CN109145703A - Intelligent identification method, device, equipment and medium - Google Patents
Intelligent identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN109145703A CN109145703A CN201810614076.1A CN201810614076A CN109145703A CN 109145703 A CN109145703 A CN 109145703A CN 201810614076 A CN201810614076 A CN 201810614076A CN 109145703 A CN109145703 A CN 109145703A
- Authority
- CN
- China
- Prior art keywords
- information
- stored
- face
- identification
- characteristic information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
- G06Q20/3821—Electronic credentials
- G06Q20/38215—Use of certificates or encrypted proofs of transaction rights
-
- 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
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The embodiment of the invention discloses a kind of intelligent identification method, device, equipment and media.This method comprises: obtaining fisrt feature information, fisrt feature information refers to the characteristic information of picture to be verified；Fisrt feature information and second feature information are compared, determines the picture similarity value between fisrt feature information and second feature information, second feature information is to search the characteristic information that the pre-stored information on block chain obtains by being pre-stored key assignments；When picture similarity value is greater than default picture similarity threshold, then picture to be verified passes through identification.The scheme provided according to embodiments of the present invention, the information such as true calligraphy and painting are first stored in block chain, when needing to identify the calligraphy and painting true and false, current calligraphy and painting information can be compared with the calligraphy and painting information being stored in block chain, the accuracy, confidence level and efficiency that identification not only can be improved, can also reduce the subjective factor artificially judged.
Description
Technical field
The present invention relates to block chain field more particularly to a kind of intelligent identification method, device, equipment and media.
Background technique
Calligraphy and painting auction and transaction all become increasingly prevalent on existing market, but since the authentic work of calligraphy and painting is fewer, city
Occur pseudo- calligraphy and painting on field more, so that it is some be ignorant of identification calligraphy and painting buy and/or seller is spoofed, loss is a large amount of
Money.
At present since the assay certificate of papery and calligraphy and painting are separation, only use certificate books body can not confirm calligraphy and painting
The true and false, therefore transaction requires to examine again every time.
Moreover, because the true and false of calligraphy and painting can only lean on expert or authoritative institution to identify, there are many subjective factor, cause to occur
The problem of, with a low credibility, low efficiency low to the accuracy of calligraphy and painting identification.
Summary of the invention
The embodiment of the present invention provides a kind of intelligent identification method, device, equipment and medium, can overcome it is artificial it is subjective because
Element, the automatic true and false for identifying picture, improves accuracy, confidence level and the efficiency of identification.
One side according to an embodiment of the present invention provides a kind of intelligent identification method, comprising: fisrt feature information is obtained,
The fisrt feature information refers to the characteristic information of picture to be verified；
The fisrt feature information and second feature information are compared, determines the fisrt feature information and the second feature
Picture similarity value between information, second feature information are to search the pre-stored information on block chain by being pre-stored key assignments
Obtained characteristic information；
When the picture similarity value is greater than default picture similarity threshold, then the picture to be verified passes through identification.
According to another aspect of an embodiment of the present invention, a kind of intelligent identification apparatus is provided, comprising: first obtains module, the
One contrast module and the first identification module；
Described first obtains module, and for obtaining fisrt feature information, the fisrt feature information refers to picture to be verified
Characteristic information；
First contrast module determines described first for comparing the fisrt feature information and second feature information
Picture similarity value between characteristic information and the second feature information, second feature information are searched by pre-stored key assignments
The characteristic information that pre-stored information on block chain obtains；
The first identification module, it is for being greater than default picture similarity threshold when the picture similarity value, then described
Picture to be verified passes through identification.
It is according to an embodiment of the present invention in another aspect, provide a kind of terminal device, memory, processor, communication interface and
Bus；
The memory, the processor are connected by the bus with the communication interface and complete mutual lead to
Letter；
The memory is for storing program code；
The processor is run by reading the executable program code stored in the memory can be performed with described
The corresponding program of program code, for executing intelligent identification method described in first aspect.
It is according to an embodiment of the present invention in another aspect, provide a kind of computer storage medium, described instruction is worked as in including instruction
When running on computers, the computer is made to execute intelligent identification method described in first aspect.
