CN106815731A - A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings - Google Patents
A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings Download PDFInfo
- Publication number
- CN106815731A CN106815731A CN201611225276.5A CN201611225276A CN106815731A CN 106815731 A CN106815731 A CN 106815731A CN 201611225276 A CN201611225276 A CN 201611225276A CN 106815731 A CN106815731 A CN 106815731A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- antifalsification label
- label
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000003550 marker Substances 0.000 claims abstract description 10
- 238000010200 validation analysis Methods 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 239000007788 liquid Substances 0.000 claims description 7
- 239000003973 paint Substances 0.000 claims description 7
- 238000001035 drying Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000007711 solidification Methods 0.000 claims description 3
- 230000008023 solidification Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 238000012795 verification Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 12
- 239000000463 material Substances 0.000 description 6
- 239000000049 pigment Substances 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- -1 watercolor Substances 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
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
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Editing Of Facsimile Originals (AREA)
Abstract
The invention discloses a kind of label anti-counterfeit system and method based on SURF Image Feature Matchings, including：Antifalsification label, Front End Authentication module, labeled marker module and Back End Authentication module；The antifalsification label includes security pattern and data medium, and security pattern is made using randomness principle, it is ensured that antifalsification label cannot be by batch duplicating and manufacture difficulty is relatively low, the characteristic information of record security pattern in data medium；In the Front End Authentication module extract real-time antifalsification label preserve characteristic information and carry out automation matching checking；The labeled marker module completes the making of above-mentioned antifalsification label, and backup label details；The Back End Authentication module makes full use of the data backed up in server to ensure the accuracy of label anti-counterfeit checking.The imitated economic loss brought of label batch can be effectively reduced, and fake certification program is simplified by a set of automatic Verification system, while providing various checking means ensures that fake certification reliable results are errorless.
Description
Technical field
It is anti-more particularly, to a kind of label based on SURF Image Feature Matchings the invention belongs to field of anti-counterfeit technology
Antiforge system and method.
Background technology
Antifalsification label is to paste, print, shifting in product surface, the mark with anti-fake effect.Consumer can lead to
Antifalsification label is crossed to judge the true and false of product.In order to ensure the reliability of antifalsification label, at present mainly by following several ways
Realize：
(1) special printing technology is used.Such as laser hologram image technology, safety line embedded technology etc., this kind of technology
Imitated technical threshold is improve, mark cannot be replicated by common printing technology.Such mark has unique vision table
Existing, consumer can recognize easily.But this kind of mark by third part purchase or customization, therefore it cannot be guaranteed that can be pasted
The product for having such mark is exactly certified products.
(2) special paper material is used.For example temperature becomes material, humidity-sensitive material, nuclear track anti-counterfeit material etc., these materials
Qualitative change can occur under specific external condition, and show hiding word or pattern-information.Make undoubtedly in this way
The cost of imitated mark is improved, but inevitably, enterprise also can accordingly be improved using the cost of such mark, thus only be existed
Used on part value product higher, popularization degree is not high.
(3) query formulation digital code anti-false.The number that consumer is identified by phone, short message, internet checking.This scheme
Problem be：On the one hand, simply simply it is printed on mark surface due to digital, it is easy to be imitated；On the other hand, consumer
The participation of inquiry is relatively low.For above-mentioned two problems, current way be by the way of Quick Response Code combination query counts come
Improve reliability.Will during Anti-fake digital recorded Quick Response Code, consumer need to only be scanned under networking state Quick Response Code will from
Dynamic false distinguishing, and by judging the true and false of product in line computation inquiry times.But mark still is possible to be imitated, even if looking into
Asking feedback is first time false distinguishing also or cannot very determine whether product is certified products.
(4) uniqueness characteristic technology is identified.The characteristics of this scheme is mark is possessed some unique features,
Any third party cannot produce the mark with just the same feature.Most commonly texture anti-fake technology, is to pack
Material speckle mark inherently is a kind of anti-counterfeiting technology of anti-counterfeit recognition mark.The speckle of nature always varies
, such as fingerprint, wood grain, bag texture are all random unique.Or artificial texture technology, such as random fibers technology produce
Raw fiber pattern is also unique.Using this principle, the packaging material from clean mark are made anti-counterfeiting mark, and will mark
Knowledge carries out shooting archive, and consumer judges the true and false of mark by these images of Network Capture.This is avoided to a certain extent
The situation that the mark occurred in above-mentioned 3 kinds of modes is imitated, but the making of mark requires high, relatively costly, and consumes
Person must carry out false distinguishing by network.Because textural characteristics details is more, consumer is only difficult to judge mark and achieve with naked eyes
Image whether match completely, false distinguishing result reliability is relatively low.
The content of the invention
For the disadvantages described above or Improvement requirement of prior art, SURF Image Feature Matchings are based on the invention provides one kind
Label anti-counterfeit system and method, its object is to be automatically performed by image processing techniques label the true and false judgement, thus solve
The technical problem that certainly label true and false inquiry operation is more complicated in the prior art and human eye driscrimination error is larger.
To achieve the above object, according to one aspect of the present invention, there is provided a kind of based on SURF Image Feature Matchings
Label anti-counterfeit system, including：Antifalsification label, Back End Authentication module, labeled marker module and Front End Authentication module；
The antifalsification label includes security pattern and data medium, and the data medium preserves the SURF of the security pattern
The exclusive identification code of the coded data of characteristic information and the antifalsification label；
The Back End Authentication module, image and unique mark with the antifalsification label for obtaining the antifalsification label
Know the corresponding target labels image of code, and image and the target labels image to the antifalsification label carries out matching survey
Examination；
The labeled marker module, the making for completing the antifalsification label, and to the correlation letter of the antifalsification label
Breath is backed up, wherein, the relevant information of the antifalsification label includes exclusive identification code, the anti-counterfeiting label of the antifalsification label
The coded data of the SURF characteristic informations of the security pattern in label and meet the antifalsification label image of default resolution ratio；
The Front End Authentication module, for obtain the image of the antifalsification label, the exclusive identification code of the antifalsification label,
The coded data of the SURF characteristic informations of the security pattern and target corresponding with the exclusive identification code of the antifalsification label
Label image, and with reference to selection default Validation Mode carry out automation matching checking, wherein, in the default Validation Mode wrap
Include the Back End Authentication pattern that matching test is carried out using the Back End Authentication module.
