CN105678136A - Cloud data anti-leak access method based on face recognition technology - Google Patents
Cloud data anti-leak access method based on face recognition technology Download PDFInfo
- Publication number
- CN105678136A CN105678136A CN201410658955.6A CN201410658955A CN105678136A CN 105678136 A CN105678136 A CN 105678136A CN 201410658955 A CN201410658955 A CN 201410658955A CN 105678136 A CN105678136 A CN 105678136A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- hmm
- data
- recognition technology
- 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
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a cloud data anti-leak access method based on face recognition technology; the method is characterized by comprising the following steps: if present face image data is determined to be valid, the system automatically opens decryption authority of a corresponding level, so the client can normally access the cloud data through the system; if the client leaves, the system cannot scan the client face data, the system will immediately shut down the cloud data access, thus effectively protecting cloud data. The cloud data anti-leak access method based on face recognition technology can flexibly configure safety strategies, is strong in suitability, thus effectively ensuring cloud data safety, and preventing data leakage conditions caused by a conventional account authority mode.
Description
Technical field
The present invention relates to a kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology.
Background technology
Along with the development of cloud technology, big data age is flourish, accesses therefore and with some leaks, traditional account permission mode single can not meet the condition of high in the clouds data access for high in the clouds data, if visitor's computer away from keyboard or be in a hurry is gone out, data are probably leaked.
Therefore, prior art needs to be improved.
Summary of the invention
The present invention is in order to solve the deficiencies in the prior art, thering is provided a kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology, it is possible to flexible configuration security strategy, suitability is strong, effectively ensure that the safety of high in the clouds data, avoid the leaking data situation that tradition account permission mode causes.
For solving the problems of the technologies described above, a kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology that the embodiment of the present invention provides, adopts following technical scheme:
A kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology, it is characterised in that, comprise the steps:
S1: computer end all configures front-facing camera, is arranged by port, is connected with man face image acquiring system. When there being people to bring into use this computer, it is necessary to carry out man face image acquiring, camera gathers human face photo automatically, and carries out relevant treatment;
S2: after system successfully collects facial image, it is necessary to compare and retrieval with the human face data in face database, determines the access rights of this people with this;
The facial image recognition process of S3:HMM is exactly first extract the proper vector of target image, then uses algorithm to draw the probability belonging to everyone, and maximum that of last select probability is as the result identified;
S4: by U mouth, camera typing facial image, set up view data storehouse, and according to form, the relevant information of input correspondence image, and authority rank is arranged, utilize port to arrange, it is connected with anti-disclosure system, setting up decision mechanism between two systems, anti-disclosure system carries out the behavior of corresponding authority according to the result of comparison in data base management system (DBMS), facilitates staff can successfully inquire the data in high in the clouds;
S5: cloud stores end data to be existed with ciphertext form, high in the clouds data can be carried out encryption and decryption operation by the encrypting and deciphering system in local client terminal, when performing encryption behavior, there is grade difference, document, according to company's requirement, is carried out graduation encryption by high in the clouds data management staff.
Specifically, the concrete grammar of described step S1 is as follows:
1) by special pick up camera, facial image is got;
2) face image data collected is sent to Data centre;
3) image is carried out face change detection;
4) by Adaboost algorithm, image is carried out Face datection;
5) face candidate region is put into by the image of Face datection
6) area-of-interest for the facial image in face candidate region obtains;
7) setting up face complexion model, judge whether detected image is face by the colour of skin, if not being just give up, being just enter next step;
8) asking variance to calculate the image entered, and the valve value of result and setting compared, if comparing valve value, little just the giving up of result, confirms as non-face image, if bigger than valve value, just thinks facial image.
Specifically, the concrete grammar of described step S2 is as follows:
1) HMM mathematical model is first determined;
2) HMM model of face is established again;
3) training and the recognition process of HMM algorithm is finally determined.
Specifically, described training refers to and everyone facial image in sample storehouse is determined HMM parameter, sets up the process of HMM model.