Intelligent identification method, device, equipment and medium according to embodiments of the present invention, the information such as true calligraphy and painting are first stored
Into block chain, when there is bargain transaction, when needing to identify the calligraphy and painting true and false, by current calligraphy and painting information and block can be stored in
Calligraphy and painting information in chain compares, and by using the mode of block chain, the accuracy of identification not only can be improved, can also subtract
Few subjective factor artificially judged.Accuracy, confidence level and the efficiency of identification can also be improved simultaneously.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, for those of ordinary skill in the art, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 is the structural schematic diagram for showing the embodiment of the present invention and depositing card process；
Fig. 2 is the flow chart for showing intelligence identification method of the embodiment of the present invention；
Fig. 3 is the flow chart for showing another embodiment of the present invention intelligence identification method；
Fig. 4 is the structural schematic diagram for showing face verification of the embodiment of the present invention；
Fig. 5 is the structural schematic diagram for showing intelligence identification apparatus of the embodiment of the present invention；
Fig. 6 is the structural schematic diagram for showing another embodiment of the present invention intelligence identification apparatus；
Fig. 7 is the example for showing the calculating equipment that intelligent identification method and device according to an embodiment of the present invention may be implemented
The structure chart of property hardware structure.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make mesh of the invention
, technical solution and advantage be more clearly understood, with reference to the accompanying drawings and embodiments, the present invention is further retouched in detail
It states.It should be understood that specific embodiment described herein is only configured to explain the present invention, it is not configured as limiting the present invention.
To those skilled in the art, the present invention can be real in the case where not needing some details in these details
It applies.Below the description of embodiment is used for the purpose of better understanding the present invention to provide by showing example of the invention.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including
There is also other identical elements in the process, method, article or equipment of the element.
Fig. 1 is the structural schematic diagram for showing the embodiment of the present invention and depositing card process.
As shown in Figure 1, including two parts during depositing card.First part is that author information deposits card, when author is as picture
After family or expert of calligraphy and painting log in APP, calling mobile phone camera shooting human face photo carries out recognition of face and then obtains face characteristic,
The photo of shooting is extracted face characteristic by face recognition algorithms.Then author's essential information is inputted, the author is basic
Information includes name, gender, date of birth etc..Then face characteristic and the generation of author's essential information is combined to be stored in block chain
Digital certificate, which includes: face characteristic, private key and public key.
Second part is that calligraphy and painting information deposits card, makes based on the numerical characteristic of calligraphy and painting digital certificate, calls scanning dress
Shooting calligraphy and painting photo is set, calligraphy and painting photo is called numerical characteristic using the value that Hash hash algorithm is calculated.Then by
The creator of calligraphy and painting, artist and calligraphist are digitally signed the numerical characteristic, and the digital certificate obtained after signature is stored in
On the block chain of more mechanism amalgamated consolidations, so that digital certificate is not tampered.When calligraphy and painting needs to identify, from block chain
Upper reading number certificate, according to the numerical characteristic and calligraphy and painting progress Auto-matching in digital certificate.
It is below exactly the true and false of the digital certificate being stored in using these in block chain and digital signature verification calligraphy and painting.
In order to better understand the present invention, below in conjunction with attached drawing, intelligence mirror according to an embodiment of the present invention is described in detail
Determine method, apparatus, equipment and medium, it should be noted that these embodiments are not for limiting the scope of the present disclosure.
Fig. 2 is the flow chart for showing intelligence identification method of the embodiment of the present invention.As shown in Fig. 2, the intelligence in the present embodiment
Identification method 200 the following steps are included:
Step S210, obtains fisrt feature information, and fisrt feature information refers to the characteristic information of picture to be verified.
In this step, the fisrt feature information of acquisition is mainly the picture that some calligraphies and paintings, seal etc. need to verify the true and false
Information.Scanning calligraphy and painting by scanning means, perhaps seal is such as: the photo of calligraphy and painting or seal is shot using mobile phone, including whole
Width works are taken pictures takes pictures with seal, and the photo upload of shooting is to server end, and trained convolution is refreshing for server end use
The feature that these pictures are extracted through network model obtains the characteristic information for the picture that these need to verify calligraphy and painting and/or seal.
Step S220, comparison fisrt feature information and second feature information determine that fisrt feature information and second feature are believed
Picture similarity value between breath, second feature information are obtained by being pre-stored pre-stored information of the key assignments lookup on block chain
The characteristic information arrived.
In this step, in qualification process, firstly, according to the i.e. pre-stored key assignments of the calligraphy and painting key assignments key of submission in block
Searched on chain and deposit the characteristic information of chain, then by the characteristic information for extracting calligraphy and painting and the characteristic information searched by key assignments into
Row compares, and picture similarity value is obtained, so that it is determined that whether calligraphy and painting is true calligraphy and painting.