Preferably, the Back End Authentication module includes data reception module, data server, images match module and knot
Fruit feedback module；
The data reception module, for obtaining the image of the antifalsification label and the unique mark of the antifalsification label
Code；
The data server, for using the exclusive identification code as index, from the data server inquiry with
The corresponding target labels information of the exclusive identification code, wherein, the target labels information includes target labels image；
Described image matching module, for when the data server finds the target labels image, by the mesh
Mark label image carries out matching test with the image of the antifalsification label；
The result feedback module, for not finding the target labels image or the figure in the data server
When failing as matching module matching test, the prompt message of output matching failure, and match survey in described image matching module
Try when successfully, the successful prompt message of output matching.
Preferably, the labeled marker module includes the endowed module of label, security pattern image processing module, label information
Acquisition module and data transmission module；
The endowed module of label, for distributing exclusive identification code for antifalsification label, and the exclusive identification code of distribution is write
In entering the data medium of the antifalsification label；
The security pattern image processing module, for splitting the security pattern image in the antifalsification label, detects institute
The SURF characteristic points of security pattern image are stated, and the SURF features of the security pattern image are determined using non-maxima suppression method
The position of Partial Feature point and Partial Feature point in point, it is then determined that each feature in Partial Feature point
The principal direction of point describes the SURF characteristic informations of the security pattern image, and the SURF characteristic informations are converted into coding
Data are write in the data medium of the antifalsification label；
The label information acquisition module, for obtaining the relevant information of the antifalsification label, and is integrally formed anti-counterfeiting label
Message file is signed, wherein, the relevant information of the antifalsification label includes that the exclusive identification code of the antifalsification label, the SURF are special
The coded data of reference breath and meet the antifalsification label image of default resolution ratio；
The data transmission module, is carried out for the antifalsification label message file to be sent in the data server
Backup.
Preferably, the Front End Authentication module includes image capture module, carrier data recognition module, data transmit-receive mould
Block, identification module and information feedback module；
Described image acquisition module, for gathering and chooses the image of the less antifalsification label of distortion；
The carrier data distinguishes module, for reading the exclusive identification code and SURF spies that are recorded in the data medium
The coded data CODE of reference breath1；
The data transmit-receive module, for select manpower comparing to pattern when, to the data server requests with it is described
The corresponding target labels information of exclusive identification code, and the target labels image that the target labels information includes is exported, by people
Work determines whether the target labels image matches with the image of the antifalsification label；
The identification module, during for holding Validation Mode before the selection, from the described anti-of described image acquisition module acquisition
Security pattern image is partitioned into the image of pseudo label, and calculates the coded data CODE of the security pattern image that segmentation is obtained2,
Assessment CODE1With CODE2Degree of agreement；
The data transmit-receive module, when being additionally operable to hold Validation Mode after selection, described image acquisition module is obtained
The exclusive identification code that the image of the antifalsification label is obtained with carrier data recognition module is sent to the Back End Authentication mould
The data reception module of block, matching test is carried out by the Back End Authentication module；
Described information feedback module, for being more than predetermined threshold value in degree of agreement or receiving the Back End Authentication module
When sending the prompt message that the match is successful, the successful prompt message of output matching；Default threshold is less than or equal in degree of agreement
When being worth or receive the Back End Authentication module transmission prompt message that it fails to match, the prompting letter of output matching failure
Breath.
Preferably, the security pattern is the solidification stereogram that the random splash of liquid paint is formed several times and after drying
Case.
Preferably, the security pattern image processing module includes image segmentation module, subregion direction determining mould, figure
As direction determining mould, image feature vector determining module, characteristic information describing module and coding information acquisition module：
Described image splits module, identical for the security pattern image in the antifalsification label to be divided into N number of size
Subregion, wherein, N is positive integer；
The subregion direction determining mould, for the principal direction using each sub-regions of statistics with histogram, chooses straight
Peak value direction in square figure as the subregion principal direction, using the weighted average angle in all characteristic point directions as the sub-district
The auxiliary direction in domain obtains the direction character vector of each sub-regions：VSon=[AIt is main,AIt is auxiliary], wherein, AIt is mainIt is principal direction, AIt is auxiliarySupplemented by
Help direction；
Described image direction determining mould, for determine the direction character of the security pattern image in the antifalsification label to
Amount：VPrincipal direction=[AMain 1,…,AMain i,…,AMain n], VAuxiliary direction=[AAuxiliary 1,…,AAuxiliary i,…,AAuxiliary n], wherein, AMain iRepresent i-th subregion
Principal direction, AAuxiliary iRepresent i-th auxiliary direction of subregion；
Described image characteristic vector determining module, the characteristic point quantity for counting each sub-regions obtains described anti-
The quantative attribute vector of the security pattern image in pseudo label：VQuantity=[R1,R2,…,Ri,…,Rn], wherein, Ri=Ni/ N is represented
I-th quantity ratios of subregion characteristic point, NiThe i-th characteristic point quantity of subregion is represented, N represents all effective features
Point quantity；
The characteristic information describing module, for according to vectorial VPrincipal direction、VAuxiliary directionAnd VQuantityCome in describing the antifalsification label
Security pattern image SURF characteristic informations；
The coding information acquisition module, it is described false proof for the SURF characteristic informations to be converted into coded data write-in
In the data medium of label.
