CN103903039B - Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof - Google Patents
Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof Download PDFInfo
- Publication number
- CN103903039B CN103903039B CN201410117589.3A CN201410117589A CN103903039B CN 103903039 B CN103903039 B CN 103903039B CN 201410117589 A CN201410117589 A CN 201410117589A CN 103903039 B CN103903039 B CN 103903039B
- Authority
- CN
- China
- Prior art keywords
- hidden
- code
- image
- hidden code
- counterfeiting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention relates to the anti-counterfeiting technical field, and particularly discloses a hidden code holographic anti-counterfeiting film. The hidden code holographic anti-counterfeiting film comprises an anti-counterfeiting information layer which comprises a holographic anti-counterfeiting image-text part and a hidden code. The invention further discloses a manufacturing method of the anti-counterfeiting information layer in the anti-counterfeiting film and a device, intelligent terminal equipment, a data server and a recognition system which are used for scanning and recognizing the hidden code holographic anti-counterfeiting film. The hidden code holographic anti-counterfeiting film can be produced by using a mature holographic embossing technology, is low in cost and has dual anti-counterfeiting effects. The hidden code holographic anti-counterfeiting film can be distinguished through the naked eyes by means of the holographic anti-counterfeiting image-text part, and a decoding program of hand-held equipment (such as a smart phone) can also be used for displaying information hidden in the hidden code.
Description
Technical field
The present invention relates to field of anti-counterfeit technology is and in particular to a kind of hidden code holographic anti-counterfeiting film, its manufacture method, and
Identifying system.
Background technology
Holographic false proof trade mark contributes to hitting counterfeit and shoddy goods, has a wide range of applications, such as various wine product and other
Packaging of high-grade goods etc..However, the holographic anti-counterfeiting film using currently on the market has gone through development for many years, in structure and
Credibility is increasingly lost on anti-counterfeiting power.
In recent years, with the quick popularization of smart mobile phone, particularly i Phone is fashionable, has realized using smart mobile phone
Coding information on open programmable module reading holographic false proof trade mark is to show more merchandise newss.
By holographic security technology with can be combined by the coding information that smart mobile phone decodes, holographic to form hidden code
The double anti-forge technology of anti false film, will be a direction of following anti-counterfeiting technology.
Content of the invention
It is contemplated that overcoming the problems referred to above and the other problemses of prior art, by holographic security technology and smart mobile phone
Coding techniques combines, to provide hidden code holographic anti-counterfeiting film and the identifying system with double anti-forge function.
A first aspect of the present invention provides a kind of hidden code holographic anti-counterfeiting film, including anti-counterfeiting information layer, described false proof letter
Picture and text containing holographic false proof in breath layer, and with described holographic false proof overlap, overlap and/or separate the hidden code of arrangement.
Described hidden code can be exported by the programmable interface coding by using opening to smart machine
Discrete codes point, and the hiding information of described hidden code can be shown by using the decoding program of intelligent terminal.
Described hiding information can comprise word, image, voice document, video file, or combinations thereof.
Described holographic false proof picture and text can be hologram, bar code, Quick Response Code, or combinations thereof.
A second aspect of the present invention provides a kind of method of the anti-counterfeiting information layer for making hidden code holographic anti-counterfeiting film,
Including step：S1, by the programmable interface coding open to smart machine, exports discrete codes point；S2 will be described discrete
Encoded point is together with holographic false proof graphic rendering；S3 is shot or photoetching technique using holographic, makes and has hidden code holography
The photoetching hectograph of Antiforge；S4 utilizes galvanoplastics, makes contour forging nickel version；And S5 utilizes hot pressing reproduction technology, will
Hidden code holographic false proof picture and text in described contour forging nickel version are stamped on information carrying layer, to form anti-counterfeiting information layer.
A third aspect of the present invention provides a kind of scanning and the device identifying above-mentioned hidden code holographic anti-counterfeiting film, bag
Include：Video Capture module, for scanning described hidden code holographic anti-counterfeiting film, completes Video Capture；And hidden code analysis module,
Image for obtaining to Video Capture module scans hidden code holographic anti-counterfeiting film carries out Image semantic classification, and parsing is located through pre-
Hidden code in image after reason, sends to enter to a data server by wireless network after the hidden pattern encryption that parsing is obtained
Line retrieval and coupling.
Described Video Capture module can scan described hidden code holographic anti-counterfeiting film further in the following way, completes
Video Capture：（a）Select video capturing device, define the parameters of video capturing device, preview call back function is set, thus
Start video capturing device, and intervalometer is set；（b）Described video capturing device focuses once every a setting time, focusing
Shoot a sub-picture after success to the parsing of hidden code analysis module, video capturing device stop taking pictures but proceed Video Capture and
Focusing；（c）If hidden code analysis module successfully resolved, terminate；Otherwise return execution（b）.
Described hidden code analysis module may further include：Image pre-processing unit, for Video Capture module scans
The image that hidden code holographic anti-counterfeiting film obtains carries out homomorphic filtering, histogram equalization and Canny operator edge detection, makes institute
State and in image, project hidden pattern and noise distribution；Hidden pattern analytic unit, for extracting hidden pattern from noise
Come and identified, including：Stealthy to Video Capture module scans using the Markov random field model for bianry image
Hidden pattern denoising containing noise in the image that encoded holographic anti false film obtains, using the machine of linear multi-class support vector machine
Learning method carries out model training and obtains classification function, identifies 10 radixes of hidden code image using described classification function, to going
Image after making an uproar is scanned to obtain hidden pattern sequence；Hidden pattern ciphering unit, for the hidden code mould that parsing is obtained
Formula is encrypted, including：Using personal key algorithm, the character string of described hidden pattern is encrypted.
Described device can also include a display performing module, is returned by wireless network for receiving described data server
Item Information after the retrieval passing and coupling, and described Item Information is shown on a display screen.
A fourth aspect of the present invention provides a kind of intelligence of the hidden code holographic anti-counterfeiting film of scanning and the identification present invention eventually
End equipment, described intelligent terminal includes the dress of the hidden code holographic anti-counterfeiting film of above-mentioned scanning and the identification present invention
Put, described intelligent terminal is provided with video capturing device, described intelligent terminal possesses wireless networking capabilities.