Step S230, when picture similarity value is greater than default picture similarity threshold, then picture to be verified passes through identification.
In this step, the characteristic similarity value of two pictures is more than certain threshold value, decides that this same width of two pictures
Calligraphy and painting works.Second feature information be extracted by preparatory trained convolutional neural networks, including seal feature and
The textural characteristics etc. of paper in background.
Intelligent identification method according to embodiments of the present invention, the information of true calligraphy and painting is first stored in block chain, when
There is bargain transaction, when needing to identify the calligraphy and painting true and false, current calligraphy and painting information and the calligraphy and painting being stored in block chain can be believed
Breath compares.The accuracy of identification not only can be improved, the subjective factor artificially judged can also be reduced.It can also mention simultaneously
Accuracy, confidence level and the efficiency of height identification.
Fig. 3 is the flow chart for showing another embodiment of the present invention intelligence identification method.Fig. 4 is to show people of the embodiment of the present invention
The structural schematic diagram of face verifying.
In one embodiment, step Fig. 3 identical or equivalent with Fig. 2 uses identical label.As shown in figure 3, method 300
It is substantially identical to method 200, the difference is that, method 300 further include:
After executing the step S230, following steps can also be performed:
Step S240, obtains the first face characteristic information, and the first face characteristic information refers to the feature letter of face to be verified
Breath.
In this step, some face recognition technologies of use, the face recognition technology may include: the people of geometrical characteristic
Face recognition method, based on the face identification method of eigenface (PCA), the face identification method of neural network, elastic graph matching
Face identification method, the face identification method of line segment Hausdorff distance (LHD), support vector machines (SVM) recognition of face side
Method etc..And it can also be related to the algorithm of some recognitions of face in these face recognition technologies.
The face recognition algorithms used in the embodiment of the present invention can be the recognizer based on human face characteristic point
(Feature-based recognition algorithms), the recognizer (Appearance- based on whole picture facial image
Based recognition algorithms), recognizer (the Template-based recognition based on template
Algorithms algorithm (the Recognition algorithms using neural) and using neural network identified
Network) etc..
Step S250 compares the first face characteristic information and the second face characteristic information, determines human face similarity degree value, and second
Face characteristic information is obtained according to the pre-stored pre-stored information of digital certificate and pre-stored public key lookup on block chain
Face characteristic information.
As shown in figure 4, the first face characteristic information can be obtained in such a way that living body is tested in the embodiment of the present invention, than
Such as: enrolling the video information of human eye, the characteristic information of face is extracted by the human eye video information of admission；It can also lead to
The picture for crossing identification face carries out feature extraction, face more to be verified by the depth convolutional neural networks model of pre-training
Characteristic information and the face characteristic information that is stored in advance on block chain, human face similarity degree value is determined, so that it is determined that this two
Whether face is identical.
In one example, which comprises at least one of the following: the corresponding work title letter of picture
Breath, the corresponding works dimension information of picture, the corresponding creation of works age information of picture, the corresponding works classification information of picture,
The corresponding works material information of picture and the corresponding works subject matter information of picture.
Step S260, when human face similarity degree value is greater than default human face similarity degree value, then face to be verified passes through identification.
Step S270 is stored in pre- on block chain after face to be verified is by identification by pre-stored private key acquisition
Digital certificate.
Intelligent identification method through the embodiment of the present invention, the characteristic information of face to be verified and pre-stored face is special
Reference breath compares, so that automatic identification face to be verified, can greatly improve the safety of user in this way, improve identification
Accuracy, confidence level and efficiency.
In one embodiment, pre-stored key assignments refers to the unique asset mark fed back when storing pre-stored information on block chain
Know ID.
It is understood that the essential information of characteristic information and calligraphy and painting based on calligraphy and painting, then using the public key of artist and
Private key encrypts the characteristic information of calligraphy and painting and the essential information of calligraphy and painting, forms digitlization assets.The digitlization assets are deposited
In block chain, which is saved in block chain network for storage, while server returns to the whole network unique asset mark ID,
The unique asset identifies the identification that ID is used for calligraphy and painting.The authenticity of calligraphy and painting information can be guaranteed by identifying ID by the unique asset,
Improve accuracy, the confidence level of identification.