Preferably, the identification module includes CODE2Acquisition module, decoder module, the first computing module, second calculate mould
Block, the 3rd computing module and the 4th computing module；
The CODE2Acquisition module, during for holding Validation Mode before the selection, from the institute that described image acquisition module is obtained
Security pattern image is partitioned into the image for stating antifalsification label, and calculates the coded data of the security pattern image that segmentation is obtained
CODE2；
The decoder module, for by CODE1With CODE2Decoding obtains the principal direction characteristic vector of each represented image
VPrincipal direction 1、VPrincipal direction 2, auxiliary direction characteristic vector VAuxiliary direction 1、VAuxiliary direction 2, quantative attribute vector VQuantity 1、VQuantity 2；
First computing module, the Euclidean distance d for calculating principal direction characteristic vector1=| | VPrincipal direction 1-VPrincipal direction 2||；
Second computing module, the Euclidean distance d for calculating auxiliary direction characteristic vector2=| | VAuxiliary direction 1-VAuxiliary direction 2|
|；
3rd computing module, for the Euclidean distance d of number of computations characteristic vector3=| | VQuantity 1-VQuantity 2||；
4th computing module, for calculating CODE1With CODE2Degree of agreement：E=α1*d1+α2*d2+α3*d3, its
In, α1、α2、α3Respectively principal direction parameter, auxiliary directioin parameter, the factor of influence of number parameter.
It is another aspect of this invention to provide that there is provided a kind of label anti-counterfeit method based on SURF Image Feature Matchings, bag
Include：
(1) the false proof figure in image, the exclusive identification code of the antifalsification label, the antifalsification label of antifalsification label is obtained
The coded data of the SURF characteristic informations of case and target labels image corresponding with the exclusive identification code of the antifalsification label, and
Automation matching checking is carried out with reference to the default Validation Mode of selection, wherein, the antifalsification label includes security pattern and data
Carrier, the data medium preserves the coded data and the antifalsification label of the SURF characteristic informations of the security pattern only
One identification code；
(2) if the default Validation Mode of selection is Back End Authentication pattern, image to the antifalsification label and with institute
The corresponding target labels image of exclusive identification code for stating antifalsification label carries out matching test.
Preferably, step (1) specifically includes following sub-step：
(1-1) is gathered and is chosen the image of the less antifalsification label of distortion；
(1-2) reads the coded data of the exclusive identification code and SURF characteristic informations recorded in the data medium
CODE1；
(1-3) if selection manpower comparing to pattern, to data server requests target corresponding with the exclusive identification code
Label information, and the target labels image that the target labels information includes is exported, by manually determining the target labels figure
As whether being matched with the image of the antifalsification label；
(1-4) is partitioned into security pattern image if selecting Front End Authentication pattern from the image of the antifalsification label, and
Calculate the coded data CODE of the security pattern image that segmentation is obtained2, assess CODE1With CODE2Degree of agreement；
(1-5) is if selection Back End Authentication pattern, performs step (2)；
(1-6) is if degree of agreement is more than predetermined threshold value or Back End Authentication success, the successful prompt message of output matching；
(1-7), if degree of agreement fails less than or equal to predetermined threshold value or Back End Authentication, what output matching failed carries
Show information.
Preferably, step (2) specifically includes following sub-step：
(2-1) obtains the image of the antifalsification label and the exclusive identification code of the antifalsification label；
(2-2) inquires about corresponding with the exclusive identification code using the exclusive identification code as index from data server
Target labels information, wherein, the target labels information include target labels image；
(2-3) if finding the target labels image in the data server, by the target labels image with
The image of the antifalsification label carries out matching test；
(2-4) is defeated if not finding the target labels image or matching test failure in the data server
Go out the prompt message that it fails to match；
(2-5) is if matching test success, the successful prompt message of output matching.
In general, there is following skill compared with prior art, mainly by the contemplated above technical scheme of the present invention
Art advantage：
(1) forming label is simple and difficulty is imitated.The security pattern on antifalsification label that the present invention is provided is by liquid paint
Random splash makes, and when liquid paint receives differential pressure splash, the liquid drop movement speed and direction in pigment are different, strike
Plane moment can one way or another ejection, when the complete stop motion of last each drop, form a width splashing effect pattern.Due to
Solids content in pigment drop is also inconsistent, after drying, the shape of the various pieces of pattern, size, concavo-convex degree,
Color depth, distribution of color completely random, and this process is difficult to be reappeared by specific manufacture craft.In different colors, no
Same angle, different number of times carry out the security pattern of splash formation, it is virtually impossible to be imitated.Traditional label batch duplicating printing nothing
Method is with label of the present invention.
(2) characteristic information that the present invention is signed by image processing techniques automatic benchmarking is matched, and the various defeated codes of simplification are looked into
Ask operation.Label also carries the anti-counterfeiting information of coded representation in itself, and checking directly can be completed locally, it is not necessary to by network
Platform.
(3) present invention takes full advantage of the unique and anti-light distorted characteristic of image SURF features, exists with piece image
Can retain main characteristic information under different photographed scenes.Found by human eye by SURF characteristic matchings ratio and compare two width figures
The minutia of picture is more accurate.
(4) complete information of label is have recorded in system of the invention, and there is provided various different Validation Modes, can
It is reliable enough with the result for ensureing checking.
Brief description of the drawings
Fig. 1 shows for a kind of structure of the label anti-counterfeit system based on SURF Image Feature Matchings disclosed in the embodiment of the present invention
It is intended to；
Fig. 2 shows for a kind of flow of the label anti-counterfeit method based on SURF Image Feature Matchings disclosed in the embodiment of the present invention
It is intended to.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as additionally, technical characteristic involved in invention described below each implementation method
Not constituting conflict each other can just be mutually combined.
