CN108694357A - Method, apparatus and computer storage media for In vivo detection - Google Patents
Method, apparatus and computer storage media for In vivo detection Download PDFInfo
- Publication number
- CN108694357A CN108694357A CN201710230110.0A CN201710230110A CN108694357A CN 108694357 A CN108694357 A CN 108694357A CN 201710230110 A CN201710230110 A CN 201710230110A CN 108694357 A CN108694357 A CN 108694357A
- Authority
- CN
- China
- Prior art keywords
- input data
- attack
- sample database
- vivo detection
- result
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Abstract
An embodiment of the present invention provides a kind of method, apparatus and computer storage media for In vivo detection, this method includes:Obtain input data;In vivo detection is carried out to the input data using detection algorithm;If the result of the In vivo detection determines that the input data is non-living body, automatic marking is carried out to the input data;Input data after the mark is added to attack sample database.It can be seen that the embodiment of the present invention is labeled input data when the result of In vivo detection is non-living body, and the input data after mark is added to attack sample database, it can realize automation mark, avoid consuming a large amount of manpower, so as to greatly save human cost.
Description
Technical field
The present invention relates to field of image recognition, relate more specifically to a kind of method, apparatus for In vivo detection and calculating
Machine storage medium.
Background technology
Currently, In vivo detection system is increasingly being applied to the field that security protection, finance, social security etc. need authentication
In.For example, when carrying out authentication using face etc., need to take precautions against the attacks such as photo, mask.
Detection algorithm used by current In vivo detection system is based on attack sample database and biometric sample
Database is obtained by training, and attack sample database therein needs a large amount of manpower to be labeled, and brings pole
Big manpower costs.
Invention content
The present invention is proposed in view of the above problem.The present invention provides a kind of method, apparatus for In vivo detection
And computer storage media, automatic marking can be carried out to input data in the result based on In vivo detection, so as to save
Human cost.
According to the first aspect of the invention, a kind of method for In vivo detection is provided, including:
Obtain input data;
In vivo detection is carried out to the input data using detection algorithm;
If the result of the In vivo detection determines that the input data is non-living body, the input data is carried out certainly
Dynamic mark;
Input data after the mark is added to attack sample database.
Illustratively, further include:If the result of the In vivo detection determines that the input data is live body, will be described
Input data is added to biometric sample database.
Illustratively, described that the input data is labeled, including:The input data is analyzed, and root
It is labeled according to the result of the analysis.
Illustratively, the result of the analysis is the attack type belonging to the input data, described to the input number
According to being analyzed, and it is labeled according to the result of the analysis, including:Judged belonging to the input data using sorting algorithm
Attack type, and the input data is labeled based on the attack type, wherein the sorting algorithm is by described
Attack sample database is trained.
Illustratively, described that the input data is analyzed, and be labeled according to the result of the analysis, also wrap
It includes:If the attack type belonging to the input data can not be determined, warning information is generated, in order to which administrative staff are into pedestrian
Work marks.
Illustratively, further include:Regularly acquisition attack sample, and the attack sample acquired is added to the attack
Sample database.
Illustratively, further include:According to the attack sample database after the addition and the biological characteristic after the addition
Sample database is trained, the detection algorithm after being optimized.
Illustratively, the method is executed by high in the clouds.
Second aspect provides a kind of device for In vivo detection, including:
Acquisition module, for obtaining input data;
In vivo detection module, for carrying out In vivo detection to the input data using detection algorithm;
Labeling module, if the result for the In vivo detection determines that the input data is non-living body, to described
Input data carries out automatic marking;
Add module, for the input data after the mark to be added to attack sample database.
The device is implemented for the method that In vivo detection is used for shown in aforementioned first aspect and each example.
The third aspect provides a kind of device for In vivo detection, including memory and processor, and memory is for depositing
Store up instruction code;Processor is used for live body to realize for executing described instruction code described in first aspect and each example
The method of detection.