In one embodiment, fisrt feature information, second feature information, the first face characteristic information and pre-stored information are equal
It is the information by the depth convolutional neural networks model extraction of pre-training.
It is understood that pre-processing first to face or picture in the embodiment of the present invention, depth is then trained
Convolutional neural networks model calculates similarity using feature vector finally by depth convolutional neural networks model extraction feature,
Realize recognition of face.Here is training depth convolutional neural networks model in the embodiment of the present invention, then uses depth convolutional Neural
The process of network model progress recognition of face:
The picture of step 1, pretreatment face to be verified
(1) face in picture is detected；
(2) key point (two, nose, the both sides corners of the mouth) in face is detected；
(3) face alignment operation is carried out；
(4) by face picture size normalization, such as the pixel of face picture size normalization to 112 × 96.
Step 2, training depth convolutional neural networks model
(1) the depth convolutional neural networks model based on residual error study is built；
(2) propagated forward calculates loss error (SoftMax Loss)；
(3) backpropagation loss error (SoftMax Loss) updates model parameter；
(4) trained depth convolutional neural networks model is obtained.
Step 3, recognition of face
(1) test picture passes through depth convolutional neural networks model；
(2) feature vector is extracted；
(3) similarity calculation is carried out using feature vector；
(4) recognition result is exported.
In one embodiment, step S240 may comprise steps of:
Step S241 obtains the eyes video information of face to be verified in preset time period.
Step S242 determines multiple key point informations of every frame pictorial information in eyes video information.
Step S243 determines eye state information according to multiple key point informations, using eye state information as the first
Face characteristic information.
Believed it is understood that the embodiment of the present invention obtains face characteristic information and can be by the video for enrolling human eye
Breath is changed by the human eye of every frame picture in identification video information, that is, detects 12 key point (each eyes 6 of people's eyes
It is a).These key points include canthus, upper lower eyelid profile etc..By judging the distance between upper lower eyelid key point and left and right
The ratio of canthus distance judges the opening and closings of eyes.If upper lower eyelid distance is less than certain with right and left eyes angular distance ratio
Threshold value, then regarding as eyes is closed state, otherwise to open state.Because everyone eyes size has difference, this
A threshold value varies with each individual, and is dynamic acquisition, i.e., using the maximum value of ratio in all video frames as the upper bound, minimum value is made
For lower bound.Usual situation lower bound is 0, because being closed state, what upper lower eyelid was connected together, distance is 0.
With reference to the accompanying drawing, device according to an embodiment of the present invention is discussed in detail.
Fig. 5 is the structural schematic diagram for showing intelligence identification apparatus of the embodiment of the present invention.As shown in figure 5, intelligent identification apparatus
500 include:
First obtains module 510, the first contrast module 520 and the first identification module 530.
First obtains module 510, and for obtaining fisrt feature information, fisrt feature information refers to the feature of picture to be verified
Information.
First contrast module 520, for comparing fisrt feature information and second feature information, determine fisrt feature information with
Picture similarity value between second feature information, second feature information are pre- on block chain by pre-stored key assignments lookup
The characteristic information that storage information obtains.
First identification module 530 is greater than default picture similarity threshold for working as picture similarity value, then picture to be verified
Pass through identification.
Intelligent identification apparatus according to embodiments of the present invention, the information of true calligraphy and painting is first stored in block chain, when
There is bargain transaction, when needing to identify the calligraphy and painting true and false, current calligraphy and painting information and the calligraphy and painting being stored in block chain can be believed
Breath compares.The accuracy of identification not only can be improved, the subjective factor artificially judged can also be reduced.It can also mention simultaneously
Accuracy, confidence level and the efficiency of height identification.
Fig. 6 is the structural schematic diagram for showing another embodiment of the present invention intelligence identification apparatus, and Fig. 6 is identical as Fig. 5 or equivalent
Structure use identical label.As shown in fig. 6, intelligent identification apparatus 600 is substantially identical to intelligent identification apparatus 500, it is different
Place is, intelligent identification apparatus 600 further include:
Second obtains module 540, the second contrast module 550 and the second identification module 560.
Second obtains module 540, and for obtaining the first face characteristic information, the first face characteristic information refers to witness to be tested
The characteristic information of face.
Second contrast module 550 determines face phase for comparing the first face characteristic information and the second face characteristic information
Like angle value, the second face characteristic information is pre-stored on block chain according to digital certificate and pre-stored public key lookup is pre-stored
The face characteristic information that information obtains.