It is a kind of label anti-counterfeit system based on SURF Image Feature Matchings disclosed in the embodiment of the present invention with reference to shown in Fig. 1
The structural representation of system, wherein, include in the system diagram shown in Fig. 1：Antifalsification label 100, Back End Authentication module 200, label
Sign module 300 and Front End Authentication module 400；
Above-mentioned antifalsification label 100 includes security pattern 101 and data medium 102, and data medium 102 preserves security pattern
The coded data of 101 SURF (Speeded-Up Robust Features) characteristic information and antifalsification label 100 it is unique
Identification code；
Wherein, security pattern 101 is the solidification space pattern that the random splash of liquid paint is formed several times and after drying, liquid
Including pigment, watercolor, oil colour, poster paint, acrylic paints etc., data medium 102 preserves security pattern 101 to state pigment
The coded data of SURF characteristic informations and the exclusive identification code of antifalsification label 100, data medium 102 include Quick Response Code, electronics
Label etc..
Above-mentioned Back End Authentication module 200, for obtaining the image of antifalsification label 100 and unique with antifalsification label 100
The corresponding target labels image of identification code, and image and target labels image to antifalsification label 100 carries out matching test；
Above-mentioned labeled marker module 300, the making for completing antifalsification label, and relevant information to antifalsification label are carried out
Backup, wherein, the relevant information of antifalsification label includes the security pattern in exclusive identification code, the antifalsification label of antifalsification label
The coded data of SURF characteristic informations and meet the antifalsification label image of default resolution ratio；
Above-mentioned Front End Authentication module 400, for obtaining the image of the antifalsification label, exclusive identification code of antifalsification label, false proof
The coded data of the SURF characteristic informations of pattern and target labels image corresponding with the exclusive identification code of antifalsification label, and tie
Closing the default Validation Mode of selection carries out automation matching checking, wherein, using Back End Authentication mould in default Validation Mode
Block 200 carries out the Back End Authentication pattern of matching test.
Preferably, above-mentioned Back End Authentication module 200 includes data reception module 201, data server 202, images match
Module 203 and result feedback module 204；
Above-mentioned data reception module 201, for obtaining the image of antifalsification label 100 and unique mark of antifalsification label 100
Know code；
Above-mentioned data server 202, for using exclusive identification code as index, from data server 202 inquiry with only
The corresponding target labels information of one identification code, wherein, target labels information includes target labels image；
Above-mentioned images match module 203, for when data server 202 finds target labels image, by target labels
Image carries out matching test with the image of antifalsification label 100；
The above results feedback module 204, for not finding target labels image or images match in data server 202
The matching test of module 203 fail when, output matching failure prompt message, and the matching test of images match module 203 into
During work(, the successful prompt message of output matching.
Preferably, above-mentioned labeled marker module 300 includes the endowed module 301 of label, security pattern image processing module
302nd, label information acquisition module 303 and data transmission module 304；
The above-mentioned endowed module 301 of label, for distributing exclusive identification code, and the unique mark that will be distributed for antifalsification label 100
In the data medium 102 of knowledge code write-in antifalsification label 100；
Above-mentioned security pattern image processing module 302, for splitting the security pattern image in antifalsification label 100, detection
The SURF characteristic points of security pattern image, and determine the SURF characteristic points of security pattern image using non-maxima suppression method
The position of Partial Feature point and Partial Feature point, it is then determined that the master of each characteristic point in Partial Feature point
Direction describes the SURF characteristic informations of security pattern image, and SURF characteristic informations are converted into coded data write-in anti-counterfeiting label
In the data medium 102 of label 100；
Above-mentioned label information acquisition module 303, for obtaining the relevant information of antifalsification label 100, and is integrally formed false proof
Label information file, wherein, the relevant information of antifalsification label includes exclusive identification code, the SURF characteristic informations of antifalsification label 100
Coded data and meet the antifalsification label image of default resolution ratio；
Above-mentioned data transmission module 304, for antifalsification label message file is sent in data server 202 carry out it is standby
Part.
Preferably, above-mentioned Front End Authentication module 400 includes image capture module 401, carrier data recognition module 402, number
According to transceiver module 403, identification module 404 and information feedback module 405；
Above-mentioned image capture module 401, for gathering and chooses the image of the less antifalsification label 100 of distortion；
Above-mentioned carrier data distinguishes module 402, for reading the exclusive identification code and SURF that are recorded in data medium 102
The coded data CODE of characteristic information1；
Above-mentioned data transmit-receive module 403, for when selecting manpower comparing to pattern, to the request of data server 202 and only
The corresponding target labels information of one identification code, and the target labels image that target labels information includes is exported, by manually determining
Whether target labels image matches with the image of antifalsification label；
Above-mentioned identification module 404, during for holding Validation Mode before the selection, from the false proof of the acquisition of image capture module 401
Security pattern image is partitioned into the image of label 100, and calculates the coded data of the security pattern image that segmentation is obtained
CODE2, assess CODE1With CODE2Degree of agreement；
Above-mentioned data transmit-receive module 403, when being additionally operable to hold Validation Mode after selection, image capture module 401 is obtained
The exclusive identification code that obtains of image and carrier data recognition module 402 of antifalsification label 100 send to Back End Authentication module 200
Data reception module 201, matching test is carried out by Back End Authentication module 200；
Above- mentioned information feedback module 404, for being more than predetermined threshold value in degree of agreement or receiving Back End Authentication module
During the 200 transmission prompt message that the match is successful, the successful prompt message of output matching；In degree of agreement less than or equal to default
Threshold value or when receiving Back End Authentication module 200 and sending the prompt message that it fails to match, the prompting letter of output matching failure
Breath.