A fifth aspect of the present invention provides a kind of hidden code holographic anti-counterfeiting film to the present invention to enter line retrieval and coupling
Data server, described data server includes：DBM, for storage service classify code and with described classification of service code
Corresponding Item Information；Data service module, for receiving the hidden code of the encryption of certain device or equipment transmission by wireless network
Pattern, deciphers described hidden pattern after CRC carries out error checking and correction, retrieves in described DBM
Classification of service code, match from classification of service code be adapted to described hidden pattern encode and obtain coding corresponding article letter
Object information after retrieval and coupling is fed back to described device or equipment by wireless network by breath.
A sixth aspect of the present invention provides the system that a kind of hidden code holographic anti-counterfeiting film to the present invention is identified, institute
The system of stating include above-mentioned scanning and identification hidden code holographic anti-counterfeiting film intelligent terminal and above-mentioned to hidden code
Holographic anti-counterfeiting film enters line retrieval and the data server of coupling；Wherein, described intelligent terminal is used for shooting described stealthy volume
The image of code holographic anti-counterfeiting film, the hidden pattern in parsing described image, by no after the hidden pattern encryption that parsing is obtained
Gauze network sends and enters line retrieval and coupling to described data server；Described data server is used for receiving intelligence by wireless network
Can the hidden pattern of encryption that sends of terminal unit, retrieval service classification code from DBM, from classification of service code
Allot be adapted to described hidden pattern encode and obtain the corresponding Item Information of coding, will be retrieved by wireless network and mate
Item Information afterwards feeds back to device or equipment.
Preferably, the described wireless network of the present invention can be GPRS or 3G network.
The hidden code holographic anti-counterfeiting film of the present invention has a double anti-forge effect, attractive in appearance and to be applied to the public false proof；Can lead to
Cross portable equipment（Such as smart mobile phone）Decoding program show its hide information.Ripe contour forging technique can be utilized
Produce, low manufacture cost.By the hidden code that will generate at random（Comprise the hash-coding point of hiding information）It is attached to holographic false proof
Picture and text, can solve false proof and demand that is tracing to the source simultaneously, and identification process is simple.
Brief description
The anti-counterfeiting information layer that Figure 1A to Fig. 1 D schematically shows in the hidden code holographic anti-counterfeiting film of the present invention respectively is different
Form.
Fig. 2A and Fig. 2 B schematically shows the cross-section structure of the hidden code holographic anti-counterfeiting film according to the present invention respectively.
Fig. 3 is the fabrication processing figure of the anti-counterfeiting information layer of hidden code holographic anti-counterfeiting film of the present invention.
Fig. 4 schematically shows the system of the hidden code holographic anti-counterfeiting film for identifying the present invention.
Reference：Base membrane layer 1, information carrier layer 2, anti-counterfeiting information layer 21, high reflection film plating layer 3, melt pressure sensitive glue-line
41st, gum layer 42, release layer 5, holographic false proof picture and text 211, hidden code 212
Specific embodiment
With specific embodiment, the present invention is described in further detail below in conjunction with the accompanying drawings.
Holographic security technology is combined by the present invention with smart mobile phone coding techniques, and existing holographic anti-counterfeiting film is risen
Level, the discrete codes comprising hidden code point is attached to holographic false proof picture and text, to provide the hidden code of the present invention holographic anti-
Pseudomembrane, this anti false film includes anti-counterfeiting information layer 21.Information Level 21 is the grating being formed by contour forging nickel version hot padding
Picture and text, it includes general holographic false proof picture and text 211 and hidden code 212.
With reference first to Figure 1A to Fig. 1 D, the anti-counterfeiting information layer of four kinds of different arrangement forms is respectively schematically shown.From figure
In visible, holographic false proof picture and text 211 can be hologram, bar code, Quick Response Code etc., and can also be this several group
The form closed.Holographic false proof picture and text 211 and hidden code 212, hidden code 212 and holography is comprised in described anti-counterfeiting information layer 21
Antiforge 211 can overlapping, overlapping and/or separation arrangement.
Holographic false proof picture and text 211 can diffraction go out rich color, dynamic change, multichannel and multidimensional optically variable effect holographic anti-
Pseudo- image, can distinguish there is the true and false dazzling beautiful diffraction light change it is adaptable to the public is false proof by naked eyes.Hidden code 212 is then hidden
In anti-counterfeiting information layer 21, it can be for example discrete codes point, so when overlapping with holographic false proof picture and text 211, Bu Huiyu
Holographic false proof picture and text 211 interfere with each other, and nor affect on product attractive in appearance.
This discrete codes point can be using the programmable interface coding open to smart machine, the coding being exported
Information, and smart machine can be passed through（The Handheld intelligent equipment of such as smart mobile phone）Decoding program show its hide letter
Breath, so realizes dual antifalse effect.These hiding informations can be for example word, image, voice document, video file
Deng, or combinations thereof.
With reference to Fig. 2A and Fig. 2 B, it is schematically shown two kinds of concrete forms of the hidden code holographic anti-counterfeiting film of the present invention
Cross-section structure, wherein Fig. 2A show the hidden code holographic anti-counterfeiting film of gold stamping form membrane；Fig. 2 B show composite membrane（Or complete turn
Move film）The hidden code holographic anti-counterfeiting film of form.
When the hidden code holographic anti-counterfeiting film of the present invention is gilding film（Fig. 2A）When, it includes base membrane layer from bottom to top successively
1st, release layer 5, information carrier layer 2, anti-counterfeiting information layer 21, film plating layer 3 and melt pressure sensitive glue-line 41.
Base membrane layer 1 is the carrier of coating, can be using plastic sheeting as base membrane layer.It is attached to base other coating uniform
In film layer 1.Release layer 5 is attached on base membrane layer 1, and its raw material generally adopts fusing point in 80-90 DEG C of wax.Release layer 5 is gold stamping
Dissociation is played in the use of film.