Fourth aspect provides a kind of computer storage media, is stored thereon with computer program, the computer program
The method for In vivo detection described in first aspect and each example is realized when being executed by processor.
It can be seen that the embodiment of the present invention is labeled input data when the result of In vivo detection is non-living body, and
Input data after mark is added to attack sample database, automation mark can be realized, avoid consuming a large amount of manpower,
So as to greatly save human cost
Description of the drawings
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used for providing further understanding the embodiment of the present invention, and constitutes explanation
A part for book is not construed as limiting the invention for explaining the present invention together with the embodiment of the present invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 is a schematic block diagram of the electronic equipment of the embodiment of the present invention;
Fig. 2 is a schematic flow chart of the method for In vivo detection of the embodiment of the present invention;
Fig. 3 is another schematic flow chart of the method for In vivo detection of the embodiment of the present invention;
Fig. 4 is a schematic block diagram of the device for In vivo detection of the embodiment of the present invention;
Fig. 5 is another schematic block diagram of the device for In vivo detection of the embodiment of the present invention.
Specific implementation mode
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiment of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
The embodiment of the present invention can be applied to electronic equipment, and Fig. 1 show one of the electronic equipment of the embodiment of the present invention
Schematic block diagram.Electronic equipment 10 shown in FIG. 1 include one or more processors 102, one or more storage device 104,
Input unit 106, output device 108, imaging sensor 110 and one or more non-image sensors 114, these components are logical
Cross bus system 112 and/or other forms interconnection.It should be noted that the component and structure of electronic equipment 10 shown in FIG. 1 only show
Example property, and not restrictive, as needed, the electronic equipment can also have other assemblies and structure.
The processor 102 may include CPU 1021 and GPU 1022 or have data-handling capacity and/or instruction
The processing unit of the other forms of executive capability, such as field programmable gate array (Field-Programmable Gate
Array, FPGA) or advanced reduced instruction set machine (Advanced RISC (Reduced Instruction Set
Computer) Machine, ARM) etc., and processor 102 can control other components in the electronic equipment 10 to execute
Desired function.
The storage device 104 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory 1041 and/or nonvolatile memory
1042.The volatile memory 1041 for example may include random access memory (Random Access Memory, RAM)
And/or cache memory (cache) etc..The nonvolatile memory 1042 for example may include read-only memory
(Read-Only Memory, ROM), hard disk, flash memory etc..One or more can be stored on the computer readable storage medium
A computer program instructions, processor 102 can run described program instruction, to realize various desired functions.In the meter
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
The various data etc. generated.
The input unit 106 can be the device that user is used for inputting instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 108 can export various information (such as image or sound) to external (such as user), and
May include one or more of display, loud speaker etc..
Described image sensor 110 can shoot the desired image of user (such as photo, video etc.), and will be captured
Image be stored in the storage device 104 for other components use.
When note that the component and structure of electronic equipment shown in FIG. 1 10 are only exemplary, although the electronics shown in Fig. 1
Equipment 10 includes multiple and different devices, but as needed, some of which device can not be necessary, some of which
The quantity of device can be more etc., and the present invention does not limit this.
The embodiment of the present invention can also be applied to server, and server is properly termed as high in the clouds or cloud server.The present invention
This is not limited.
Fig. 2 is a schematic flow chart of the method for In vivo detection of the embodiment of the present invention.Method shown in Fig. 2
Including:
S101 obtains input data.
Input data can be image data or video data etc..Also, the input data includes biological information,
For example, input data includes facial image etc..
Illustratively, input data can be acquire in real time or can be obtained from user terminal.
As an example, method shown in Fig. 2 can be executed by electronic equipment.Optionally, input data can be by the electricity
What sub- equipment acquired in real time, specifically can in real time it be acquired by image collecting device.Such as image collecting device can be
Camera or camera etc..Optionally, input data can be obtained from specific source by electronic equipment, such as can be from depositing
The picture for previously acquiring and storing is obtained in reservoir.
As another example, method shown in Fig. 2 can be executed by server (or high in the clouds).Optionally, input data can be with
It is to be obtained from user terminal by server, that is to say, that input data can be uploaded to server by user terminal.Wherein,
User terminal can acquire input data in real time by image collecting device, be inputted alternatively, user terminal can be obtained from specific source
Data.Wherein, user terminal can be mobile terminal where user, such as smart mobile phone, tablet computer etc..
S102 carries out In vivo detection using detection algorithm to the input data.
Wherein, detection algorithm can be passed through according to existing attack sample database and biometric sample database
What training obtained.
Illustratively, detection algorithm can be the method for the more existing machine learning based on big data, for example, neural
Network (Neural Network, NN) algorithm, support vector machines (Support Vector Machine, SVM) etc..
By taking neural network algorithm as an example, input data can be input in neural network by S102, to judge the input number
According to whether being live body.
If the result judged is yes, i.e. the result of the In vivo detection of S102 determines that the input data is live body, then by institute
It states input data and is added to biometric sample database, as shown in Figure 3.If the result judged is no, i.e. the live body of S102 is examined
The result of survey determines that the input data is non-living body (attacking), then executes S103.
S103, if the result of the In vivo detection determines that the input data is non-living body, to the input data
Carry out automatic marking.
Illustratively, the input data is labeled may include to the attribute of input data (such as:Non-living body inputs
Data) or the various information such as type (such as attack type) be labeled.Wherein, described to be labeled as automatic marking, i.e., by calculating
The mark that machine executes.
Illustratively, the input data can be analyzed, and is labeled according to the result of the analysis.
As an example, sorting algorithm may be used and judge attack type belonging to the input data, and attacked based on described
Type is hit to be labeled the input data.Wherein, the result of the analysis is the attack type belonging to the input data,
The sorting algorithm is trained to obtain by the attack sample database.
Wherein, sorting algorithm is referred to as attack type algorithm.It illustratively, can be according to existing attack sample number
Attack type algorithm is obtained according to library is trained, and the attack type belonging to input data is judged using the attack type algorithm.Its
In, existing attack sample database includes the attack sample with mark;Attack type algorithm can be based on big data
The method of machine learning, for example, neural network algorithm, SVM etc..
For example, attack type may include paper attack, mask attack, screen reproduction attack etc..Wherein, based on attacking
Hitting type and being labeled to input data to be:By input data labeled as the attack type belonging to it.
Assuming that the attack type in existing attack sample database includes attack type A, attack type B and attack type
C.If determining that input data belongs to the maximum probability of attack type A by attack type algorithm, the input number can be determined
It is attack type A according to affiliated attack type.
Illustratively, if the attack type belonging to the input data can not be determined, warning information is generated, in order to
Administrative staff are manually marked based on the warning information.For example, if input data is attacked with all in attack sample database
The attack sample standard deviation of type is hit there are certain gap (being more than some preset threshold value), then the input data may belong to new and attack
Type is hit, can send out warning information to administrative staff at this time.Then, administrative staff can carry out manually the input data
Verification and mark.
Assuming that the attack type in existing attack sample database includes attack type A, attack type B and attack type
C.If determining that input data belongs to the probability P 1 of attack type A, belongs to the probability P 2 of attack type B by attack type algorithm
Be both less than some specific numerical value with the absolute value for 3 Difference of probability P for belonging to attack type C, alternatively, if probability P 1,
Probability P 2 and probability P 3 are both less than some preset probability value, then can determine that input data belongs to new attack type.
It can be seen that in the embodiment of the present invention, can be completed to input data according to existing attack sample database
Mark, only when that can not determine the attack type belonging to input data, is just manually marked by administrative staff, in this way can
Greatly reduce artificial cost.
Input data after the mark is added to attack sample database by S104.
The input data after mark is then added to attack sample database, can be completed to attack sample database
Update.
Illustratively, other attack samples can also be acquired to be added in the attack sample database, for example, can determine
Attack sample is acquired to phase, and the attack sample acquired is added to the attack sample database.In this way, by collected
Attack sample is supplemented in the attack sample database, so as to increase robustness.
As an example, the attack sample of acquisition is the attack sample with mark, then can be by the attack with mark
Sample is added to attack sample database.
As another example, the attack sample of acquisition is the attack sample without mark, then can be to the attack sample of the acquisition
Originally attack sample database is then added to after being labeled.
Illustratively, after S104, the attack sample database that update can be utilized later is trained, and is optimized
Sorting algorithm (or attack type algorithm).
Illustratively, after S104, the later life of the later attack sample database of update and update can be utilized
Object feature samples database is trained, the detection algorithm optimized.
For example, can periodically be optimized to sorting algorithm (or attack type algorithm) and/or detection algorithm.Alternatively,
It can be carried out when the newly-increased sample in attacking sample database and/or biometric sample database reaches a certain threshold value excellent
Change.Alternatively, can be optimized when other trigger conditions are achieved, the present invention does not limit this.Wherein, sample database is attacked
Newly-increased sample be input data after the mark being added in the attack sample database, alternatively, for the acquisition of addition
Attack sample;The newly-increased sample of biometric sample database is the input number being added in the biometric sample database
According to.
For example, first can be reached in the quantity of the input data after the mark in being added to the attack sample database
Threshold value, and/or, when the quantity for the input data being added in the biometric sample database reaches second threshold, according to
The biometric sample database after attack sample database and the addition after the addition is trained, after obtaining optimization
Detection algorithm.
It can be seen that the embodiment of the present invention is labeled input data when the result of In vivo detection is non-living body, and
Input data after mark is added to attack sample database, automation mark can be realized, avoid consuming a large amount of manpower,
So as to greatly save human cost.
Fig. 4 is a schematic block diagram of the device for In vivo detection of the embodiment of the present invention.Device 40 shown in Fig. 4
Including:Acquisition module 401, In vivo detection module 402, labeling module 403 and add module 404.
Acquisition module 401, for obtaining input data;
In vivo detection module 402, the input data for being obtained to acquisition module 401 using detection algorithm are lived
Physical examination is surveyed;
Labeling module 403, if the result for carrying out In vivo detection for In vivo detection module 402 determines the input data
For non-living body, then automatic marking is carried out to the input data;
Add module 404 is added to attack sample database for the input data after marking labeling module 403.
Illustratively, add module 404 can be also used for:If In vivo detection module 402 carries out the result of In vivo detection
It determines that the input data is live body, then the input data is added to biometric sample database.
Illustratively, labeling module 403 can be specifically used for:The input data is analyzed, and according to described point
The result of analysis is labeled.
Illustratively, the result of the analysis is the attack type belonging to the input data, and labeling module 403 can have
Body is used for:Attack type belonging to the input data is judged using sorting algorithm, and based on the attack type to described defeated
Enter data to be labeled, wherein the sorting algorithm is trained to obtain by the attack sample database.
Illustratively, which can also include reminding module.If labeling module 403 can not determine the input number
According to affiliated attack type, then reminding module can be used for generating warning information, in order to which administrative staff are manually marked.
Illustratively, which can also include acquisition module.Acquisition module can be used for:Regularly acquisition attack sample
This.Correspondingly, the attack sample that add module 404 can be also used for be acquired is added to the attack sample database.
Illustratively, which can also include optimization algorithm module, as shown in figure 5, the optimization algorithm module can be with
For:It is trained according to the attack sample database after the addition and the biometric sample database after the addition,
Detection algorithm after being optimized.
Illustratively, which can be also used for being instructed according to the attack sample database after the addition
Practice, the attack type algorithm after being optimized.
Illustratively, Fig. 4 or shown in fig. 5 devices 40 are high in the clouds.
Fig. 4 or shown in fig. 5 devices 40 are implemented for earlier figures 2 or the method shown in Fig. 3 for In vivo detection.
In addition, the embodiment of the present invention additionally provides another device for being used for In vivo detection, which may include processing
Device and memory, wherein when processor executes the instruction code, earlier figures 2 may be implemented in memory code for storing instruction
Or the method shown in Fig. 3 for In vivo detection.
In addition, the embodiment of the present invention additionally provides a kind of electronic equipment, which may include shown in Fig. 4 or Fig. 5
Device 40.Earlier figures 2 or the method shown in Fig. 3 for In vivo detection may be implemented in the electronic equipment.
In addition, the embodiment of the present invention additionally provides a kind of computer storage media, it is stored thereon with computer program.Work as institute
When stating computer program and being executed by processor, earlier figures 2 or the method shown in Fig. 3 for In vivo detection may be implemented.
It can be seen that the embodiment of the present invention is labeled input data when the result of In vivo detection is non-living body, and
Input data after mark is added to attack sample database, automation mark can be realized, avoid consuming a large amount of manpower,
So as to greatly save human cost.
Although describing example embodiment by reference to attached drawing here, it should be understood that the above example embodiment is merely exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may realize that lists described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, depends on the specific application and design constraint of technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of each inventive aspect,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the present invention should be construed to reflect following intention:It is i.e. claimed
The present invention claims the more features of feature than being expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
It levies to solve corresponding technical problem.Therefore, it then follows thus claims of specific implementation mode are expressly incorporated in this specific
Embodiment, wherein each claim itself is as a separate embodiment of the present invention.
It will be understood to those skilled in the art that other than mutually exclusive between feature, any combinations pair may be used
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all processes or unit of equipment are combined.Unless expressly stated otherwise, this specification (including want by adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced by providing the alternative features of identical, equivalent or similar purpose.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of arbitrary
It mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processors
Software module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to the ... of the embodiment of the present invention
The some or all functions of block.The present invention is also implemented as the part or complete for executing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that the program of the present invention store
It on a computer-readable medium, or can be with the form of one or more signal.Such signal can be from internet
It downloads and obtains on website, either provide on carrier signal or provide in any other forms.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific implementation mode, protection of the invention
Range is not limited thereto, and any one skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection domain.
Claims (18)
1. a kind of method for In vivo detection, which is characterized in that including:
Obtain input data;
In vivo detection is carried out to the input data using detection algorithm;
If the result of the In vivo detection determines that the input data is non-living body, the input data is marked automatically
Note;
Input data after the mark is added to attack sample database.
2. the method as described in claim 1, which is characterized in that further include:
If the result of the In vivo detection determines that the input data is live body, the input data is added to biological spy
Levy sample database.
3. the method as described in claim 1, which is characterized in that it is described that the input data is labeled, including:
The input data is analyzed, and is labeled according to the result of the analysis.
4. method as claimed in claim 3, which is characterized in that the result of the analysis is the attack belonging to the input data
Type,
It is described that the input data is analyzed, and be labeled according to the result of the analysis, including:
Attack type belonging to the input data is judged using sorting algorithm, and based on the attack type to the input number
According to being labeled, wherein the sorting algorithm is trained to obtain by the attack sample database.
5. method as claimed in claim 4, which is characterized in that it is described that the input data is analyzed, and according to described
The result of analysis is labeled, and further includes:
If the attack type belonging to the input data can not be determined, warning information is generated, in order to which administrative staff carry out
Artificial mark.
6. the method as described in claim 1, which is characterized in that further include:
Regularly acquisition attack sample, and the attack sample acquired is added to the attack sample database.
7. the method as described in claim 2 or 6, which is characterized in that further include:
It is trained, is obtained according to the attack sample database after the addition and the biometric sample database after the addition
Detection algorithm after to optimization.
8. method as described in any one of claim 1 to 7, which is characterized in that the method is executed by high in the clouds.
9. a kind of device for In vivo detection, which is characterized in that including:
Acquisition module, for obtaining input data;
In vivo detection module, for carrying out In vivo detection to the input data using detection algorithm;
Labeling module, if the result for the In vivo detection determines that the input data is non-living body, to the input
Data carry out automatic marking;
Add module, for the input data after the mark to be added to attack sample database.
10. device as claimed in claim 9, which is characterized in that the add module is additionally operable to:
If the result of the In vivo detection determines that the input data is live body, the input data is added to biological spy
Levy sample database.
11. device as claimed in claim 9, which is characterized in that the labeling module is specifically used for:
The input data is analyzed, and is labeled according to the result of the analysis.
12. device as claimed in claim 11, which is characterized in that the result of the analysis is attacking belonging to the input data
Type is hit, the labeling module is specifically used for:
Attack type belonging to the input data is judged using sorting algorithm, and based on the attack type to the input number
According to being labeled, wherein the sorting algorithm is trained to obtain by the attack sample database.
13. device as claimed in claim 12, which is characterized in that further include reminding module, be used for:
If the labeling module can not determine the attack type belonging to the input data, warning information is generated, in order to
Administrative staff are manually marked.
14. device as claimed in claim 9, which is characterized in that further include acquisition module, be used for:
Regularly acquisition attack sample;
The add module, the attack sample for being additionally operable to be acquired are added to the attack sample database.
15. the device as described in claim 10 or 14, which is characterized in that further include optimization algorithm module, be used for:
It is trained, is obtained according to the attack sample database after the addition and the biometric sample database after the addition
Detection algorithm after to optimization.
16. such as claim 9 to 15 any one of them device, which is characterized in that described device is high in the clouds.
17. a kind of device for In vivo detection, which is characterized in that including:
Memory, for storing instruction code;
Processor, for executing described instruction code, to realize claim 1 to 8 any one of them method.
18. a kind of computer storage media, is stored thereon with computer program, which is characterized in that the computer program is located
The step of when reason device executes to realize any one of claim 1 to 8 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710230110.0A CN108694357A (en) | 2017-04-10 | 2017-04-10 | Method, apparatus and computer storage media for In vivo detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710230110.0A CN108694357A (en) | 2017-04-10 | 2017-04-10 | Method, apparatus and computer storage media for In vivo detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108694357A true CN108694357A (en) | 2018-10-23 |
Family
ID=63843296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710230110.0A Pending CN108694357A (en) | 2017-04-10 | 2017-04-10 | Method, apparatus and computer storage media for In vivo detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108694357A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633647A (en) * | 2019-08-21 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Living body detection method and device |
| CN112036238A (en) * | 2020-07-24 | 2020-12-04 | 支付宝实验室(新加坡)有限公司 | Face data processing method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853400A (en) * | 2010-05-20 | 2010-10-06 | 武汉大学 | Multiclass image classification method based on active learning and semi-supervised learning |
| CN103150795A (en) * | 2013-03-01 | 2013-06-12 | 姬志刚 | Door control system capable of generating door control open passwords through human body characteristic verification |
| EP2863339A2 (en) * | 2013-10-18 | 2015-04-22 | Daon Holdings Limited | Methods and systems for determing user liveness |
| US20160005050A1 (en) * | 2014-07-03 | 2016-01-07 | Ari Teman | Method and system for authenticating user identity and detecting fraudulent content associated with online activities |
| CN105612533A (en) * | 2015-06-08 | 2016-05-25 | 北京旷视科技有限公司 | In-vivo detection method, in-vivo detection system and computer programe products |
| CN105913024A (en) * | 2016-04-12 | 2016-08-31 | 上海交通大学 | Android mobile terminal detecting method based on LAP operator for resisting replay attacks |
| CN106096557A (en) * | 2016-06-15 | 2016-11-09 | 浙江大学 | A kind of semi-supervised learning facial expression recognizing method based on fuzzy training sample |
| CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
| US20170053406A1 (en) * | 2014-09-09 | 2017-02-23 | EyeVerify Inc. | Systems and methods for liveness analysis |
-
2017
- 2017-04-10 CN CN201710230110.0A patent/CN108694357A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853400A (en) * | 2010-05-20 | 2010-10-06 | 武汉大学 | Multiclass image classification method based on active learning and semi-supervised learning |
| CN103150795A (en) * | 2013-03-01 | 2013-06-12 | 姬志刚 | Door control system capable of generating door control open passwords through human body characteristic verification |
| EP2863339A2 (en) * | 2013-10-18 | 2015-04-22 | Daon Holdings Limited | Methods and systems for determing user liveness |
| US20160005050A1 (en) * | 2014-07-03 | 2016-01-07 | Ari Teman | Method and system for authenticating user identity and detecting fraudulent content associated with online activities |
| US20170053406A1 (en) * | 2014-09-09 | 2017-02-23 | EyeVerify Inc. | Systems and methods for liveness analysis |
| CN105612533A (en) * | 2015-06-08 | 2016-05-25 | 北京旷视科技有限公司 | In-vivo detection method, in-vivo detection system and computer programe products |
| CN105913024A (en) * | 2016-04-12 | 2016-08-31 | 上海交通大学 | Android mobile terminal detecting method based on LAP operator for resisting replay attacks |
| CN106096557A (en) * | 2016-06-15 | 2016-11-09 | 浙江大学 | A kind of semi-supervised learning facial expression recognizing method based on fuzzy training sample |
| CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
Non-Patent Citations (2)
| Title |
|---|
| KAI LI ET.AL: ""A Semi-Supervised 2DPCA Face Recognition Method Based on Self-training"", 《2012 FOURTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL AND INFORMATION SCIENCES》 * |
| 赵元元: ""基于流形学习与支持向量机的人脸识别研究"", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633647A (en) * | 2019-08-21 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Living body detection method and device |
| CN112036238A (en) * | 2020-07-24 | 2020-12-04 | 支付宝实验室(新加坡)有限公司 | Face data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180260621A1 (en) | Picture recognition method and apparatus, computer device and computer- readable medium | |
| US11250324B2 (en) | Intelligent recognition and alert methods and systems | |
| CN107622240B (en) | Face detection method and device | |
| CN109146830A (en) | For generating the method, apparatus, system and storage medium of training data | |
| CN109784391A (en) | Sample mask method and device based on multi-model | |
| CN105938552A (en) | Face recognition method capable of realizing base image automatic update and face recognition device | |
| Choi et al. | Malware detection using malware image and deep learning | |
| CN108875522A (en) | Face cluster methods, devices and systems and storage medium | |
| CN109447156B (en) | Method and apparatus for generating a model | |
| CN106650662A (en) | Target object occlusion detection method and target object occlusion detection device | |
| CN108875546A (en) | Face auth method, system and storage medium | |
| CN108875515A (en) | Face identification method, device, system, storage medium and capture machine | |
| CN108509921B (en) | Method and apparatus for generating information | |
| CN110751675B (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
| CN108875476A (en) | Automatic near-infrared face registration and recognition methods, device and system and storage medium | |
| CN110222641B (en) | Method and apparatus for recognizing image | |
| US20220351042A1 (en) | Intelligent recognition and alert methods and systems | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN108875483A (en) | Image detecting method, device, system and computer-readable medium | |
| CN107959798A (en) | Video data real-time processing method and device, computing device | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| CN109690571A (en) | Group echo system and method based on study | |
| CN110490058A (en) | Training method, device, system and the computer-readable medium of pedestrian detection model | |
| CN108875500A (en) | Pedestrian recognition methods, device, system and storage medium again | |
| CN108694357A (en) | Method, apparatus and computer storage media for In vivo detection |
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 |