Preferably, above-mentioned security pattern image processing module 302 includes that image segmentation module, subregion direction determine mould
Block, image direction determining module, image feature vector determining module, characteristic information describing module and coding information obtain mould
Block：
Above-mentioned image segmentation module, for the security pattern image in antifalsification label 100 to be divided into N number of size identical
Subregion, wherein, N is positive integer；
Above-mentioned subregion direction determining mould, for the principal direction using each sub-regions of statistics with histogram, chooses straight
Peak value direction in square figure as the subregion principal direction, using the weighted average angle in all characteristic point directions as the sub-district
The auxiliary direction in domain obtains the direction character vector of each sub-regions：VSon=[AIt is main,AIt is auxiliary], wherein, AIt is mainIt is principal direction, AIt is auxiliarySupplemented by
Help direction；
Above-mentioned image direction determining module, for determine the direction character of the security pattern image in antifalsification label 100 to
Amount：VPrincipal direction=[AMain 1,…,AMain i,…,AMain n], VAuxiliary direction=[AAuxiliary 1,…,AAuxiliary i,…,AAuxiliary n], wherein, AMain iRepresent i-th subregion
Principal direction, AAuxiliary iRepresent i-th auxiliary direction of subregion；
Above-mentioned image feature vector determining module, the characteristic point quantity for counting each sub-regions, obtains anti-counterfeiting label
Sign the quantative attribute vector of the security pattern image in 100：VQuantity=[R1,R2,…,Ri,…,Rn], wherein, Ri=Ni/ N is represented
I-th quantity ratios of subregion characteristic point, NiThe i-th characteristic point quantity of subregion is represented, N represents all effective features
Point quantity；
Features described above information describing module, for according to vectorial VPrincipal direction、VAuxiliary directionAnd VQuantityCome in describing antifalsification label 100
Security pattern image SURF characteristic informations；
Above-mentioned coding information acquisition module, for SURF characteristic informations to be converted into coded data write-in antifalsification label 100
Data medium 102 in.
Preferably, above-mentioned identification module 404 includes CODE2Acquisition module, decoder module, the first computing module, the second meter
Calculate module, the 3rd computing module and the 4th computing module；
Above-mentioned CODE2Acquisition module, during for holding Validation Mode before the selection, from preventing that image capture module 401 is obtained
Security pattern image is partitioned into the image of pseudo label 100, and calculates the coded data of the security pattern image that segmentation is obtained
CODE2；
Above-mentioned decoder module, for by CODE1With CODE2Decoding obtains the principal direction characteristic vector of each represented image
VPrincipal direction 1、VPrincipal direction 2, auxiliary direction characteristic vector VAuxiliary direction 1、VAuxiliary direction 2, quantative attribute vector VQuantity 1、VQuantity 2；
Above-mentioned first computing module, the Euclidean distance d for calculating principal direction characteristic vector1=| | VPrincipal direction 1-VPrincipal direction 2||；
Above-mentioned second computing module, the Euclidean distance d for calculating auxiliary direction characteristic vector2=| | VAuxiliary direction 1-VAuxiliary direction 2|
|；
Above-mentioned 3rd computing module, for the Euclidean distance d of number of computations characteristic vector3=| | VQuantity 1-VQuantity 2||；
Above-mentioned 4th computing module, for calculating CODE1With CODE2Degree of agreement：E=α1*d1+α2*d2+α3*d3, its
In, α1、α2、α3Respectively principal direction parameter, auxiliary directioin parameter, the factor of influence of number parameter.
A kind of label anti-counterfeit method based on SURF Image Feature Matchings with reference to disclosed in Fig. 2 show the embodiment of the present invention
Schematic flow sheet, in the method shown in Fig. 2, comprise the following steps：
(1) the false proof figure in image, the exclusive identification code of the antifalsification label, the antifalsification label of antifalsification label is obtained
The coded data of the SURF characteristic informations of case and target labels image corresponding with the exclusive identification code of the antifalsification label, and
Automation matching checking is carried out with reference to the default Validation Mode of selection, wherein, the antifalsification label includes security pattern and data
Carrier, the data medium preserves the coded data and the antifalsification label of the SURF characteristic informations of the security pattern only
One identification code；
(2) if the default Validation Mode of selection is Back End Authentication pattern, image to the antifalsification label and with institute
The corresponding target labels image of exclusive identification code for stating antifalsification label carries out matching test.
Preferably, step (1) specifically includes following sub-step：
(1-1) is gathered and is chosen the image of the less antifalsification label of distortion；
(1-2) reads the coded data of the exclusive identification code and SURF characteristic informations recorded in the data medium
CODE1；
(1-3) if selection manpower comparing to pattern, to data server requests target corresponding with the exclusive identification code
Label information, and the target labels image that the target labels information includes is exported, by manually determining the target labels figure
As whether being matched with the image of the antifalsification label；
(1-4) is partitioned into security pattern image if selecting Front End Authentication pattern from the image of the antifalsification label, and
Calculate the coded data CODE of the security pattern image that segmentation is obtained2, assess CODE1With CODE2Degree of agreement；
(1-5) is if selection Back End Authentication pattern, performs step (2)；
(1-6) is if degree of agreement is more than predetermined threshold value or Back End Authentication success, the successful prompt message of output matching；
(1-7), if degree of agreement fails less than or equal to predetermined threshold value or Back End Authentication, what output matching failed carries
Show information.
Preferably, step (2) specifically includes following sub-step：
(2-1) obtains the image of the antifalsification label and the exclusive identification code of the antifalsification label；
(2-2) inquires about corresponding with the exclusive identification code using the exclusive identification code as index from data server
Target labels information, wherein, the target labels information include target labels image；
(2-3) if finding the target labels image in the data server, by the target labels image with
The image of the antifalsification label carries out matching test；
(2-4) is defeated if not finding the target labels image or matching test failure in the data server
Go out the prompt message that it fails to match；
(2-5) is if matching test success, the successful prompt message of output matching.
As it will be easily appreciated by one skilled in the art that the foregoing is only presently preferred embodiments of the present invention, it is not used to
The limitation present invention, all any modification, equivalent and improvement made within the spirit and principles in the present invention etc., all should include
Within protection scope of the present invention.