Specifically, the described process setting up HMM model comprises:
1) first image is split uniformly, and extract the observed value sequence of correspondence image;
2) parameter of HMM is carried out initialize, it is determined that the state number of model and the size of observation sequence vector;
3) the HMM parameter using iterative computation initial, first by unified for image segmentation with each state of corresponding HMM, then split (using dual Viterbi to split in EHMM) with Viterbi and replace above-mentioned segmentation, this process by output an initial HMM parameter, as the input carrying out revaluation HMM parameter next time;
4) with Baum-Welch algorithm, HMM parameter obtained above being carried out revaluation, according to the observation vector of training image, by HMM parameter adjustment to a local maximum, what this process obtained export just can the HMM final mask of training image.
A kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology provided by the invention, it is possible to flexible configuration security strategy, suitability is strong, effectively ensure that the safety of high in the clouds data, avoids the leaking data situation that tradition account permission mode causes.
Accompanying drawing explanation
Fig. 1 is the step schematic diagram of a kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology described in the embodiment of the present invention.
Fig. 2 is the man face image acquiring workflow schematic diagram described in the embodiment of the present invention.
Fig. 3 is that the HMM described in the embodiment of the present invention trains schema.
Fig. 4 is the HMM recognition of face schema described in the embodiment of the present invention.
Fig. 5 is the data encrypting and deciphering functional diagram described in the embodiment of the present invention.
Embodiment
The anti-method of divulging a secret of high in the clouds data access based on the face recognition technology embodiment of the present invention being supplied to below in conjunction with accompanying drawing is described in detail.
As shown in Fig. 1,2,3,4,5, a kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology that the embodiment of the present invention provides, it is characterised in that, comprise the steps:
S1: computer end all configures front-facing camera, is arranged by port, is connected with man face image acquiring system. When there being people to bring into use this computer, it is necessary to carry out man face image acquiring, camera gathers human face photo automatically, and carries out relevant treatment;
S2: after system successfully collects facial image, it is necessary to compare and retrieval with the human face data in face database, determines the access rights of this people with this;
The facial image recognition process of S3:HMM is exactly first extract the proper vector of target image, then uses algorithm to draw the probability belonging to everyone, and maximum that of last select probability is as the result identified;
S4: by U mouth, camera typing facial image, set up view data storehouse, and according to form, the relevant information of input correspondence image, and authority rank is arranged, utilize port to arrange, it is connected with anti-disclosure system, setting up decision mechanism between two systems, anti-disclosure system carries out the behavior of corresponding authority according to the result of comparison in data base management system (DBMS), facilitates staff can successfully inquire the data in high in the clouds;
S5: cloud stores end data to be existed with ciphertext form, high in the clouds data can be carried out encryption and decryption operation by the encrypting and deciphering system in local client terminal, when performing encryption behavior, there is grade difference, document, according to company's requirement, is carried out graduation encryption by high in the clouds data management staff.
Specifically, the concrete grammar of described step S1 is as follows:
1) by special pick up camera, facial image is got;
2) face image data collected is sent to Data centre;
3) image is carried out face change detection;
4) by Adaboost algorithm, image is carried out Face datection;
5) face candidate region is put into by the image of Face datection
6) area-of-interest for the facial image in face candidate region obtains;
7) setting up face complexion model, judge whether detected image is face by the colour of skin, if not being just give up, being just enter next step;
8) asking variance to calculate the image entered, and the valve value of result and setting compared, if comparing valve value, little just the giving up of result, confirms as non-face image, if bigger than valve value, just thinks facial image.
Specifically, the concrete grammar of described step S2 is as follows:
1) HMM mathematical model is first determined;
2) HMM model of face is established again;
3) training and the recognition process of HMM algorithm is finally determined.
Specifically, described training refers to and everyone facial image in sample storehouse is determined HMM parameter, sets up the process of HMM model.
Specifically, the described process setting up HMM model comprises:
1) first image is split uniformly, and extract the observed value sequence of correspondence image;
2) parameter of HMM is carried out initialize, it is determined that the state number of model and the size of observation sequence vector;
3) the HMM parameter using iterative computation initial, first by unified for image segmentation with each state of corresponding HMM, then split (using dual Viterbi to split in EHMM) with Viterbi and replace above-mentioned segmentation, this process by output an initial HMM parameter, as the input carrying out revaluation HMM parameter next time;
4) with Baum-Welch algorithm, HMM parameter obtained above being carried out revaluation, according to the observation vector of training image, by HMM parameter adjustment to a local maximum, what this process obtained export just can the HMM final mask of training image.
Main abbreviated functional description
1. native system carries out anti-management of divulging a secret mainly for company's high in the clouds data, server data, authority recognition is carried out according to face image data, it is not limited to physical address, it is possible to flexible company personnel checks company's high in the clouds secret data anywhere or anytime, and guarantees data security coefficient height.
2. face identification functions.Recognition of face is a popular computer technology research field, and face tracking is detected, and automatically adjusts image zoom, and night infrared is detected, and automatically adjusts exposure intensity; It belongs to living things feature recognition technology, is that the biological characteristic to organism (generally refering in particular to people) itself is to distinguish organism individuality.
3. the modeling of face and retrieval. The portrait data of registration warehouse-in can be carried out the feature that face is extracted in modeling, and be generated face template (face characteristic file) and be saved in database. When carrying out face and search for (search type), the portrait specified is carried out modeling, then everyone template in itself and database is compared identification, adjudicate the authority rank of this people the most at last according to the similar value of institute's comparison.
4. classified papers content is undertaken forcing encrypting storing by Intelligent Dynamic encryption and decryption technology by the security strategy set by management end, and the data of storage (not comprised: various mobile storage equipment, network, e-mail by any approach; Immediate communication tool: MSN, QQ, PaoPao, Skype etc.) outwards divulge a secret; When legal user reads data, encrypted data deciphering can arrive internal memory automatically, it may also be useful to the existence of the imperceptible encryption and decryption process of personnel; For the plaintext in internal memory, it is provided that unique internal memory guard technology, prevents from leaking.
Two, main function detailed annotation
1. man face image acquiring function.
Computer end all configures front-facing camera, is arranged by port, is connected with man face image acquiring system. When there being people to bring into use this computer, it is necessary to carry out man face image acquiring, camera gathers human face photo automatically, and carries out relevant treatment, and concrete steps are as follows:
1) by special pick up camera, facial image is got;
2) face image data collected is sent to Data centre;
3) image is carried out face change detection;
4) by Adaboost algorithm, image is carried out Face datection;
5) face candidate region is put into by the image of Face datection
6) area-of-interest for the facial image in face candidate region obtains;
7) setting up face complexion model, judge whether detected image is face by the colour of skin, if not being just give up, being just enter next step;
8) asking variance to calculate the image entered, and the valve value of result and setting compared, if comparing valve value, little just the giving up of result, confirms as non-face image, if bigger than valve value, just thinks facial image.
2. facial image decision function
After system successfully collects facial image, it is necessary to compare and retrieval with the human face data in face database, determining the access rights of this people with this, concrete steps are as follows:
First HMM mathematical model is determined.
HMM is based upon on the basis of Markov chain, and Markov chain is a kind of description to Markov process. Markov process refers to the stochastic process of markov property, and its discoverer is Soviet Union's scholar's markov, and this kind of stochastic process is assumed to be in the state of t, so this stochastic process is in the state in t+m momentOnly relevant with the state of t, and unrelated with the state before t[16]。
HMM is made up of two stochastic processes, and one is the Markov chain with state transition probability, and another is the stochastic process describing relation between observed value and state. Observed value can only be seen owing to standing in the angle of viewer, can not directly see state, it is necessary to a stochastic process, the existence of state and characteristic be carried out perception, so being called as " hidden " Markov model[17]。
HMM can be described by 5 kinds of parameters below:
The state number of Markov chain in N:HMM.Assume that S is the set of state,, this model in the state of t is,,, T is the length [18] of observation sequence here.
: original state probability vector,,,。
A: state transition probability,,,。
M: state may the number of corresponding observed value, it is possible to observed value be denoted as, the observed value of t is designated as,。
B: observed value probability matrix,, wherein。
Like this, according to above-mentioned reasoning, it is possible to HMM is represented, it is also possible to write a Chinese character in simplified form
. WithRepresent two stochastic process formulas, the both Markov chains of composition HMM, export as state sequence; Another stochastic process is usedStatement, observation sequence value can determine beThe output value produced, T is the size [18] of observed value time. The composition of HMM algorithm:
Establish the HMM model of face again.
In facial image, the relative position of each organ is stable, for the front elevation picture of vertical face, divides from the top-to-bottom of image, it is possible to be divided into forehead, eyes, nose, face, chin. Even if captured human face photo is for the rotation having Small angle between vertical line, the position relation of these organs is still determined, it is possible to each region in these five regions divided is considered as dimension one of them state of continuous HMM model from left to right. The HMM model of face and wherein state transition probability between each state, a dimension HMM model of face:
Finally determine training and the recognition process of HMM algorithm
So-called training just refers to be determined HMM parameter by everyone facial image in sample storehouse, sets up the process of HMM model.
1) first image is split uniformly, and extract the observed value sequence of correspondence image.
2) parameter of HMM is carried out initialize, it is determined that the state number of model and the size of observation sequence vector.
3) the HMM parameter using iterative computation initial. First by unified for image segmentation with each state of corresponding HMM. Then with Viterbi split (using dual Viterbi split in EHMM) replace above-mentioned segmentation, this process by export an initial HMM parameter, as the input carrying out revaluation HMM parameter next time.
4) with Baum-Welch algorithm, HMM parameter obtained above is carried out revaluation. According to the observation vector of training image, by HMM parameter adjustment to a local maximum. What this process obtained export just can the HMM final mask of training image.
The facial image recognition process of HMM is exactly first extract the proper vector of target image, then uses algorithm to draw the probability belonging to everyone, and maximum that of last select probability is as the result identified, detailed process is as follows:
(1) the observation sequence vector of image to be identified is extracted。
(2) by the matching degree of the observation vector calculation and everyone HMM model that obtain, it is assumed that there be M people, calculating is in actual computation, and the maximum likelihood probability often calculated using Viterbi algorithm is as the replacement of above-mentioned probability[25]。
(3) choose the maximum value of above-mentioned probability as recognition result, or it is judged as that when maximum value does not meet recognition threshold this face picture does not belong to the personage in this face database.
3. data base administration (DBM) is arranged
By U mouth, camera typing facial image, set up view data storehouse, and according to form, input the relevant information of correspondence image, and authority rank is arranged. Utilizing port to arrange, be connected with anti-disclosure system, set up decision mechanism between two systems, anti-disclosure system carries out the behavior of corresponding authority according to the result of comparison in data base management system (DBMS), facilitates staff can successfully inquire the data in high in the clouds.
4. anti-disclosure system is arranged
Cloud stores end data to be existed with ciphertext form, high in the clouds data can be carried out encryption and decryption operation by the encrypting and deciphering system in local client terminal, when performing encryption behavior, there is grade difference, document, according to company's requirement, is carried out graduation encryption by high in the clouds data management staff.
Cipher key hierarchy function:
High in the clouds data are arranged grade according to safe rank, and thinks corresponding with the authority grade of staff.
After enabling cipher key hierarchy, there is the Administrator of mandate just can carry out key partition of the level for particular user. 1 grade of rank is the highest, and then rank is successively decreased successively.
A kind of anti-method of divulging a secret of high in the clouds data access based on face recognition technology provided by the invention, it is possible to flexible configuration security strategy, suitability is strong, effectively ensure that the safety of high in the clouds data, avoids the leaking data situation that tradition account permission mode causes.
The above; it is only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any it is familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention. Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (5)
1. the anti-method of divulging a secret of high in the clouds data access based on face recognition technology, it is characterised in that, comprise the steps:
S1: computer end all configures front-facing camera, is arranged by port, is connected with man face image acquiring system, when there being people to bring into use this computer, it is necessary to carry out man face image acquiring, camera gathers human face photo automatically, and carries out relevant treatment;
S2: after system successfully collects facial image, it is necessary to compare and retrieval with the human face data in face database, determines the access rights of this people with this;
The facial image recognition process of S3:HMM is exactly first extract the proper vector of target image, then uses algorithm to draw the probability belonging to everyone, and maximum that of last select probability is as the result identified;
S4: by U mouth, camera typing facial image, set up view data storehouse, and according to form, the relevant information of input correspondence image, and authority rank is arranged, utilize port to arrange, it is connected with anti-disclosure system, setting up decision mechanism between two systems, anti-disclosure system carries out the behavior of corresponding authority according to the result of comparison in data base management system (DBMS), facilitates staff can successfully inquire the data in high in the clouds;
S5: cloud stores end data to be existed with ciphertext form, high in the clouds data can be carried out encryption and decryption operation by the encrypting and deciphering system in local client terminal, when performing encryption behavior, there is grade difference, document, according to company's requirement, is carried out graduation encryption by high in the clouds data management staff.
2. the anti-method of divulging a secret of high in the clouds data access based on face recognition technology according to claim 1, it is characterised in that, the concrete grammar of described step S1 is as follows:
1) by special pick up camera, facial image is got;
2) face image data collected is sent to Data centre;
3) image is carried out face change detection;
4) by Adaboost algorithm, image is carried out Face datection;
5) face candidate region is put into by the image of Face datection
6) area-of-interest for the facial image in face candidate region obtains;
7) setting up face complexion model, judge whether detected image is face by the colour of skin, if not being just give up, being just enter next step;
8) asking variance to calculate the image entered, and the valve value of result and setting compared, if comparing valve value, little just the giving up of result, confirms as non-face image, if bigger than valve value, just thinks facial image.
3. the anti-method of divulging a secret of high in the clouds data access based on face recognition technology according to claim 1, it is characterised in that, the concrete grammar of described step S2 is as follows:
1) HMM mathematical model is first determined;
2) HMM model of face is established again;
3) training and the recognition process of HMM algorithm is finally determined.
4. the anti-method of divulging a secret of the access of the high in the clouds data based on face recognition technology according to claim 3, it is characterised in that, described training refers to be determined HMM parameter by everyone facial image in sample storehouse, sets up the process of HMM model.
5. the anti-method of divulging a secret of high in the clouds data access based on face recognition technology according to claim 4, it is characterised in that, the described process setting up HMM model comprises:
1) first image is split uniformly, and extract the observed value sequence of correspondence image;
2) parameter of HMM is carried out initialize, it is determined that the state number of model and the size of observation sequence vector;
3) the HMM parameter using iterative computation initial, first by unified for image segmentation with each state of corresponding HMM, then split (using dual Viterbi to split in EHMM) with Viterbi and replace above-mentioned segmentation, this process by output an initial HMM parameter, as the input carrying out revaluation HMM parameter next time;
4) with Baum-Welch algorithm, HMM parameter obtained above being carried out revaluation, according to the observation vector of training image, by HMM parameter adjustment to a local maximum, what this process obtained export just can the HMM final mask of training image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410658955.6A CN105678136A (en) | 2014-11-19 | 2014-11-19 | Cloud data anti-leak access method based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410658955.6A CN105678136A (en) | 2014-11-19 | 2014-11-19 | Cloud data anti-leak access method based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105678136A true CN105678136A (en) | 2016-06-15 |
Family
ID=56944855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410658955.6A Pending CN105678136A (en) | 2014-11-19 | 2014-11-19 | Cloud data anti-leak access method based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105678136A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182351A (en) * | 2017-12-26 | 2018-06-19 | 华中科技大学同济医学院附属协和医院 | A kind of Automatic work system of high safety grade |
| CN108446659A (en) * | 2018-03-28 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting facial image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000050230A (en) * | 2000-05-30 | 2000-08-05 | 김성우 | Method for authentication security on network by face recognition |
| CN102902935A (en) * | 2012-09-26 | 2013-01-30 | 广东欧珀移动通信有限公司 | Mobile terminal privacy protection method and device |
| CN103577764A (en) * | 2012-07-27 | 2014-02-12 | 国基电子（上海）有限公司 | Document encryption and decryption method and electronic device with document encryption and decryption function |
| CN104008320A (en) * | 2014-05-19 | 2014-08-27 | 惠州Tcl移动通信有限公司 | Using permission and user mode control method and system based on face recognition |
-
2014
- 2014-11-19 CN CN201410658955.6A patent/CN105678136A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000050230A (en) * | 2000-05-30 | 2000-08-05 | 김성우 | Method for authentication security on network by face recognition |
| CN103577764A (en) * | 2012-07-27 | 2014-02-12 | 国基电子（上海）有限公司 | Document encryption and decryption method and electronic device with document encryption and decryption function |
| CN102902935A (en) * | 2012-09-26 | 2013-01-30 | 广东欧珀移动通信有限公司 | Mobile terminal privacy protection method and device |
| CN104008320A (en) * | 2014-05-19 | 2014-08-27 | 惠州Tcl移动通信有限公司 | Using permission and user mode control method and system based on face recognition |
Non-Patent Citations (1)
| Title |
|---|
| 王琛: "基于HMM模型的人脸识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182351A (en) * | 2017-12-26 | 2018-06-19 | 华中科技大学同济医学院附属协和医院 | A kind of Automatic work system of high safety grade |
| CN108446659A (en) * | 2018-03-28 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting facial image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112651348B (en) | Identity authentication method and device and storage medium | |
| Adler | Sample images can be independently restored from face recognition templates | |
| CN105335643B (en) | The processing method and processing system of file | |
| CN106096548B (en) | Multi-intelligent-terminal shared face secret recognition method based on cloud environment | |
| Ogiela et al. | Bio-inspired cryptographic techniques in information management applications | |
| CN110472519A (en) | A kind of human face in-vivo detection method based on multi-model | |
| CN112686191B (en) | Living body anti-counterfeiting method, system, terminal and medium based on three-dimensional information of human face | |
| CN105354509A (en) | Picture processing method and processing system | |
| CN113298158B (en) | Data detection method, device, equipment and storage medium | |
| WO2021197369A1 (en) | Liveness detection method and apparatus, electronic device, and computer readable storage medium | |
| WO2021164252A1 (en) | Iris recognition-based user identity determining method and related apparatus | |
| CN105469042A (en) | Improved face image comparison method | |
| CN108595975A (en) | A kind of carrier-free information concealing method based on the retrieval of nearly multiimage | |
| CN105678136A (en) | Cloud data anti-leak access method based on face recognition technology | |
| CN106255109A (en) | Router purview certification method and system | |
| Yu et al. | An identity authentication method for ubiquitous electric power Internet of Things based on dynamic gesture recognition | |
| Datta et al. | Machine learning explainability and robustness: connected at the hip | |
| Yucer et al. | Racial bias within face recognition: A survey | |
| CN108009532A (en) | Personal identification method and terminal based on 3D imagings | |
| CN109614804B (en) | Bimodal biological characteristic encryption method, device and storage device | |
| CN116886315A (en) | Authentication method based on biological characteristics and zero knowledge proof under web3.0 | |
| Quintiliano et al. | Face recognition based on eigeneyes | |
| CN105160229A (en) | Single-soldier system with voice and fingerprint dual authentication | |
| Sivasangari et al. | Facial recognition system using decision tree algorithm | |
| Jin et al. | Ppvibe: privacy preserving background extractor via secret sharing in multiple cloud servers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160615 |
|
| WD01 | Invention patent application deemed withdrawn after publication |