Second identification module 560, for being greater than default human face similarity degree value when human face similarity degree value, then face to be verified is logical
Cross identification；And for being stored in prestoring on block chain by pre-stored private key acquisition after face to be verified is by identification
Store up digital certificate.
In one embodiment, pre-stored key assignments refers to the unique asset mark fed back when storing pre-stored information on block chain
Know ID.
In one embodiment, fisrt feature information, second feature information, the first face characteristic information and pre-stored information are equal
It is the information by the depth convolutional neural networks model extraction of pre-training.
In one embodiment, second module 540 is obtained, comprising: acquiring unit 541 and determination unit 542.
Acquiring unit 541, for obtaining the eyes video information of face to be verified in preset time period.
Determination unit 542, for determining multiple key point informations of every frame pictorial information in eyes video information；And it uses
In determining eye state information according to multiple key point informations, using eye state information as the first face characteristic information.
In one embodiment, picture to be verified comprises at least one of the following: calligraphy and painting picture and seal picture.
In one embodiment, pre-stored information comprises at least one of the following: pre-stored pictorial information, pre-stored face information
With pre-stored author's essential information.
In one embodiment, pre-stored digital certificate is raw according to pre-stored face information and pre-stored author's essential information
At certificate.
In one embodiment, pre-stored pictorial information comprises at least one of the following: seal characteristic information, corresponding with seal
The texture feature information of background paper.
In one embodiment, it is pre-stored author's essential information to comprise at least one of the following: the corresponding work title letter of picture
Breath, the corresponding works dimension information of picture, the corresponding creation of works age information of picture, the corresponding works classification information of picture,
The corresponding works material information of picture and the corresponding works subject matter information of picture.
The other details of intelligence identification apparatus according to embodiments of the present invention are with more than in conjunction with Fig. 1 to Fig. 4 description according to originally
The method of inventive embodiments is similar, and details are not described herein.
The intelligent identification method and device according to embodiments of the present invention described in conjunction with Fig. 1 to Fig. 4 can by removably or
Person, which is fixedly mounted in, calculates equipment realization.Fig. 7 is to show to can be realized intelligent identification method and dress according to embodiments of the present invention
The structure chart of the exemplary hardware architecture for the calculating equipment set.As shown in fig. 7, calculating equipment 700 includes input equipment 701, defeated
Incoming interface 702, central processing unit 703, memory 704, output interface 705 and output equipment 706.Wherein, input interface
702, central processing unit 703, memory 704 and output interface 705 are connected with each other by bus 710,701 He of input equipment
Output equipment 706 is connect by input interface 702 and output interface 705 with bus 710 respectively, so with calculating equipment 700
Other assemblies connection.Specifically, input equipment 701 is received from external input information, and will be inputted by input interface 702
Information is transmitted to central processing unit 703；Central processing unit 703 is based on the computer executable instructions pair stored in memory 704
Input information is handled to generate output information, in memory 704, then output information is temporarily or permanently stored
Output information is transmitted to output equipment 706 by output interface 705；Output information is output to calculating and set by output equipment 706
Standby 700 outside is for users to use.
That is, calculating equipment shown in Fig. 7 also may be implemented as including: to be stored with computer executable instructions
Memory；And processor, the processor may be implemented when executing computer executable instructions that Fig. 1 to Fig. 6 to be combined to describe
Intelligent identification method and device.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But method process of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after understanding spirit of the invention, or suitable between changing the step
Sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention is used to execute program or the generation of required task
Code section.Perhaps code segment can store in machine readable media program or the data-signal by carrying in carrier wave is passing
Defeated medium or communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.
The example of machine readable media includes electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), soft
Disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, inline
The computer network of net etc. is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
The above description is merely a specific embodiment, it is apparent to those skilled in the art that,
For convenience of description and succinctly, the system, module of foregoing description and the specific work process of unit can refer to preceding method
Corresponding process in embodiment, details are not described herein.It should be understood that scope of protection of the present invention is not limited thereto, it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.
Claims (11)
1. a kind of intelligence identification method, which is characterized in that the described method includes:
Fisrt feature information is obtained, the fisrt feature information refers to the characteristic information of picture to be verified；
The fisrt feature information and second feature information are compared, determines the fisrt feature information and the second feature information
Between picture similarity value, second feature information is to search pre-stored information on block chain by being pre-stored key assignments to obtain
Characteristic information；
When the picture similarity value is greater than default picture similarity threshold, then the picture to be verified passes through identification.