Claims (10)
1. a kind of label anti-counterfeit system based on SURF Image Feature Matchings, it is characterised in that including：Antifalsification label, rear end are tested
Card module, labeled marker module and Front End Authentication module；
The antifalsification label includes security pattern and data medium, and the data medium preserves the SURF features of the security pattern
The exclusive identification code of the coded data of information and the antifalsification label；
The Back End Authentication module, image and exclusive identification code with the antifalsification label for obtaining the antifalsification label
Corresponding target labels image, and image and the target labels image to the antifalsification label carries out matching test；
The labeled marker module, the making for completing the antifalsification label, and relevant information to the antifalsification label are entered
Row backup, wherein, in exclusive identification code, the antifalsification label of the relevant information including the antifalsification label of the antifalsification label
Security pattern SURF characteristic informations coded data and meet the antifalsification label image of default resolution ratio；
The Front End Authentication module, for obtaining the image of the antifalsification label, exclusive identification code of the antifalsification label, described
The coded data of the SURF characteristic informations of security pattern and target labels corresponding with the exclusive identification code of the antifalsification label
Image, and with reference to selection default Validation Mode carry out automation matching checking, wherein, the default Validation Mode includes profit
The Back End Authentication pattern of matching test is carried out with the Back End Authentication module.
2. system according to claim 1, it is characterised in that the Back End Authentication module includes data reception module, number
According to server, images match module and result feedback module；
The data reception module, for obtaining the image of the antifalsification label and the exclusive identification code of the antifalsification label；
The data server, for using the exclusive identification code as index, inquired about from the data server with it is described
The corresponding target labels information of exclusive identification code, wherein, the target labels information includes target labels image；
Described image matching module, for when the data server finds the target labels image, by the target mark
Sign image carries out matching test with the image of the antifalsification label；
The result feedback module, for not finding the target labels image or described image in the data server
When failing with module matching test, output matching failure prompt message, and described image matching module matching test into
During work(, the successful prompt message of output matching.
3. system according to claim 2, it is characterised in that the labeled marker module includes the endowed module of label, anti-
Pseudo- pattern image processing module, label information acquisition module and data transmission module；
The endowed module of label, for distributing exclusive identification code for antifalsification label, and the exclusive identification code that will be distributed writes institute
In stating the data medium of antifalsification label；
The security pattern image processing module, for splitting the security pattern image in the antifalsification label, detects described anti-
The SURF characteristic points of pseudo- pattern image, and using non-maxima suppression method determine the SURF characteristic points of the security pattern image
Partial Feature point and Partial Feature point position, it is then determined that each characteristic point in Partial Feature point
Principal direction describes the SURF characteristic informations of the security pattern image, and the SURF characteristic informations are converted into coded data
In writing the data medium of the antifalsification label；
The label information acquisition module, for obtaining the relevant information of the antifalsification label, and is integrally formed antifalsification label letter
Breath file, wherein, the relevant information of the antifalsification label includes the exclusive identification code of the antifalsification label, SURF features letter
The coded data of breath and meet the antifalsification label image of default resolution ratio；
The data transmission module, for the antifalsification label message file is sent in the data server carry out it is standby
Part.
4. system according to claim 3, it is characterised in that the Front End Authentication module includes image capture module, carries
Volume data recognition module, data transmit-receive module, identification module and information feedback module；
Described image acquisition module, for gathering and chooses the image of the less antifalsification label of distortion；
The carrier data distinguishes module, for reading the exclusive identification code and SURF features letter that are recorded in the data medium
The coded data CODE of breath1；
The data transmit-receive module, it is unique with described to the data server requests for when selecting manpower comparing to pattern
The corresponding target labels information of identification code, and the target labels image that the target labels information includes is exported, by manually determining
Whether the fixed target labels image matches with the image of the antifalsification label；
The identification module, during for holding Validation Mode before the selection, from the anti-counterfeiting label that described image acquisition module is obtained
Security pattern image is partitioned into the image of label, and calculates the coded data CODE of the security pattern image that segmentation is obtained2, assessment
CODE1With CODE2Degree of agreement；
The data transmit-receive module, when being additionally operable to hold Validation Mode after selection, by described in the acquisition of described image acquisition module
The exclusive identification code that the image of antifalsification label is obtained with carrier data recognition module is sent to the Back End Authentication module
Data reception module, matching test is carried out by the Back End Authentication module；
Described information feedback module, sends for being more than predetermined threshold value or receiving the Back End Authentication module in degree of agreement
During the prompt message that the match is successful, the successful prompt message of output matching；Degree of agreement less than or equal to predetermined threshold value or
When person receives the Back End Authentication module transmission prompt message that it fails to match, the prompt message of output matching failure.
5. the system according to Claims 1-4 any one, it is characterised in that the security pattern be liquid paint with
The solidification space pattern that machine splash is formed several times and after drying.
6. system according to claim 3, it is characterised in that the security pattern image processing module includes image segmentation
Module, subregion direction determining mould, image direction determining module, image feature vector determining module, characteristic information describe mould
Block and coding information acquisition module：
Described image splits module, for the security pattern image in the antifalsification label to be divided into N number of size identical
Region, wherein, N is positive integer；
The subregion direction determining mould, for the principal direction using each sub-regions of statistics with histogram, chooses histogram
In peak value direction as the subregion principal direction, using the weighted average angle in all characteristic point directions as the subregion
Auxiliary direction obtains the direction character vector of each sub-regions：VSon=[AIt is main,AIt is auxiliary], wherein, AIt is mainIt is principal direction, AIt is auxiliaryIt is auxiliary square
To；
Described image direction determining mould, the direction character vector for determining the security pattern image in the antifalsification label：
VPrincipal direction=[AMain 1,…,AMain i,…,AMain n], VAuxiliary direction=[AAuxiliary 1,…,AAuxiliary i,…,AAuxiliary n], wherein, AMain iRepresent i-th master of subregion
Direction, AAuxiliary iRepresent i-th auxiliary direction of subregion；
Described image characteristic vector determining module, the characteristic point quantity for counting each sub-regions, obtains the anti-counterfeiting label
The quantative attribute vector of the security pattern image in label：VQuantity=[R1,R2,…,Ri,…,Rn], wherein, Ri=Ni/ N represents i-th
The quantity ratios of sub-regions characteristic point, NiThe i-th characteristic point quantity of subregion is represented, N represents all effective characteristic points
Quantity；
The characteristic information describing module, for according to vectorial VPrincipal direction、VAuxiliary directionAnd VQuantityIt is anti-in the antifalsification label to describe
The SURF characteristic informations of pseudo- pattern image；
The coding information acquisition module, the antifalsification label is write for the SURF characteristic informations to be converted into coded data
Data medium in.
