtained, the ink label image is identified to extract ink characteristic information；
Validation template is obtained, the ink feature information and validation template are subjected to aspect ratio pair, obtain aspect ratio to knot
Fruit；
Pseudo- result is tested as a result, returning according to the aspect ratio pair.
The present embodiment carries out identification to the ink label of no radium-shine figure layer of superposition and tests puppet, which includes ink area
Domain and non-ink region, the ink feature information that need to only extract the ink label carry out aspect ratio pair.
The ink label image that the embodiment of the present invention uses camera directly to acquire can also carry out ink label real
When scan, the scan video of ink label is obtained, if extracting to obtain dry ink label image, In to the frame of the scan video
Subsequent identification and feature extraction are carried out to ink label image.The frame of scan video is extracted, using MATLAB to scanning
Video is read out, and it is isolated then to carry out image.
Preferably, validation template, the unique identification of the ink label are obtained by the unique identification of ink label are as follows: with
The bar code information of the validation template binding of ink label or the tag number of ink label.
In other embodiments of the present invention, realize that validation template obtains using the bar code used with ink tag match, it should
Bar code uses one-dimension code or two dimensional code to carry out data storage, by taking two dimensional code as an example, obtains two dimension by the identification to two dimensional code
Code information, the two-dimensional barcode information are the unique identification of the ink label, and the two-dimensional barcode information and the validation template of ink label are pre-
First bind；Validation template is obtained from server according to two-dimensional barcode information and is used for aspect ratio pair, then acquires ink label image, it is right
After ink label image carries out identification and feature information extraction, this feature information is compared with validation template, according to comparison
As a result, obtaining testing puppet as a result, carrying out testing pseudo- comparison using the ink feature information extracted, testing pseudo- comparison process includes:
Ink feature information validation template corresponding with the pre-stored ink label is compared, when comparing successfully
When, then it tests puppet and passes through；Do not pass through conversely, testing puppet.In other embodiments of the invention, if comparing successfully, it is logical to return to verifying
It crosses, and returns to the merchandise news using the ink label, realization traces to the source to commodity.
In another embodiment of the invention, the unique identification of ink label is the tag number printed on ink label, right
When ink label image is identified, the tag number in ink label image is extracted by OCR technique, in addition to this it is possible to
Simulation identification is carried out using MATLAB removal ink label image, mark is extracted by binaryzation, character normalization, template matching algorithm
Sign, then validation template is obtained by tag number.
The ink tag recognition that the present embodiment proposes, which tests fake method, can apply in terminal or server, which includes
But it is not limited to mobile phone, tablet computer etc. and can be carried out the electronic product of video acquisition, Image Acquisition and network transmission, make at the terminal
When testing fake method with the ink tag recognition, image recognition is carried out after directly acquiring ink label image by terminal, to mention
Take the characteristic information of ink label, then obtain validation template from database and be compared with characteristic information, obtain testing puppet as a result,
It is displayed on the terminals that pseudo- result will be tested.When testing fake method using the ink tag recognition on the server, server is from verifying end
Image recognition is carried out after obtaining ink label image, to extract the characteristic information of ink label, then from the number of server itself
It is compared according to validation template is obtained in library with characteristic information, will obtain testing pseudo- result return verifying end and show.
If server obtains ink label image by obtaining the video flowing of ink label from verifying end, when server connects
After the unique identification for receiving ink label, after sending video stream pushing URL to verifying end, verifying end passes through the monitoring of RTMP agreement
Thread creation plug-flow thread to acquire real-time ink tag scan video by plug-flow thread, and is pushed to video stream pushing
URL, server end pull corresponding Video stream information from video flowing URL, and the frame of the Video stream information is taken to be converted to ink
Label image.
Preferably, the ink label image is identified to extract the specific steps of ink characteristic information and be situated between
It continues, comprising:
The ink label image is pre-processed, according to figure location feature, from the pretreated ink mark
The position that positioning pattern is determined in image is signed,
According to the position of target signature and the positioning pattern, anti-fake region is determined；
The anti-fake region is corrected by affine transformation；
Anti-fake region after correction is subjected to binary conversion treatment, obtains binary map；
The binary map is divided into several piecemeals, the size of these piecemeals can be equal, can not also wait.It calculates each
The value of piecemeal is set to 0 if the accounting is greater than threshold value by the accounting of ink in piecemeal, otherwise is set to 1；By described several points
The value of block is combined into binary number in order, and the binary number is ink feature information.It is understood that binary map is drawn
Point block count it is more, obtained binary number is also more, and when comparison is also more accurate.