Information carrier layer 2 is used for carrying holographic information, is transferred on base membrane layer 1 and is done by the coated equipment of coating fluid
Dry, form information carrier layer 2.By hot press printing technology, anti-counterfeiting information layer 21 can be transferred on information carrier layer 2.
High reflection film plating layer 3 is attached on anti-counterfeiting information layer 21, it typically is the metal with high reflection performance or medium,
And can be formed by the method for vacuum evaporation.The presence of film plating layer 3 can improve the brightness of holographic film, and convenient utilization is reflected
Light directly observes holographic false proof figure.Melt pressure sensitive glue-line 4 is one layer of the outermost of this hidden code holographic false proof gilding film, its effect
It is to adhere to stock surface when product uses.
When the hidden code holographic anti-counterfeiting film of the present invention is composite membrane（Or total transfer film）（Fig. 2 B）When, its from bottom to top according to
Secondary inclusion base membrane layer 1, information carrier layer 2, Information Level 21, high reflection film plating layer 3 and gum layer 42.From Fig. 2 B, this
Bright hidden code holographic false proof composite membrane（Or total transfer film）Similar with the gilding film shown in Fig. 2A, but do not include release layer,
And when for composite membrane, base membrane layer 1 does not separate in use；And when for total transfer film, base membrane layer 1 is in the mistake of composite transferring
Separate in journey, and can be with recycling.
The hidden code holographic anti-counterfeiting film of the present invention generally can be produced using ripe contour forging technique, becomes
This is relatively low.The method have the characteristics that the making of anti-counterfeiting information layer therein.With reference to Fig. 3, illustrate for making this hidden code
The technological process of the anti-counterfeiting information layer in holographic anti-counterfeiting film.It can be seen that manufacture method mainly includes following step：
First in step S1, by the open programmable interface coding of smart mobile phone, output invisible encodes, for example from
Scattered encoded point.Afterwards in step S2, by described hidden code（Discrete codes point）Together with holographic false proof graphic rendering；And
Shot or photoetching technique using holographic in step S3, make the photoetching hectograph with hidden code holographic false proof picture and text；Then exist
Utilize galvanoplastics in step S4, make contour forging nickel version；Utilize hot pressing reprography afterwards, by described contour forging nickel version
On hidden code holographic false proof picture and text print to information carrying layer, to form anti-counterfeiting information layer.
It will be understood by those skilled in the art that according to the concrete form of anti false film, can before process steps made above,
Between and afterwards, correspondingly increase suitable operation.For example in the case of gilding film, holographic false proof figure batch is being imprinted
Before duplication, need information carrying layer 2 is coated on base membrane layer 1.After anti-counterfeiting information layer 21 is formed, using vacuum coating skill
Art, plates metal film or the deielectric-coating of high reflection on anti-counterfeiting information layer 21, forms high reflection film plating layer 3；Coating hot-fusible pressure-sensitive adhesive
Layer 41 or gum layer 42 are on high reflection film plating layer 3.Finally anti false film can be cut, to be applied on product.
The product so making can diffraction go out that rich color is attractive in appearance, the optically variable effect of dynamic change, multichannel and multidimensional complete
Breath anti-counterfeiting image, distinguishes to have not only by naked eyes and dazzles the true and false of beautiful diffraction light change it is adaptable to the public is false proof；In Information Level also
Hide coding, portable equipment can be passed through（Smart mobile phone）Decoding program show its information hidden, such as word, image, language
Sound file or video file etc., have double anti-forge effect, can be applicable to the fields such as anti-false trademark.
The present invention gilding film specifically used in, due to when gold stamping gilding film be subject to high temperature and certain pressure,
Acted on by temperature and pressure, release layer 5 is first begin to melting as the minimum part of fusing point in each layer and is converted into liquid, in stripping
In the presence of power, this layer destroys first, thus the information carrier layer 2 of carrying information layer 21 is separated with base membrane layer 5.With
The increase of temperature and pressure, melt pressure sensitive glue-line 4 starts to soften and viscosity, melt when the effect of glue-line adhesion is more than
During the wax layer adhesion melted, bronzing material is transferred on stock, and base membrane layer 1 is stripped, thus realizing complete gold stamping
Process.
Composite membrane in the present invention（Or total transfer film）Specifically used in, using the adhesiveness of gum layer 4, using compound
The base material and another base material with holographic information are combined and ripening by equipment.Thus the holographic anti-counterfeiting film with hidden code is turned
Move on on stock.As described above, when the present invention holographic anti-counterfeiting film be composite membrane when, base membrane layer 1 in recombination process not
Separate；And when the holographic anti-counterfeiting film of the present invention is total transfer film, this base membrane layer will separate in recombination process, and can be by
Recycling.
With reference to Fig. 4, illustrate according to the present invention, using portable equipment（Such as smart mobile phone）Hidden code to the present invention
Holographic anti-counterfeiting film is identified, to decode the system of display hiding information.This system mainly includes two parts：Intelligent terminal sets
Standby（Such as smart mobile phone）, include wherein for scan and identify the present invention hidden code holographic anti-counterfeiting film device, with
And be used for the hidden code holographic anti-counterfeiting film of the present invention is entered with the data server of line retrieval and coupling.
It is described separately below.
The embodiment of the present invention additionally provides a kind of scanning and the device identifying above-mentioned hidden code holographic anti-counterfeiting film, this device
Including Video Capture module and hidden code analysis module, wherein Video Capture module is used for scanning hidden code holographic anti-counterfeiting film, complete
Become Video Capture；The image that hidden code analysis module is used for Video Capture module scans hidden code holographic anti-counterfeiting film is obtained is carried out
Image semantic classification, and parse the hidden code in pretreated image, by no after the hidden pattern encryption that parsing is obtained
Gauze network sends and enters line retrieval and coupling to a data server.Wireless network can adopt general packet radio service technology
（General Packet Radio Service, GPRS）Network or 3G network.