7. system according to claim 4, it is characterised in that the identification module includes CODE2Acquisition module, decoding mould
Block, the first computing module, the second computing module, the 3rd computing module and the 4th computing module；
The CODE2Acquisition module, during for holding Validation Mode before the selection, from the described anti-of described image acquisition module acquisition
Security pattern image is partitioned into the image of pseudo label, and calculates the coded data CODE of the security pattern image that segmentation is obtained2；
The decoder module, for by CODE1With CODE2Decoding obtains the principal direction characteristic vector of each represented image
VPrincipal direction 1、VPrincipal direction 2, auxiliary direction characteristic vector VAuxiliary direction 1、VAuxiliary direction 2, quantative attribute vector VQuantity 1、VQuantity 2；
First computing module, the Euclidean distance d for calculating principal direction characteristic vector1=| | VPrincipal direction 1-VPrincipal direction 2||；
Second computing module, the Euclidean distance d for calculating auxiliary direction characteristic vector2=| | VAuxiliary direction 1-VAuxiliary direction 2||；
3rd computing module, for the Euclidean distance d of number of computations characteristic vector3=| | VQuantity 1-VQuantity 2||；
4th computing module, for calculating CODE1With CODE2Degree of agreement：E=α1*d1+α2*d2+α3*d3, wherein,
α1、α2、α3Respectively principal direction parameter, auxiliary directioin parameter, the factor of influence of number parameter.
8. a kind of label anti-counterfeit method based on SURF Image Feature Matchings, it is characterised in that including：
(1) security pattern in image, the exclusive identification code of the antifalsification label, the antifalsification label of antifalsification label is obtained
The coded data of SURF characteristic informations and target labels image corresponding with the exclusive identification code of the antifalsification label, and combine
The default Validation Mode of selection carries out automation matching checking, wherein, the antifalsification label includes security pattern and data medium,
The data medium preserves the coded data and unique mark of the antifalsification label of the SURF characteristic informations of the security pattern
Know code；
(2) if the default Validation Mode of selection is Back End Authentication pattern, image to the antifalsification label and anti-with described
The corresponding target labels image of exclusive identification code of pseudo label carries out matching test.
9. method according to claim 8, it is characterised in that step (1) specifically includes following sub-step：
(1-1) is gathered and is chosen the image of the less antifalsification label of distortion；
(1-2) reads the coded data CODE of the exclusive identification code and SURF characteristic informations recorded in the data medium1；
(1-3) if selection manpower comparing to pattern, to data server requests target labels corresponding with the exclusive identification code
Information, and export the target labels image that the target labels information includes, by manually determine the target labels image with
Whether the image of the antifalsification label matches；
(1-4) is if selection Front End Authentication pattern, is partitioned into security pattern image, and calculate from the image of the antifalsification label
The coded data CODE of the security pattern image that segmentation is obtained2, assess CODE1With CODE2Degree of agreement；
(1-5) is if selection Back End Authentication pattern, performs step (2)；
(1-6) is if degree of agreement is more than predetermined threshold value or Back End Authentication success, the successful prompt message of output matching；
(1-7), if degree of agreement fails less than or equal to predetermined threshold value or Back End Authentication, the prompting of output matching failure is believed
Breath.
10. method according to claim 9, it is characterised in that step (2) specifically includes following sub-step：
(2-1) obtains the image of the antifalsification label and the exclusive identification code of the antifalsification label；
(2-2) inquires about mesh corresponding with the exclusive identification code using the exclusive identification code as index from data server
Mark label information, wherein, the target labels information includes target labels image；
(2-3) if finding the target labels image in the data server, by the target labels image with it is described
The image of antifalsification label carries out matching test；
(2-4) in the data server if do not find the target labels image or matching test failure, output
Prompt message with failure；
(2-5) is if matching test success, the successful prompt message of output matching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611225276.5A CN106815731A (en) | 2016-12-27 | 2016-12-27 | A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611225276.5A CN106815731A (en) | 2016-12-27 | 2016-12-27 | A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106815731A true CN106815731A (en) | 2017-06-09 |
Family
ID=59110818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611225276.5A Pending CN106815731A (en) | 2016-12-27 | 2016-12-27 | A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815731A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522947A (en) * | 2018-10-31 | 2019-03-26 | 联想(北京)有限公司 | Recognition methods and equipment |
| CN110014763A (en) * | 2019-05-07 | 2019-07-16 | 中山易必固新材料科技有限公司 | A kind of antifalsification label production method and device based on electronic beam curing |
| CN110414586A (en) * | 2019-07-22 | 2019-11-05 | 杭州沃朴物联科技有限公司 | Antifalsification label based on deep learning tests fake method, device, equipment and medium |
| CN111435458A (en) * | 2019-01-11 | 2020-07-21 | 罗伯特·博世有限公司 | Method and apparatus for creating and verifying an anti-counterfeiting mark |
| CN112560989A (en) * | 2020-12-25 | 2021-03-26 | 烟台职业学院 | Artificial intelligence anti-counterfeiting image identification method and system based on big data |