In the present embodiment, pretreated operation is carried out to the ink label image are as follows: utilize ink label image
MATLAB function rgb2gray () is converted to gray level image.Edge detection is carried out to pretreated ink label image, is used
MATLAB edge detection operator realize, edge detection algorithm can be selected Sobel operator, Canny operator, Prewitt operator,
Roberts operator, Laplacian operator etc..
The position that gray scale discontinuously changes can be positioned by edge detection, to obtain anti-fake figure in ink label image
The boundary line of case and background.According to positioning pattern feature, positioning pattern is obtained in the ink label image after edge detection
Position.
The position of obtained positioning pattern is obtained into candidate anti-fake region by permutation and combination, is screened further according to target signature
Anti-fake region out is corrected the anti-fake region by affine transformation, so that the anti-fake region is standard rectangular, so as to
Carry out subsequent feature information extraction.
Wherein above-mentioned target signature and positioning pattern feature are the standard feature in anti-fake region predetermined, as from
The reference standard that anti-fake region is extracted in ink label determines anti-fake region using the standard feature when puppet is tested in identification.
When the unique identification of ink label is two-dimensional barcode information, 3 on two dimensional code can be utilized to the positioning of ink label
A " time " type region has determining black and white interval as positioning pattern feature, according to the multiple continuous black and white intervals of combination
Distance obtains the specific location of positioning pattern, and the sample mode that the position of positioning pattern obtained above do not put back to carries out
Permutation and combination, to obtain candidate anti-fake region.
Because the ink feature information extracted is binary number, when carrying out ink feature comparison, numerical value need to be only carried out
It compares, does not need the concrete shape to inked areas, size and distribution and extract, operation is simpler, can reduce ink spy
The technology complexity extracted is levied, the overhead generated in comparison process is small.
Anti-fake region after correction is subjected to self-adaption binaryzation using Binarization methods, a threshold value is taken, will be greater than threshold
The pixel value 1 of value is displayed in white, and the pixel for being less than threshold value is assigned a value of 0 naturally and is shown as black.Therefore at this
In binary map in embodiment by self-adaption binaryzation processing, inked areas is indicated with 0, and non-ink region is indicated with 1.
In self-adaption binaryzation, the quality that this threshold value determines directly influences effect.Simplest threshold value determination is
It is rounded the mean value mean of width picture, naturally it is also possible to select other algorithms to go to determine the threshold value of self-adaption binaryzation, such as be based on
The adaptive threshold of Wall algorithm, basic considering carefully exactly traverse image, a mobile average value are calculated, if some pixel
Significantly it is lower than this average value, then is set as black, is otherwise provided as white.
Embodiment 2
The present embodiment and above-described embodiment the difference is that, knowledge of this example to the ink label for being superimposed radium-shine figure layer
It does not test fake method to be introduced, as shown in Fig. 2, its step includes:
Ink label image is obtained, the ink label image is identified to extract ink characteristic information；
Validation template is obtained, the ink feature information and the validation template are subjected to aspect ratio pair, obtain aspect ratio
To result；
The color change for analyzing ink label image described in multiframe, judges whether the color change meets the ink mark
The color change rule of label, obtains judging result；
According to the feature comparison result and the judging result, pseudo- result is tested in return.
Wherein, the ink label image is identified to extract the specific steps packet of its extraction of ink characteristic information
It includes:
The ink label image is pre-processed, according to figure location feature, from the pretreated ink mark
The position that positioning pattern is determined in image is signed,
According to the position of target signature and the positioning pattern, anti-fake region is determined；
The anti-fake region is corrected by affine transformation；
Anti-fake region after correction is subjected to binary conversion treatment, obtains binary map；
The binary map is drawn and is divided into several piecemeals, the accounting of ink in each piecemeal is calculated, if the accounting is greater than
The value of piecemeal is then set to 0 by threshold value, otherwise is set to 1；The value of several piecemeals is combined into binary number in order, it is described
Binary number is ink feature information.
The color change for analyzing ink label image described in multiframe, judges whether the color change meets the ink mark
The color change rule of label, obtains judging result, the specific steps are that:
Ink label image described in multiframe is obtained, the ink label image is converted into HSV color space；
The HSV color space of ink label image described in multiframe is recorded, is analyzed each in ink label image described in multiframe
The color change of pixel,
When the pixel quantity of the color change and distribution meet the condition of setting, then meet the face of the ink label
Discoloration law, conversely, not meeting then；
Wherein, pass through color change described in VIBE algorithm, mixed Gauss model or deep learning model analysis.
Ink label in the present embodiment is formed by ink figure layer and radium-shine map overlay, which includes ink area
Domain and radium-shine region, therefore in the binary map that is handled by self-adaption binaryzation of the present embodiment, inked areas is indicated with 0,
Radium-shine region is indicated with 1.
In other embodiments of the invention, the ink label image can also be converted to cmyk color space, HSL
Then color space or HSB color space analyze color change of each pixel in the ink label image described in multiframe again.
The present embodiment analyzes color change of each pixel in multiframe ink label image, using deep learning
Model summarizes the color change of ink label image described in multiframe, specifically selects CNN (convolutional neural networks)+LSTM (shot and long term
Memory network) deep learning model summarize the ink label image color change it is regular (color change feature), when the face
When color change feature meets the condition of setting, then it is judged to meeting, otherwise does not meet, the condition set is according to actual conditions
Customized, the condition of the setting can be customized respective threshold, that is, realizes and passed through using CNN+LSTM deep learning model
Training is regular (radium-shine rule) come the color change for judging the true and false of ink label to get ink label is arrived.
CNN+LSTM deep learning model be machine learning model, be computer be based on sample data carry out rote learning,
Learning from instruction, analogical learning or event selection etc. obtain corresponding relational model.Sample data is more, what machine learning obtained
Relational model is also more accurate, i.e., summarizes in this example and obtain the color change rule meeting of radium-shine material used in ink label
More acurrate, the changing rule of radium-shine material is obtained by successive ignition training, therefore the ink label figure that the present invention obtains
The frame number of picture is more (quantity is more), and the color change feature for obtaining ink label by study summary is more accurate.Utilize CNN+
LSTM carries out the common knowledge that model training is the art, its specific training process is not described in detail herein.
Preferably, carry out testing pseudo- comparison using the ink feature information extracted, test pseudo- comparison process include: will be described
Ink feature information validation template corresponding with the pre-stored ink label is compared, when comparing successfully and meet institute
When stating color change rule, then tests puppet and pass through；Do not pass through conversely, testing puppet.I.e. to ink label carry out identification test puppet after, will return
It returns to test puppet and pass through and test and pseudo- does not test pseudo- result by two kinds.In other embodiments of the invention, when comparing successfully and meet institute
When stating color change rule, return test it is pseudo- pass through as a result, and return to the product informations of the commodity using the ink label, realizing
Realize that commodity are traced to the source while commodity test puppet.The binary number of the ink distribution of ink label described herein, quantity and ink
The binary number of characteristic information is equal, and the piecemeal (size and number) and sortord that divide are completely corresponding.
The ink label referred in above-described embodiment 1 and embodiment 2 has substrate, diffusion layer, the tool of multiple and different patterns
There is the ink layer of random contraction picture and text, diffusion layer is located on substrate, and ink layer is located on diffusion layer.The substrate can be laser card
Paper.The color of ink layer can be black or other are colored.Above-mentioned substrate can also be the adhesive sticker substrate comprising radium-shine paper jam, lead to
It crosses and diffusion coating is set on having figuratum substrate, and setting has the ink layer of random contraction pattern on diffusion coating,
The position covered by ink is presented ink and shrinks picture and text, and radium-shine shading and/or pattern is presented in the position not covered by ink.Also
It is to say, is not leaked out at random by the radium-shine texture that ink covers and reached randomness, while the different depths and different colours radium are presented
The random features for penetrating texture, be formed by structure assemblage characteristic be structure three-dimensional, it is three-dimensional, unique, not reproducible
Physical security.
Following characteristics are presented in above-mentioned ink label: the substrate with a variety of different patterns combines the ink with random picture and text
Layer, randomness is strong, and repetitive rate is extremely low；The antifalsification label that ink is formed after shrinking, there is concave-convex sense, has three-dimensional random feature, increases
Added it is physical, the advantages that and forming dynamic change by radium-shine shading, can not be forged by the way of duplicating.On radium-shine paper jam
The color of a variety of different patterns and laser card hard copy under light, make it have 3 D stereo random character and four-dimensional dynamic with
Machine feature, increased dynamic change overcome the Random Graph of no dynamic change so that running off the pattern come cannot achieve forgery
Case is easy to duplicate forgery by the modes such as take pictures.The ink label that the present invention refers to is difficult to duplicate, that is, increases behavioral characteristics
Afterwards, it is difficult to which imitated, four-dimensional random code considerably increases imitation difficulty.
Embodiment 3
Present embodiment discloses a kind of identifications of the ink label of corresponding above-described embodiment to test the corresponding device of fake method, is
The virtual device structure of above-described embodiment, shown referring to figure 3., pseudo-device is tested in the identification of ink label, comprising:
Image collection module 310 identifies to extract the ink label image for obtaining ink label image
Ink feature information and radium-shine characteristic information；
Pseudo- module 320 is tested, for obtaining validation template, the ink feature information and the radium-shine characteristic information are distinguished
Aspect ratio pair is carried out with validation template, obtains feature comparison result；
As a result output module 330, for testing pseudo- result as a result, returning according to the aspect ratio pair.
Preferably, the validation template is the ink feature information of inked areas in above-mentioned ink label.To the oil
When black label image is identified, anti-fake region is carried out using the figure location feature and target signature of ink label and is determined, really
Carry out feature extraction again behind fixed anti-fake region, the figure location feature and target signature it is pre-defined after stored.Using testing
Card template carries out aspect ratio pair with the ink feature information extracted respectively, to complete the puppet of testing of ink label, and then judges
The true and false of commodity.
When ink label is formed by ink figure layer and radium-shine map overlay, tests in pseudo- module 320 at this, will also analyze
The color change of ink label image described in multiframe, judges whether the color change meets the color change of the ink label
Rule obtains judging result, that is, judges whether the color change rule for meeting the ink label.
If aspect ratio is to success and meets the color change rule of ink label, return test it is pseudo- pass through as a result, simultaneously
Return is shown using the product information of the commodity of the ink label, realizes that commodity are traced to the source；Conversely, return test it is pseudo- unacceptable
As a result.
Embodiment 4
Fig. 4 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention 4 provides, as shown in figure 4, the electronic equipment
Including processor 410, memory 420, input unit 430 and output device 440；The quantity of processor 410 in computer equipment
It can be one or more, in Fig. 4 by taking a processor 410 as an example；It is processor 410, memory 420 in electronic equipment, defeated
Entering device 430 can be connected with output device 440 by bus or other modes, in Fig. 4 for being connected by bus.
Memory 420 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, as the identification of the ink label in the embodiment of the present invention test the corresponding program instruction/module of fake method (for example,
Image collection module 310 that the identification of ink label is tested in pseudo-device tests pseudo- module 320 and result output module 330).Processing
Software program, instruction and the module that device 410 is stored in memory 420 by operation, thereby executing the various of electronic equipment
Fake method is tested in the identification of functional application and data processing, i.e. realization above-described embodiment 1 and the ink label of embodiment 2.
Memory 420 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 420 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 420 can be into one
Step includes the memory remotely located relative to processor 410, these remote memories can be set by network connection to electronics
It is standby.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 430 can be used for receiving ink label image or unique identification of ink label of input etc..Output dress
Setting 440 may include that display screen etc. shows equipment.
Embodiment 5
The embodiment of the present invention 5 also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction tests fake method for executing the identification of ink label when being executed by computer processor, this method comprises:
Ink label image is obtained, the ink label image is identified to extract ink characteristic information and radium-shine spy
Reference breath；
Validation template is obtained, the ink feature information and the radium-shine characteristic information are carried out with validation template respectively special
Sign compares, and obtains feature comparison result；
Pseudo- result is tested as a result, returning according to the aspect ratio pair.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above can also be performed provided by any embodiment of the invention based on ink
The relevant operation in fake method is tested in the identification of label.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions use so that an electronic equipment
(can be mobile phone, personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, the above-mentioned identification based on ink label is tested in the embodiment of fake method device, included is each
A unit and module are only divided according to the functional logic, but are not limited to the above division, as long as can be realized phase
The function of answering；In addition, the specific name of each functional unit is also only for convenience of distinguishing each other, it is not limited to this hair
Bright protection scope.
It will be apparent to those skilled in the art that can make various other according to the above description of the technical scheme and ideas
Corresponding change and deformation, and all these changes and deformation all should belong to the protection scope of the claims in the present invention
Within.
Claims (10)
1. fake method is tested in a kind of identification of ink label, which comprises the following steps:
Ink label image is obtained, the ink label image is identified to extract ink characteristic information；
Validation template is obtained, the ink feature information and validation template are subjected to aspect ratio pair, obtain feature comparison result；
Pseudo- result is tested as a result, returning according to the aspect ratio pair.
2. fake method is tested in the identification of ink label as described in claim 1, which is characterized in that pass through unique mark of ink label
Know and obtain validation template, the unique identification of the ink label are as follows: the bar code information bound with the validation template of ink label or
The tag number of ink label.
3. fake method is tested in the identification of ink label as described in claim 1, which is characterized in that the ink label image into
To extract ink characteristic information, specific extraction step includes: for row identification
The ink label image is pre-processed, according to figure location feature, from the pretreated ink label figure
The position of positioning pattern is determined as in,
According to the position of target signature and the positioning pattern, anti-fake region is determined；
The anti-fake region is corrected by affine transformation；
Anti-fake region after correction is subjected to binary conversion treatment, obtains binary map；
The binary map is divided into several piecemeals, calculates the accounting of ink in each piecemeal, if the accounting is greater than or equal to
The value of piecemeal is then set to 0 by threshold value, otherwise is set to 1；The value of several piecemeals is combined into binary number in order, it is described
Binary number is ink feature information.
4. fake method is tested in the identification of ink label as claimed in claim 3, which is characterized in that when ink label includes radium-shine figure
When layer, the color change of the ink label image is also analyzed, to judge whether the color change rule for meeting the ink label
Rule comprising following steps:
Ink label image described in multiframe is obtained, the ink label image is converted into HSV color space；
The HSV color space of ink label image described in multiframe is recorded, each pixel in ink label image described in multiframe is analyzed
Color change, when the pixel quantity of the color change and distribution meet setting condition when, then meet the ink label
Color change rule, conversely, not meeting then；
Wherein, pass through color change described in VIBE algorithm, mixed Gauss model or deep learning model analysis.
5. fake method is tested in the identification of ink label as claimed in claim 3, which is characterized in that by being positioned described in permutation and combination
The position of figure forms candidate anti-fake region, and the anti-fake region is determined from the candidate region further according to target signature.
6. fake method is tested in the identification of ink label as claimed in claim 3, which is characterized in that utilize the ink feature extracted
Information carries out testing pseudo- comparison, and testing pseudo- comparison process includes: by the ink feature information and the pre-stored ink mark
It signs corresponding validation template to be compared, when comparing successfully, then tests puppet and pass through；Do not pass through conversely, testing puppet.
7. fake method is tested in the identification of ink label as claimed in claim 4, which is characterized in that utilize the ink feature extracted
Information carries out testing pseudo- comparison, and testing pseudo- comparison process includes: by the ink feature information and the pre-stored ink mark
It signs corresponding validation template to be compared, when comparing successfully and meeting the color change rule, then tests puppet and pass through；Conversely,
Puppet is tested not pass through.
8. pseudo-device is tested in a kind of identification of ink label, characterized in that it comprises:
Image collection module identifies the ink label image for obtaining ink label image to extract ink spy
Reference breath；
Pseudo- module is tested, for obtaining validation template, the ink feature information and validation template is subjected to aspect ratio pair, obtain spy
Levy comparison result；
As a result output module, for testing pseudo- result as a result, returning according to the aspect ratio pair.
9. a kind of electronic equipment comprising processor, storage medium and computer program, the computer program are stored in
In storage media, which is characterized in that realize that claim 1 to 7 is described in any item when the computer program is executed by processor
Fake method is tested in the identification of ink label.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Realize that fake method is tested in the identification of the described in any item ink labels of claim 1 to 7 when being executed by processor.
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 true CN110533704A (en) | 2019-12-03 |
| CN110533704B 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) |
Cited By (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 |
| CN115423771A (en) * | 2022-09-01 | 2022-12-02 | 西安电子科技大学 | Quasi-dynamic laser anti-counterfeit label identification method based on characteristic inconsistency |
Citations (19)
| 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 |
| CN1452034A (en) * | 2002-04-15 | 2003-10-29 | 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 |
| 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 |
| CN102663961A (en) * | 2012-03-21 | 2012-09-12 | 杜浩燕 | Fabrication method for anti-counterfeiting film, tag of anti-counterfeiting film, anti-counterfeiting tag and anti-counterfeiting system |
| CN103426014A (en) * | 2013-07-12 | 2013-12-04 | 天津科技大学 | Anti-counterfeiting method of print pictures based on CCD detection |
| CN103559473A (en) * | 2013-10-28 | 2014-02-05 | 汝思商务咨询（上海）有限公司 | Method and system using feature images to achieve printing stock security |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| US20180121933A1 (en) * | 2016-10-28 | 2018-05-03 | Dande Image Master Co., Ltd., Zhuhai | Inspection system and inspection method for commodity uniqueness confirmation |
| 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 |
| CN109929270A (en) * | 2019-03-29 | 2019-06-25 | 东莞市斯缤克化工科技有限公司 | A kind of material and preparation method thereof changed with temperature-sensitive with optics changeable colors along with angle |
-
2019
- 2019-07-22 CN CN201910663611.7A patent/CN110533704B/en active Active
Patent Citations (19)
| 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 |
| CN1452034A (en) * | 2002-04-15 | 2003-10-29 | 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 |
| 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 |
| CN102663961A (en) * | 2012-03-21 | 2012-09-12 | 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 |
| CN103559473A (en) * | 2013-10-28 | 2014-02-05 | 汝思商务咨询（上海）有限公司 | Method and system using feature images to achieve printing stock security |
| 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 |
| 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 |
| US20180121933A1 (en) * | 2016-10-28 | 2018-05-03 | Dande Image Master Co., Ltd., Zhuhai | Inspection system and inspection method for commodity uniqueness confirmation |
| 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 |
| 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 |
| 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 |
| 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 |
| CN109929270A (en) * | 2019-03-29 | 2019-06-25 | 东莞市斯缤克化工科技有限公司 | A kind of material and preparation method thereof changed with temperature-sensitive with optics changeable colors along with angle |
Non-Patent Citations (3)
| Title |
|---|
| YANG LIU 等: "Inkjet-printed unclonable quantum dot fluorescent anti-counterfeiting labels with artificial intelligence authentication", 《NATURE COMMUNICATIONS》 * |
| 任龙飞: "光学水印半色调信息隐藏防伪技术研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
| 张耀天 等: "基于 CNN+LSTM 的空间目标识别", 《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》 * |
Cited By (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 |
| CN115423771A (en) * | 2022-09-01 | 2022-12-02 | 西安电子科技大学 | Quasi-dynamic laser anti-counterfeit label identification method based on characteristic inconsistency |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533704B (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190236614A1 (en) | Artificial intelligence counterfeit 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 | |
| Gebhardt et al. | Document authentication using printing technique features and unsupervised anomaly detection | |
| CN108291876A (en) | System and method for the authenticity for detecting product | |
| CN110533704A (en) | Fake method, device, equipment and medium are tested in the identification of ink label | |
| CN110428028B (en) | Identification and verification method, device, equipment and medium based on quasi-dynamic laser label | |
| US7840028B2 (en) | Authentication system and method | |
| CN102292700A (en) | System and method for enhancing security printing | |
| CN106056183B (en) | The printed medium of printing press readable image and the system and method for scanning the image | |
| Castelblanco et al. | Machine learning techniques for identity document verification in uncontrolled environments: A case study | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN106815731A (en) | A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings | |
| CN109784384B (en) | Method and device for automatically distinguishing authenticity of trademark | |
| CN113435219B (en) | Anti-counterfeiting detection method and device, electronic equipment and storage medium | |
| CN111160331A (en) | Anti-counterfeit label authentication method, device, medium and template graph generation method | |
| CN113392664B (en) | Anti-counterfeiting two-dimensional code generation method, anti-counterfeiting method and device | |
| CN108921006B (en) | Method for establishing handwritten signature image authenticity identification model and authenticity identification method | |
| Taran et al. | PharmaPack: mobile fine-grained recognition of pharma packages | |
| CN113688650B (en) | Method and device for identifying picture | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| CN110443623A (en) | Fake method, device, equipment and medium are tested in identification for antifalsification label | |
| CN110428264A (en) | Fake method, device, equipment and medium are tested in identification based on dot matrix screen antifalsification label | |
| Khuspe et al. | Robust image forgery localization and recognition in copy-move using bag of features and SVM | |
| Hauri | Detecting signatures in scanned document images | |
| US20220129914A1 (en) | Method for verifying product authenticity and establishing authorized product data with fabric features |
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 |