Video Capture module can be applicable to Android, iOS, Windows Phone（Abbreviation WP）Etc. intelligent operating system,
Cover and there is the equipment such as the smart mobile phone of photographic head, notebook computer, panel computer on the market, its major function is according to difference
Operating system set up complete Video Capture platform, guiding user uses photographic head scanning material interested（Including two dimension
Code, bar code or laser anti-counterfeit label etc.）.Video Capture module can scan hidden code holographic false proof in the following way
Film, completes Video Capture：
（a）Select video capturing device（Photographic head as intelligent terminal）, define the parameters of photographic head in this way
No preview, picture format, preview frame number, preview size etc., then arrange preview call back function, receive, divide in call back function
Analyse each frame, start previews, thus starting video capturing device, and intervalometer is set；
（b）Photographic head focuses once every a setting time, and this setting time is arranged by above-mentioned intervalometer, for example, can set
Put and once focused every 1 second, shoot a sub-picture after focusing success, then set up another a thread, image cursor is pointed to hidden
Code analysis module, is parsed by hidden code analysis module；Take pictures thread simultaneously（Main thread）Configuration state word（For example configuration state word be 1 or
Person's other numerical value except zero）Make photographic head stop taking pictures, but photographic head proceeds Video Capture, focusing task, waits
Hidden code division analyses resume module；
（c）When hidden code analysis module thread terminates, it is likely to be obtained the result of analysis success or failure.If hidden code analysis module
Successfully resolved, namely have successfully been obtained hidden pattern, then terminate this task of Video Capture module；If failing to obtain hidden code mould
Formula, then remind user need to try again, can return to execute（b）.No matter which kind of situation above-mentioned, when user returns to Video Capture circle
Face, main thread removes status word（Status word is made to be 0）, restart to be spaced the process of 1 second focusing photographic analysis.
Hidden code analysis module carries out pretreatment to the image that Video Capture module scans obtain, and obtains and is distributed in image
Self-defined random code word, to self-defined random code word pattern recognition, analysis, is encrypted to self-defined code word using key, calculates
Ciphertext is simultaneously sent to the data server in high in the clouds by the ciphertext of regular length by wireless network.High in the clouds data server then docks
The ciphertext received is decrypted, the classification of service code in quick-searching server, and what coupling was suitable for encodes and feed back corresponding information, then
Secondary utilization wireless network（GPRS or 3G）Object information is sent to the intelligent terminal of user, user can be according to corresponding information
Differentiate the true and false of commodity and trace to the source.
Specifically, hidden code analysis module includes image pre-processing unit, hidden pattern analytic unit and the encryption of hidden pattern
Unit.Through focusing, the image of acquisition of taking pictures easily is affected by shadow change, weather, photographer, need to pass through Image semantic classification list
Unit carries out pretreatment to image.For feature of image, the present embodiment priority image is carried out homomorphic filtering, histogram equalization with
Canny operator edge detection, makes to project hidden pattern and noise distribution in image.Equal to homomorphic filtering, rectangular histogram separately below
This 3 image processing process of weighing apparatusization and Canny operator edge detection are described further：
（1）Homomorphic filtering：
Take pictures acquisition dynamic range of images very big, and the gray scale of interesting part is very dark, and image detail can not be distinguished
Recognize, bad using general gray-level linear transfonnations method effect.The homomorphic filtering of image belongs to picture frequency domain and processes category, its
Effect is that gradation of image scope is adjusted, and by eliminating the problem illuminating inequality on image, strengthens the image detail of dark space,
Lose the image detail in clear zone simultaneously and not.
Image f (x, y) of natural scene can be by grading function fi(x, y) and reflective function frThe product representation of (x, y).fi
(x, y) describes the illumination of scenery, unrelated with scenery；fr(x, y) comprises the details of scenery, unrelated with illuminating.
F (x, y)=fi(x, y) * fr(x, y)
0 ＜ fi(x, y) ＜ ∞；0 ＜ fr(x, y) ＜ 1 (1)
Because the two multiplication is separately processed it is impossible to transform to frequency domain again, therefore do following process：
To formula（1）Take the logarithm
Lnf (x, y)=lnfi(x, y)+lnfr(x, y)（2）
Make to become addition relation in spatial domain, to formula（2）Take Fourier transformation
Fln(u, v)=FI, ln(u, v)+FR, ln(u, v) (3)
In formula, FI, ln：Grading function is spatially varying slowly, and its spectral characteristic concentrates on low-frequency range；FR, ln：Reflection letter
The spectrum concentration of number is in high band（There is in image more details and edge）, the scenery reflection image of reflective function description
Detail content, its frequency is in high-frequency region.
If image illumination is uneven, then on image, the mean flow rate of each several part has fluctuating.Image corresponding to dark space is thin
The just more difficult resolution of nodule structure, needs to eliminate this inhomogeneities.The tonal range of grading function can be compressed, that is, in frequency domain
The upper composition weakening grading function, strengthens the spectrum component of reflective function it is possible to increase the anti-of reflection picture contrast simultaneously
Penetrate the contrast of function.As a result, so that dark space image detail on image is increased, and as wide as possible keep clear zone image thin
Section.It is multiplied by transfer function H (u, v)（Homomorphic filter）, low-frequency range is compressed, and high band extends.
Gln(u, v)=Fln(u, v) * H (u, v)
=GI, ln(u, v)+GR, ln(u, v) (4)
Then seek Fourier inversion, obtain in corresponding spatial domain representation
G (x, y)=exp { F-1{Gln(u, v) } } (5)
According to different picture characteristics and needs, from different H (u, v), poor to detail contrast, differentiate unclear figure
After being processed with homomorphic filter, image frame brightness ratio is more uniform, and details is enhanced.
（2）Histogram equalization：
After homomorphic filtering, convert the image into gray-scale maps, due to the gray value non-uniform Distribution of many images, wherein
The image that gray value concentrates in a minizone is very common.Histogram equalization is by being again evenly distributed each ash
The method to strengthen picture contrast for the angle value.Through the image of histogram equalization, binary-state threshold is chosen highly beneficial.
The present embodiment uses image scale transform：Pixel in gray scale interval [a, b] is mapped to [z1,zk] interval.
Generally, original image gray scale interval [a, b] usually from space [z1,zk] subspace, now, by former interval in picture
The function representation that vegetarian refreshments z is mapped to new district interior pixel z ' is
Above-mentioned mapping relations are actually by [a, b] interval extension to interval [z1,zk] on, make the more black of image black, white more
In vain.
（3）Rim detection：
Need in image to extract the position of hidden code and noise, that is, in image, gray scale occurs zone boundary jumpy.Real
On border, this is a typical rim detection problem.The essence of rim detection be to be extracted using certain algorithm right in image
As the boundary line between background, Canny operator be neighborhood using centered on pending pixel as the basis carrying out gray analysis,
Realize extracting and having been achieved for preferable treatment effect to image border.Its basic step is：
1st, filter.Rim detection is based primarily upon derivative calculations, but affected by noise.Wave filter is while reducing noise
Lead to the loss of edge strength.
2nd, strengthen.Strengthen algorithm to highlight the point that gray scale in neighborhood has significant change.Typically pass through to calculate gradient width
Value completes.
3rd, detect.What in some images, gradient magnitude was larger is not marginal point.Simplest rim detection is gradient
Amplitude thresholds judge.
4th, position.Accurately determine the position at edge.
Canny operator asks marginal point specific algorithm step as follows：
1st, use Gaussian filter smoothed image.
2nd, single order local derviation finite difference formulations gradient magnitude and direction are used.
3rd, non-maxima suppression is carried out to gradient magnitude.
4th, the detection of dual threashold value-based algorithm and adjoining edge are used.
Hidden pattern and noise can be projected through pretreated image to be distributed, and the final purpose of the present embodiment be by
Hidden pattern extracts from noise and is identified.Hidden code code word in the present embodiment contains 10 radixes, every 30 structures
Become a hidden pattern, the quantity that can be calculated all hidden patterns is 1030Individual.For obtaining the hidden code mould containing noise
Formula is it is necessary first to carry out denoising to hidden code image, then above-mentioned using the classification function identification being obtained by machine learning method
10 radixes, are finally scanned to image, discriminate whether containing hidden pattern accordingly.
Therefore, in the present embodiment, by hidden pattern analytic unit, hidden pattern is extracted from noise and in addition
Identification, including：Holographic to Video Capture module scans hidden code using the Markov random field model for bianry image
Hidden pattern denoising containing noise in the image that anti false film obtains, using the machine learning method of linear multi-class support vector machine
Carry out model training and obtain classification function, identify 10 radixes of hidden code image using classification function, the image after denoising is entered
Row scanning is to obtain hidden pattern sequence.Additionally, hidden pattern encryption parsing being obtained by hidden pattern ciphering unit, example
As the character string of hidden pattern being encrypted using personal key algorithm.Separately below to hidden code image denoising and hidden code base
The processing procedure of identification is described further：
（1）Hidden code image denoising：
Image denoising herein is directed to the hidden pattern containing noise.In view of efficiency, the present embodiment adopts
Markov random field model for bianry image.The quantity assuming noise is less than real hidden pattern it is believed that no
Any point x in the hidden pattern of noiseiWith point y on the relevant position in the hidden pattern of NoiseiThere is stronger dependency,
Same it is also assumed that consecutive points x in the hidden pattern of noiselessiWith xjThere is stronger dependency.We have such
The point of strong correlation, to being defined as one group of neighborhood, then just has two kinds of neighborhood：(xi, yi) and (xi, xj).Will
Both prioris are programmed in energy function, for (xi, yi), energy function takes-η xiyi, η is a positive constant, right
(xi, xj), energy function takes-γ xixj, γ is a positive constant.In addition, for the hidden pattern of the present embodiment, needing to add
Enter the appearance that an energy function is conducive to individually putting, then complete energy function form is：
Energy function defines the joint probability distribution of a vector x and y：
Formula（8）Middle Z is normalization factor.
Because y is the point observing, formula（8）Actually it is equivalent to define conditional probability p (x | y), the mesh of image denoising
Be the probit finding maximum possible.The algorithm that the system adopts is graph-cuts, and this algorithm can ensure that global convergence,
There is higher efficiency simultaneously.
（2）Hidden code base identification
In the present embodiment, hidden pattern is made up of 10 primary image patterns, implies in the picture for can effectively extract
Pattern, need to carry out model training in advance, obtain discriminant function, the image clapped is carried out detecting primary image mode sequences thereafter
And coding mode sequence.
The machine learning algorithm that in the present embodiment, model training is adopted is multi-class support vector machine（Support Vector
Machine, SVM）.Support vector machine are V.Vipnik etc. according to Statistical Learning Theory（Statistical Learning
Theory, SLT）A kind of new machine learning method proposing, shows in solving the problems, such as non-linear and high dimensional pattern identification
Many distinctive advantages, achieve good effect at aspects such as pattern recognition, function approximation and Multilayer networks.?
Holding vector machine is a kind of feedforward neural network in essence, according to empirical risk minimization, classifies making training sample
On the premise of error minimization, improve the extensive Generalization Ability of grader as far as possible.From the angle implemented, Training Support Vector Machines
Core concept is equivalent to solve the quadratic programming problem of a linear restriction, thus constructing a hyperplane as decision plane,
Make the distance between two quasi-modes maximum in feature space, and can guarantee that the solution obtaining is globally optimal solution.
SVM method is the optimal classification surface in the case of linear separability（Optimal Hyperplane）Propose.Optimum
Classifying face be exactly require classification line not only can will be faultless separate for two class samples, and the distance between two classes maximum to be made.
If linear separability sample set is (xi, yi), i=1,2 ..., n, x ∈ Rd, y ∈ {+1, -1 }, y are category labels.d
In dimension space, the general type of linear discriminant function is：G (x)=ωTX+b, classifying face equation is：
ωTX+v=0 (9)
Discriminant function is normalized, makes all samples of two classes all meet | g (x) | >=1, i.e. to make nearest from classifying face
Sample g (x) |=1, such class interval is equal to 2/ | | ω | |, therefore interval maximum is equivalent to make | | ω | |（Or | | ω
||2）Minimum；And require classification line all samples correctly to be classified it is simply that requiring its satisfaction：
yi[ωTX+b] -1 >=0, (i=1,2 ..., n) (10)
It therefore meets above-mentioned condition and make | | ω | |2Minimum classifying face is exactly optimal classification surface.In this two classes sample from
The nearest point of classifying face and be exactly to make formula parallel to the training sample on the hyperplane of optimal classification surface（9）Middle equal sign set up that
A little samples, they are called supporting vector（Support Vectors）.According to the above discussion, optimal classification surface problem can represent
Become following constrained optimization problems, that is, in formula（10）Constraint under, find a function：
Minima.This is a quadratic programming problem, can get optimal solution ω*, b*.Then obtaining optimal classification function is：
F (x)=sgn { ω*Tx+b*} (12)
Wherein：Sgn (.) is sign function, for given unknown sample x, only needs calculating formula（12）Can determine that belonging to x
Classification.
In sum, the present embodiment uses linear multi-class support vector machine, after the completion of the training stage, obtains letter of classifying
Number.Image-region is scanned, obtains hidden pattern sequence, using key, the character string of corresponding hidden pattern is encrypted（Example
As encrypted using personal key algorithm）, and ciphertext is sent to data service module coupling, searches for this pattern corresponding article letter
Breath.
Additionally, this device also includes a display performing module, returned by wireless network for receiving data server
Item Information after retrieval and coupling, and Item Information is shown on a display screen.
It will be appreciated by those skilled in the art that this device can form an application program by programming, for example, it is applied to intelligence
The application program of terminal unit, after this application program is installed on intelligent terminal, the video capture of combined with intelligent terminal unit
Equipment can achieve scanning and identify above-mentioned hidden code holographic anti-counterfeiting film function, identification success after can also be superimposed figure layer in
The commodity true and false of display data server feedback and other information on video.
The embodiment of the present invention additionally provides a kind of scanning and identifies that the intelligent terminal of above-mentioned hidden code holographic anti-counterfeiting film sets
Standby, this intelligent terminal includes device as above（In the case of this device being passed through programming formation one application program, can
It is understood as in this intelligent terminal being provided with this application program）, intelligent terminal is provided with video capturing device and possesses no
Line function of surfing the Net, the mode of wireless networking can adopt GPRS or 3G network.Intelligent terminal can be smart mobile phone, notebook
The intelligent movable equipment such as computer or PDA, it is typically provided with this video capturing device of photographic head.
The embodiment of the present invention additionally provides a kind of data that above-mentioned hidden code holographic anti-counterfeiting film is entered with line retrieval and coupling
Server, this data server includes DBM data service module, and wherein DBM divides for storage service
Class code and Item Information corresponding with classification of service code；Data service module is used for receiving certain device or equipment by wireless network
The hidden pattern of the encryption sending, by CRC（Cyclic Redundancy Check）Carry out error checking and correction
After decipher hidden pattern, the classification of service code in searching database module, match from classification of service code with hidden pattern fit
That joins encodes and obtains the corresponding Item Information of coding, feeds back the object information after retrieval and coupling finally by wireless network
Device or equipment to scanning recognition.Increase with product, the record in data base will rise to and have a strong impact on retrieval rate
The order of magnitude, in the present embodiment adopt level indexing structure improve query performance.
The embodiment of the present invention additionally provides a kind of system that above-mentioned hidden code holographic anti-counterfeiting film is identified, this system
Intelligent terminal including scanning as above and identification hidden code holographic anti-counterfeiting film and as above holographic to hidden code prevent
Pseudomembrane enters line retrieval and the data server of coupling.Wherein, intelligent terminal shoots the image of hidden code holographic anti-counterfeiting film,
Hidden pattern in analysis diagram picture, sends to enter to data server by wireless network after the hidden pattern encryption that parsing is obtained
Line retrieval and coupling；Data server receives the hidden pattern of the encryption that intelligent terminal sends by wireless network, from number
According to retrieval service classification code in library module, match from classification of service code encoding of be adapted to hidden pattern obtaining encode right
Item Information after retrieval and coupling is fed back to device or equipment by wireless network by the Item Information answered.Likewise, it is wireless
Network can be GPRS or 3G network.
During concrete application, the hidden code of additional random on Quick Response Code, bar code or laser anti-counterfeit label, by the intelligence of user
The intelligent terminal that energy mobile phone, notebook computer, panel computer etc. have photographic head is prevented to Quick Response Code, bar code or laser
Pseudo label scans and shoots specimen page, and the picture of acquisition is identified on intelligent terminal, and intelligent terminal parses wherein
The corresponding hidden pattern of article, the coding of hidden pattern is sent to data server by wireless network, obtains after String matching
Article corresponding informance, again by wireless network by Item Information（The true and false information of such as commodity or additional information）From number
According to server feedback to user intelligent terminal, thus completing an identification process.
The system can be with APP（Application）Form provide download, it is possible to provide iOS, Android and WP version.
During use, video scanning is carried out to the carrier containing hidden pattern, system can complete auto-focusing, take pictures, pattern analyses, feedback
Merchandise news process.For example：Add microcode anti-counterfeiting technology in holographic laser label, with intelligent terminal, label is swept
Retouch, APP is decoded to scanogram, form the interval code of a string encryption, then the data being sent to high in the clouds by wireless network
Server carries out Data Matching, returns corresponding data after the match is successful on the intelligent terminal of user.
The specific embodiment of present invention described above, does not constitute limiting the scope of the present invention.Any basis
Various other corresponding change done by the technology design of the present invention and deformation, should be included in the guarantor of the claims in the present invention
In the range of shield.
Claims (8)
1. a kind of scanning and identification hidden code holographic anti-counterfeiting film device it is characterised in that
Described hidden code holographic anti-counterfeiting film includes anti-counterfeiting information layer, picture and text containing holographic false proof in described anti-counterfeiting information layer, and
With described holographic false proof overlap, hidden code that is overlapping and/or separating arrangement；
Described hidden code is the discrete codes being exported by using the programmable interface coding open to smart machine
Point, and the hiding information of described hidden code can be shown by using the decoding program of intelligent terminal；
Described hiding information comprises word, image, voice document, video file, or combinations thereof；
Described holographic false proof picture and text are hologram, bar code, Quick Response Code, or combinations thereof；
Described device includes：
Video Capture module, for scanning described hidden code holographic anti-counterfeiting film, completes Video Capture；
Hidden code analysis module, it is pre- that the image for obtaining to Video Capture module scans hidden code holographic anti-counterfeiting film carries out image
Process, hidden code in pretreated image for the parsing, sent out by wireless network after the hidden pattern encryption that parsing is obtained
Deliver to a data server and enter line retrieval and coupling；
Described hidden code analysis module further includes：
Image pre-processing unit, the image for obtaining to Video Capture module scans hidden code holographic anti-counterfeiting film carries out homomorphism
Filtering, histogram equalization and Canny operator edge detection, make to project hidden pattern and noise distribution in described image；
Hidden pattern analytic unit, for hidden pattern being extracted from noise and being identified, including：Using for two
Contain in the image that the Markov random field model of value image obtains to Video Capture module scans hidden code holographic anti-counterfeiting film
There is the hidden pattern denoising of noise, carry out model training using the machine learning method of linear multi-class support vector machine and classified
Function, is identified 10 radixes of hidden code image, the image after denoising is scanned to obtain hidden code using described classification function
Mode sequences；
Hidden pattern ciphering unit, for encrypting to the hidden pattern that parsing obtains, including：Will be described using personal key algorithm
The character string of hidden pattern is encrypted.
2. device as claimed in claim 1 is it is characterised in that described Video Capture module scans further in the following way
Described hidden code holographic anti-counterfeiting film, completes Video Capture：
A () selects video capturing device, define the parameters of video capturing device, arranges preview call back function, thus starting
Video capturing device, and intervalometer is set；
B () described video capturing device focuses once every a setting time, shoot a sub-picture to hidden code division after focusing success
Analysis module parsing, video capturing device stops taking pictures but proceeds Video Capture and focusing；
If (c) hidden code analysis module successfully resolved, terminate；Otherwise return execution (b).
3. the device as any one of claim 1 or 2 is it is characterised in that described device also includes a display execution mould
Block, for receiving the Item Information after the retrieval that described data server returned and coupling by wireless network, and by described thing
Product presentation of information is on a display screen.
4. the device as any one of claim 1 or 2 is it is characterised in that described wireless network is GPRS or 3G network.
5. the intelligent terminal of a kind of scanning and identification hidden code holographic anti-counterfeiting film is it is characterised in that described intelligent terminal
Equipment includes the device described in any one of claim 1-3, and described intelligent terminal is provided with video capturing device, described intelligence
Can possess wireless networking capabilities by terminal unit.
6. intelligent terminal as claimed in claim 5 is it is characterised in that described wireless network is GPRS or 3G network.
7. a kind of system that hidden code holographic anti-counterfeiting film is identified is it is characterised in that described system includes claim 5
Described scanning and the identification intelligent terminal of hidden code holographic anti-counterfeiting film and hidden code holographic anti-counterfeiting film is examined
Rope and the data server of coupling；Wherein,
Described data server includes：
DBM, for storage service classification code and Item Information corresponding with described classification of service code；
Data service module, for receiving the hidden pattern of the encryption of certain device or equipment transmission by wireless network, by following
Ring redundancy check code deciphers described hidden pattern after carrying out error checking and correction, retrieve the classification of service code in described DBM,
Match from classification of service code be adapted to described hidden pattern encode and obtain the corresponding Item Information of coding, by wireless
Object information after retrieval and coupling is fed back to described device or equipment by network；
Described intelligent terminal is used for shooting the image of described hidden code holographic anti-counterfeiting film, the hidden code in parsing described image
Pattern, after the hidden pattern encryption that parsing is obtained by wireless network send to described data server enter line retrieval and
Join；
Described data server is used for receiving the hidden pattern of the encryption that intelligent terminal sends by wireless network, from data
In library module, retrieval service classification code, matches from classification of service code and encodes and obtain coding with described hidden pattern is adapted to
Item Information after retrieval and coupling is fed back to device or equipment by wireless network by corresponding Item Information.
8. system as claimed in claim 7 is it is characterised in that described wireless network is GPRS or 3G network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410117589.3A CN103903039B (en) | 2014-03-26 | 2014-03-26 | Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410117589.3A CN103903039B (en) | 2014-03-26 | 2014-03-26 | Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103903039A CN103903039A (en) | 2014-07-02 |
| CN103903039B true CN103903039B (en) | 2017-02-22 |
Family
ID=50994351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410117589.3A Active CN103903039B (en) | 2014-03-26 | 2014-03-26 | Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103903039B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146088B (en) | 2012-03-01 | 2021-09-17 | 系统科技解决方案公司 | Unique identification information from a feature of a mark |
| US20150379321A1 (en) | 2012-03-01 | 2015-12-31 | Sys-Tech Solutions, Inc. | Methods and a system for verifying the authenticity of a mark |