| CN114782796A (en) * | 2022-06-17 | 2022-07-22 | 武汉北大高科软件股份有限公司 | Intelligent verification method and device for article image anti-counterfeiting |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955930A (en) * | 2011-08-21 | 2013-03-06 | 深圳兆日科技股份有限公司 | Anti-counterfeiting method and system by identification by self-physical characteristics of substance |
| CN103927668A (en) * | 2014-04-14 | 2014-07-16 | 立德高科(北京)数码科技有限责任公司 | Method for identifying authenticity of product based on comparison result of shot image and pre-stored image |
| CN104008369A (en) * | 2014-05-16 | 2014-08-27 | 四川大学 | Method and device for recognizing authenticity of seal |
| CN105590219A (en) * | 2014-10-20 | 2016-05-18 | 刘杬杰 | Colorized and three-dimensional coating-based anti-counterfeiting system and method |
| WO2016077934A1 (en) * | 2014-11-21 | 2016-05-26 | Le Henaff Guy | System and method for detecting the authenticity of products |
-
2016
- 2016-12-27 CN CN201611225276.5A patent/CN106815731A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955930A (en) * | 2011-08-21 | 2013-03-06 | 深圳兆日科技股份有限公司 | Anti-counterfeiting method and system by identification by self-physical characteristics of substance |
| CN103927668A (en) * | 2014-04-14 | 2014-07-16 | 立德高科(北京)数码科技有限责任公司 | Method for identifying authenticity of product based on comparison result of shot image and pre-stored image |
| CN104008369A (en) * | 2014-05-16 | 2014-08-27 | 四川大学 | Method and device for recognizing authenticity of seal |
| CN105590219A (en) * | 2014-10-20 | 2016-05-18 | 刘杬杰 | Colorized and three-dimensional coating-based anti-counterfeiting system and method |
| WO2016077934A1 (en) * | 2014-11-21 | 2016-05-26 | Le Henaff Guy | System and method for detecting the authenticity of products |
Non-Patent Citations (1)
| Title |
|---|
| 葛盼盼 等: "基于SURF特征提取的遥感图像自动配准", 《计算机***应用》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522947A (en) * | 2018-10-31 | 2019-03-26 | 联想(北京)有限公司 | Recognition methods and equipment |
| CN109522947B (en) * | 2018-10-31 | 2022-03-25 | 联想(北京)有限公司 | Identification method and device |
| CN111435458A (en) * | 2019-01-11 | 2020-07-21 | 罗伯特·博世有限公司 | Method and apparatus for creating and verifying an anti-counterfeiting mark |
| CN110014763A (en) * | 2019-05-07 | 2019-07-16 | 中山易必固新材料科技有限公司 | A kind of antifalsification label production method and device based on electronic beam curing |
| CN110414586A (en) * | 2019-07-22 | 2019-11-05 | 杭州沃朴物联科技有限公司 | Antifalsification label based on deep learning tests fake method, device, equipment and medium |
| CN110414586B (en) * | 2019-07-22 | 2021-10-26 | 杭州沃朴物联科技有限公司 | Anti-counterfeit label counterfeit checking method, device, equipment and medium based on deep learning |
| CN112560989A (en) * | 2020-12-25 | 2021-03-26 | 烟台职业学院 | Artificial intelligence anti-counterfeiting image identification method and system based on big data |
| CN112560989B (en) * | 2020-12-25 | 2022-07-29 | 烟台职业学院 | Artificial intelligence anti-counterfeiting image identification method and system based on big data |
| CN114782796A (en) * | 2022-06-17 | 2022-07-22 | 武汉北大高科软件股份有限公司 | Intelligent verification method and device for article image anti-counterfeiting |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106815731A (en) | A kind of label anti-counterfeit system and method based on SURF Image Feature Matchings | |
| US9153005B2 (en) | Method and system for authenticating a secure document | |
| CN103761799B (en) | A kind of bill anti-counterfeit method based on texture image feature and device | |
| CN103914680B (en) | A kind of spray printing character picture identification and check system and method | |
| CN103930929A (en) | Detecting counterfeit print material with camera-equipped computing device | |
| CN104463291B (en) | Method for anti-counterfeit and mobile equipment | |
| CN109949058A (en) | Antifake method for products, device, electronic equipment and read/write memory medium | |
| CN108509870A (en) | A kind of Eriocheir sinensis uniqueness recognition methods based on images match | |
| CN104464504B (en) | Antifalsification label, the manufacture method of antifalsification label and method for anti-counterfeit | |
| CN106415608A (en) | Methods and a system for verifying the identity of a printed item | |
| CN107292636A (en) | A kind of commodity counterfeit prevention checking system based on natural biological information | |
| CN110428028A (en) | Fake method, device, equipment and medium are tested in identification based on Quasi dynamic laser label | |
| CN111242641B (en) | Method, device, equipment and medium for judging fleeing goods | |
| CN115244542A (en) | Method and device for verifying authenticity of product | |
| CN106157064A (en) | The Antiforge system that identification code associates with image | |
| CN105205673A (en) | Anti-counterfeiting tracing technology by means of cigarette carton coding characteristic | |
| CN110533704B (en) | Method, device, equipment and medium for identifying and verifying ink label | |
| CN113435219B (en) | Anti-counterfeiting detection method and device, electronic equipment and storage medium | |
| CN116227524B (en) | Anti-fake code generation and verification method and label-based anti-fake system | |
| CN113518997A (en) | Anti-counterfeiting paper product based on microstructure detection and manufacturing method and identification method thereof | |
| CN116976375A (en) | Method and device for detecting cigarette packaging box in code scanning and verification scene | |
| CN116911883A (en) | Agricultural product anti-counterfeiting tracing method and cloud platform based on AI (advanced technology) authentication technology and tracing quantification | |
| CN109934323A (en) | Random solution print pattern antifalsification label and its discrimination method based on image comparison | |
| CN106600288A (en) | Anti-counterfeiting method and device | |
| EP3992356A1 (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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170609 |
|
| RJ01 | Rejection of invention patent application after publication |