2. the method according to claim 1, wherein the method, further includes:
The first face characteristic information is obtained, first face characteristic information refers to the characteristic information of face to be verified；
First face characteristic information and the second face characteristic information are compared, determines human face similarity degree value, second face
Characteristic information is obtained according to the pre-stored pre-stored information of digital certificate and pre-stored public key lookup on the block chain
The face characteristic information arrived；
When the human face similarity degree value is greater than default human face similarity degree value, then the face to be verified passes through identification；
After the face to be verified is by identification, is obtained by pre-stored private key and prestored described in being stored on the block chain
Store up digital certificate.
3. being stored on the block chain the method according to claim 1, wherein the pre-stored key assignments refers to
The unique asset mark ID fed back when the pre-stored information.
4. according to the method described in claim 2, it is characterized in that, the fisrt feature information, the second feature information, institute
It states the first face characteristic information and the pre-stored information is the depth convolutional neural networks model extraction by pre-training
Information.
5. according to the method described in claim 2, it is characterized in that, the first face characteristic information of the acquisition, comprising:
Obtain the eyes video information of the face to be verified in preset time period；
Determine multiple key point informations of every frame pictorial information in the eyes video information；
Eye state information is determined according to the multiple key point information, using the eye state information as first face
Characteristic information.
6. according to the method described in claim 2, it is characterized in that, the pre-stored information comprises at least one of the following: prestoring
Store up pictorial information, pre-stored face information and pre-stored author's essential information.
7. according to the method described in claim 6, it is characterized in that, the pre-stored digital certificate is according to the pre-stored people
The certificate that face information and pre-stored author's essential information generate.
8. a kind of intelligence identification apparatus, which is characterized in that described device includes:
First obtains module, the first contrast module and the first identification module；
Described first obtains module, and for obtaining fisrt feature information, the fisrt feature information refers to the spy of picture to be verified
Reference breath；
First contrast module determines the fisrt feature for comparing the fisrt feature information and second feature information
Picture similarity value between information and the second feature information, second feature information are to be searched by pre-stored key assignments in area
The characteristic information that pre-stored information on block chain obtains；
The first identification module, it is for being greater than default picture similarity threshold when the picture similarity value, then described to be tested
Card picture passes through identification.
9. device according to claim 8, which is characterized in that described device, further includes:
Second obtains module, the second contrast module and the second identification module；
Described second obtains module, and for obtaining the first face characteristic information, first face characteristic information refers to be verified
The characteristic information of face；
Second contrast module determines face for comparing first face characteristic information and the second face characteristic information
Similarity value, second face characteristic information are according to pre-stored digital certificate and pre-stored public key lookup in the block chain
On the obtained face characteristic information of the pre-stored information；
The second identification module, it is for being greater than default human face similarity degree value when the human face similarity degree value, then described to be verified
Face passes through identification；And it is used for
After the face to be verified is by identification, is obtained by pre-stored private key and prestored described in being stored on the block chain
Store up digital certificate.
10. a kind of terminal device characterized by comprising
Memory, processor, communication interface and bus；
The memory, the processor are connected by the bus with the communication interface and complete mutual communication；
The memory is for storing program code；
The processor is run and the executable program by reading the executable program code stored in the memory
The corresponding program of code, for executing intelligent identification method as described in any one of claim 1 to 7.