| US20150169928A1 (en) | 2012-03-01 | 2015-06-18 | Sys-Tech Solutions, Inc. | Methods and a system for verifying the identity of a printed item |
| CN106161919A (en) * | 2015-04-15 | 2016-11-23 | 阿里巴巴集团控股有限公司 | The method and apparatus of scanogram |
| JP6439056B2 (en) * | 2015-06-16 | 2018-12-19 | シス−テック ソリューションズ，インコーポレイテッド | Method and computing device for determining whether a mark is authentic |
| CN106682715A (en) * | 2015-11-11 | 2017-05-17 | 无锡百得包装材料有限公司 | Multimedia voice information anti-counterfeiting technique |
| CN106218254B (en) * | 2016-07-26 | 2018-10-19 | 汇源印刷包装科技（天津）股份有限公司 | A kind of method that printed matter glazing is anti-fake |
| CN106548485B (en) * | 2017-01-18 | 2023-11-21 | 上海朗研光电科技有限公司 | Nanoparticle fluorescent space coding anti-counterfeiting mark method |
| CN108725004B (en) * | 2017-04-24 | 2020-08-04 | 湖南正晨节能科技有限公司 | Printing method and printed matter information display method |
| CN107169777B (en) * | 2017-05-16 | 2020-12-22 | 王登顺 | Overlay code anti-counterfeiting method and system applying same |
| CN107480744B (en) * | 2017-05-17 | 2020-09-15 | 上海冠众光学科技有限公司 | Anti-counterfeit label generation method containing watermark information and anti-counterfeit label |
| CN107563774A (en) * | 2017-08-30 | 2018-01-09 | 浙江惠码科技有限公司 | A kind of commodity counterfeit prevention and trend analysis based on machine learning |
| SG10201801042QA (en) * | 2018-02-07 | 2019-09-27 | I Sprint Innovations Pte Ltd | Two-Dimensional Barcode Generating Method, Verification Method, Server and Two-Dimensional Barcode |
| CN108492713A (en) * | 2018-04-10 | 2018-09-04 | 三维码（厦门）网络科技有限公司 | Three-dimension code pupil image anti-counterfeiting system |
| CN108563973B (en) * | 2018-04-26 | 2019-12-17 | 冯贵良 | Combined type source tracing coded label and identification method thereof |
| CN109146370B (en) * | 2018-08-07 | 2021-08-10 | 景德镇陶瓷大学 | Method for confirming conveyed article by positioning shooting |
| CN109671350A (en) * | 2019-01-25 | 2019-04-23 | 武汉宇恩防伪技术有限公司 | A kind of manufacturing method of anti-fake photoetching film band |
| WO2020183493A1 (en) * | 2019-03-11 | 2020-09-17 | Vglens Solutions Private Limited | A security device, system of generating a security device and method thereof |
| CN110009615B (en) * | 2019-03-31 | 2020-06-19 | 深圳大学 | Image corner detection method and detection device |
| CN114615423A (en) * | 2019-09-12 | 2022-06-10 | 华为技术有限公司 | Method and equipment for processing callback stream |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102263316A (en) * | 2011-07-21 | 2011-11-30 | 山东泰宝防伪技术产品有限公司 | Disposal uncovered holographic electronic tag antenna, and manufacturing method and application thereof |
| CN102310672A (en) * | 2010-07-07 | 2012-01-11 | 顾泽苍 | Processing method for novel anti-counterfeiting label |
| CN204288255U (en) * | 2014-03-26 | 2015-04-22 | 深圳大学 | Hidden code holographic anti-counterfeiting film |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6629640B2 (en) * | 1995-12-18 | 2003-10-07 | Metrologic Instruments, Inc. | Holographic laser scanning method and system employing visible scanning-zone indicators identifying a three-dimensional omni-directional laser scanning volume for package transport navigation |
-
2014
- 2014-03-26 CN CN201410117589.3A patent/CN103903039B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102310672A (en) * | 2010-07-07 | 2012-01-11 | 顾泽苍 | Processing method for novel anti-counterfeiting label |
| CN102263316A (en) * | 2011-07-21 | 2011-11-30 | 山东泰宝防伪技术产品有限公司 | Disposal uncovered holographic electronic tag antenna, and manufacturing method and application thereof |
| CN204288255U (en) * | 2014-03-26 | 2015-04-22 | 深圳大学 | Hidden code holographic anti-counterfeiting film |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103903039A (en) | 2014-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103903039B (en) | Hidden code holographic anti-counterfeiting film and manufacturing method and recognition system thereof | |
| Ross et al. | Security in smart cities: A brief review of digital forensic schemes for biometric data | |
| CN111652223B (en) | Certificate identification method and device | |
| US20220198473A1 (en) | Method and apparatus for generating and querying traceability code of commodity | |
| EP3807792A1 (en) | Authenticating an identity of a person | |
| CN109784385A (en) | A kind of commodity automatic identifying method, system, device and storage medium | |
| Passos et al. | A review of deep learning‐based approaches for deepfake content detection | |
| Wu et al. | On the usefulness of color for kinship verification from face images | |
| JP2023539712A (en) | Generation of obfuscated identification templates for transaction validation | |
| De Las Heras et al. | Use case visual bag-of-words techniques for camera based identity document classification | |
| CN116664961A (en) | Intelligent identification method and system for anti-counterfeit label based on signal code | |
| Arora et al. | A review of techniques to detect the GAN-generated fake images | |
| CN117095471B (en) | Face counterfeiting tracing method based on multi-scale characteristics | |
| CN106301775A (en) | A kind of QR code encryption method based on RSA Algorithm | |
| CN105488529A (en) | Identification method and apparatus for source camera model of picture | |
| CN204288255U (en) | Hidden code holographic anti-counterfeiting film | |
| CN107563362B (en) | Method, client and system for evaluation operation | |
| CN109740546A (en) | A kind of forgery video detecting method of tampered region Jing Guo geometric transformation | |
| Faseela et al. | Spoof face recognition in video using KSVM | |
| Sabaghi et al. | Deep learning meets liveness detection: recent advancements and challenges | |
| Prabakar et al. | Hybrid deep learning model for copy move image forgery detection | |
| Bikku et al. | Deep Residual Learning for Unmasking DeepFake | |
| Lu et al. | M-commerce secured using web-enabled mobile biometric agents | |
| CN109583421A (en) | Face identification system and method | |
| Alanazi et al. | Understanding deepfakes: a comprehensive analysis of creation, generation, and detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent for invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 518000 Nanhai Road, Guangdong, Shenzhen, No. 3688, No. Applicant after: Shenzhen University Applicant after: SHENZHEN SHENDA AURORA TECHNOLOGY CO., LTD. Address before: 518000 Nanhai Road, Guangdong, Shenzhen, No. 3688, No. Applicant before: Shenzhen University Applicant before: Reflective Materials Manufactory Company SZU |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: SHENZHEN UNIVERSITY REFLECTIVE MATERIALS PLANT TO: SHENZHEN SHENDA AURORA TECHNOLOGY CO., LTD. |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Song Guangwei Inventor after: Wang Xiaobing Inventor after: Pan Feng Inventor after: Yu Hongfei Inventor after: Duan Yunfei Inventor after: Zhan Yifeng Inventor before: Song Guangwei Inventor before: Wang Xiaobing Inventor before: Pan Feng Inventor before: Yu Hongfei Inventor before: Duan Yunfei Inventor before: Zhan Yifeng |