11. a kind of computer storage medium, which is characterized in that including instruction, when described instruction is run on computers, make institute
It states computer and executes intelligent identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810614076.1A CN109145703A (en) | 2018-06-14 | 2018-06-14 | Intelligent identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810614076.1A CN109145703A (en) | 2018-06-14 | 2018-06-14 | Intelligent identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109145703A true CN109145703A (en) | 2019-01-04 |
Family
ID=64802026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810614076.1A Pending CN109145703A (en) | 2018-06-14 | 2018-06-14 | Intelligent identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145703A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009027A (en) * | 2019-03-28 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Comparison method, device, storage medium and the electronic device of image |
| CN110751481A (en) * | 2019-09-28 | 2020-02-04 | 北京瑞卓喜投科技发展有限公司 | Digital asset right confirming method and device |
| CN112632305A (en) * | 2021-01-05 | 2021-04-09 | 安徽大学 | Photo file management method and system based on block chain technology |
| CN117687313A (en) * | 2023-12-29 | 2024-03-12 | 广东福临门世家智能家居有限公司 | Intelligent household equipment control method and system based on intelligent door lock |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991573A (en) * | 2017-04-07 | 2017-07-28 | 中链科技有限公司 | Art work fidelity method and server based on block chain technology |
| CN107147652A (en) * | 2017-05-18 | 2017-09-08 | 电子科技大学 | A kind of safety fusion authentication method of the polymorphic identity of user based on block chain |
| CN107395360A (en) * | 2017-07-23 | 2017-11-24 | 刘志强 | The method that a kind of historical relic and art work numeral based on block chain technology deposit card |
| CN107679872A (en) * | 2017-09-28 | 2018-02-09 | 中链科技有限公司 | Art work discrimination method and device, electronic equipment based on block chain |
| CN107786547A (en) * | 2017-09-30 | 2018-03-09 | 厦门快商通信息技术有限公司 | A kind of auth method based on block chain, device and computer-readable recording medium |
-
2018
- 2018-06-14 CN CN201810614076.1A patent/CN109145703A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991573A (en) * | 2017-04-07 | 2017-07-28 | 中链科技有限公司 | Art work fidelity method and server based on block chain technology |
| CN107147652A (en) * | 2017-05-18 | 2017-09-08 | 电子科技大学 | A kind of safety fusion authentication method of the polymorphic identity of user based on block chain |
| CN107395360A (en) * | 2017-07-23 | 2017-11-24 | 刘志强 | The method that a kind of historical relic and art work numeral based on block chain technology deposit card |
| CN107679872A (en) * | 2017-09-28 | 2018-02-09 | 中链科技有限公司 | Art work discrimination method and device, electronic equipment based on block chain |
| CN107786547A (en) * | 2017-09-30 | 2018-03-09 | 厦门快商通信息技术有限公司 | A kind of auth method based on block chain, device and computer-readable recording medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009027A (en) * | 2019-03-28 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Comparison method, device, storage medium and the electronic device of image |
| CN110751481A (en) * | 2019-09-28 | 2020-02-04 | 北京瑞卓喜投科技发展有限公司 | Digital asset right confirming method and device |
| CN112632305A (en) * | 2021-01-05 | 2021-04-09 | 安徽大学 | Photo file management method and system based on block chain technology |
| CN117687313A (en) * | 2023-12-29 | 2024-03-12 | 广东福临门世家智能家居有限公司 | Intelligent household equipment control method and system based on intelligent door lock |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220058426A1 (en) | Object recognition method and apparatus, electronic device, and readable storage medium | |
| US10789465B2 (en) | Feature extraction and matching for biometric authentication | |
| US20220012487A1 (en) | Systems and methods for classifying payment documents during mobile image processing | |
| CN109145703A (en) | Intelligent identification method, device, equipment and medium | |
| US8064653B2 (en) | Method and system of person identification by facial image | |
| US8320643B2 (en) | Face authentication device | |
| CN104217202B (en) | Information identifying method, equipment and system | |
| CN110309706A (en) | Face critical point detection method, apparatus, computer equipment and storage medium | |
| CN110222728B (en) | Training method and system of article identification model and article identification method and equipment | |
| US20170262472A1 (en) | Systems and methods for recognition of faces e.g. from mobile-device-generated images of faces | |
| CN106203387A (en) | Face verification method and system | |
| AU2017200935B2 (en) | Method for securing and verifying a document | |
| WO2016084072A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| JP2011510365A (en) | Document verification using dynamic document identification framework | |
| CN111191568A (en) | Method, device, equipment and medium for identifying copied image | |
| CN111079816A (en) | Image auditing method and device and server | |
| US20210390667A1 (en) | Model generation | |
| CN111291773A (en) | Feature identification method and device | |
| CN110428027A (en) | Fake method, device, equipment and medium are tested in identification based on LCD antifalsification label | |
| Hirofumi et al. | Did You Use My GAN to Generate Fake? Post-hoc Attribution of GAN Generated Images via Latent Recovery | |
| CN114373213A (en) | Juvenile identity recognition method and device based on face recognition | |
| US11250254B2 (en) | Methods and systems for detecting photograph replacement in a photo identity document | |
| CN115116147B (en) | Image recognition, model training, living body detection method and related device | |
| EP4266264A1 (en) | Unconstrained and elastic id document identification in an rgb image | |
| CN110688972B (en) | System and method for improving face generation performance |
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: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |