WO2022095355A1 - 人脸识别信息的二次加密方法、装置、设备及存储介质 - Google Patents
人脸识别信息的二次加密方法、装置、设备及存储介质 Download PDFInfo
- Publication number
- WO2022095355A1 WO2022095355A1 PCT/CN2021/090564 CN2021090564W WO2022095355A1 WO 2022095355 A1 WO2022095355 A1 WO 2022095355A1 CN 2021090564 W CN2021090564 W CN 2021090564W WO 2022095355 A1 WO2022095355 A1 WO 2022095355A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face recognition
- recognition information
- sub
- original
- standard
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Definitions
- the present application relates to the technical field of identity authentication, and in particular, to a method, device, device and storage medium for secondary encryption of face recognition information.
- Face recognition has been widely used in business scenarios such as mobile phone recognition and customer payment. This recognition method is very convenient to use. But in addition to the convenience, it is inevitable that people will worry about information security. Common user passwords can be changed frequently to ensure the security of passwords. However, the inventor realizes that private information such as face has the characteristics of uniqueness and long-term immutability. Various scenarios identified by face authentication will generate hidden dangers and risks.
- the embodiments of the present application provide a method, device, device and storage medium for secondary encryption of face recognition information, which aim to solve the problem of potential security risks in the existing face recognition technology.
- an embodiment of the present application provides a method for secondary encryption of face recognition information, including:
- the target face recognition information input by the user in real time is received, and the target face recognition information input by the user in real time is compared with the standard face recognition information in the face comparison information database. Yes, when the comparison is consistent, the identification is confirmed to be successful.
- an embodiment of the present application provides a secondary encryption device for face recognition information, including:
- An entry unit used to pre-enter the user's original face recognition information and user identity information
- a splitting unit for splitting out the original key part that can be used for identity recognition from the original face recognition information, and using the remaining part in the original face recognition information as the original non-critical part;
- a modification unit configured to split the original non-critical part into several sub-regions, and modify at least one sub-region in the several sub-regions;
- a combining unit is used to recombine the modified sub-region and the unmodified sub-region into a standard non-critical part, and splicing the standard non-critical part and the original key part to realize the recognition of the original face Secondary encryption of information, the standard face recognition information obtained after secondary encryption and the user identity information are associated and stored to obtain a face comparison information database;
- the identification unit is used to receive the target face recognition information input by the user in real time when identification is required, and compare the target face recognition information input by the user in real time with the standard person in the face comparison information database. The face recognition information is compared, and when the comparison is consistent, the identity recognition is confirmed to be successful.
- an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program When implementing the secondary encryption method for face recognition information as described in the first aspect.
- an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when executed by a processor, the computer program causes the processor to execute the first The secondary encryption method for face recognition information described in the aspect.
- the embodiments of the present application provide a secondary encryption method, device, equipment and storage medium for face recognition information.
- the user can change the face recognition information regularly or at any time, thereby improving the security of the face recognition information. It does not affect the convenience of identification.
- FIG. 1 is a schematic flowchart of a secondary encryption method for face recognition information provided by an embodiment of the present application
- FIG. 2 is a schematic sub-flow diagram of a method for secondary encryption of face recognition information provided by an embodiment of the present application
- FIG. 3 is a schematic diagram of another sub-flow of the method for secondary encryption of face recognition information provided by an embodiment of the present application.
- FIG. 4 is a schematic diagram of another sub-flow of a method for secondary encryption of face recognition information provided by an embodiment of the present application.
- FIG. 5 is a schematic block diagram of an apparatus for secondary encryption of face recognition information provided by an embodiment of the present application.
- FIG. 6 is a schematic block diagram of subunits of a device for secondary encryption of face recognition information provided by an embodiment of the present application
- FIG. 7 is a schematic block diagram of another subunit of a device for secondary encryption of face recognition information provided by an embodiment of the present application.
- FIG. 8 is a schematic block diagram of another subunit of a device for secondary encryption of face recognition information provided by an embodiment of the present application.
- FIG. 9 is a schematic block diagram of a computer device according to an embodiment of the present application.
- FIG. 1 is a schematic flowchart of a secondary encryption method for face recognition information provided by an embodiment of the present application. As shown in the figure, the method includes steps S101 to S105:
- S104 recombine the modified sub-region and the unmodified sub-region into a standard non-critical part, and splicing the standard non-critical part and the original key part, so as to realize the second analysis of the original face recognition information.
- Secondary encryption the standard face recognition information obtained after secondary encryption and the user identity information are associated and stored to obtain a face comparison information database;
- S105 when identification is required, receive the target face recognition information input by the user in real time, and compare the target face recognition information input by the user in real time with the standard face recognition information in the face comparison information database The comparison is performed, and when the comparison is consistent, the identification is confirmed to be successful.
- the original face recognition information refers to the facial feature information of the user.
- the user identity information represents the identity of the user, and may include the user's name, ID card, user identification code, contact information, platform login information, and the like.
- the user When identification is required, the user only needs to input the face recognition information, and then compare the real-time input target face recognition information with the saved standard face recognition information.
- the association relationship of identity information can obtain user identity information, thereby realizing identity recognition.
- the original face recognition information includes a key part (for the convenience of distinction, referred to as the original key part here) and a non-critical part (for the convenience of distinction, referred to as the original non-critical part here) ), where the key part refers to the least part that can characterize the user, that is, only the face recognition information contains the key part, the user can be uniquely identified.
- Non-critical parts are optional parts other than critical parts, which can help with identification, but are not required.
- the key part may be face information
- the non-key part may be hair, hair extensions, hairstyles, and so on.
- the method of splitting can be to gradually enlarge from the center in the original face recognition information, and take the smallest area whose recognition success rate reaches the preset threshold after enlargement as the key part, and take the remaining area as the non-critical part.
- the way of enlarging can be in the shape of a standard face, or in the shape of a rectangle or a circle.
- the original non-critical part is divided into a plurality of sub-regions, so that these sub-regions can be modified.
- the scope of modification may be one sub-area, or multiple sub-areas, but not all sub-areas, so that in subsequent identification, non-critical parts can be compared.
- Modifications to the sub-regions in this embodiment of the present application may be addition, deletion, or replacement.
- Adding means adding a part of the content in the sub-area to make the original sub-area different from the modified sub-area.
- Deleting means deleting part or all of the content in the sub-area, making the original sub-area different from the modified sub-area.
- Different regions, replacement refers to replacing the subregion with a new subregion, so that the original subregion is different from the modified subregion. With the above modifications, it is possible to make the atomic region different from the new subregion.
- the step S103 includes steps S201-S203:
- the non-critical part In order to ensure a big difference between the modified non-critical part and the original non-critical part, it is necessary to split the non-critical part into multiple sub-regions, and the number of sub-regions obtained by splitting should not be less than third threshold.
- the initial mechanism of the original non-critical part can be recorded first, and then divided according to the irregular shape, so as to split into several sub-regions, and each split sub-region can be labeled for restoration.
- the extraction method is random extraction, which can improve the security of encryption and avoid reverse cracking.
- the extracted sub-areas There should also be a limit on the number of , which is set here to be no less than the fourth threshold in order to improve the security of encryption.
- the fourth threshold here should be smaller than the third threshold, and the extraction method is random extraction, for example, five sub-areas are extracted from ten sub-areas.
- one or more of the modification methods such as addition, deletion or replacement can be selected to modify the extracted sub-regions.
- modification methods such as addition, deletion or replacement
- multiple modification methods can be used to modify multiple sub-areas at the same time, for example, a certain sub-area is modified using the modification method, and another sub-area is modified using the modification method 2. , and use modification method 3 to modify other sub-areas.
- multiple modification methods may be used to modify the same sub-area at the same time, for example, three kinds of modifications are performed to a certain sub-area.
- the step S203 includes:
- the feature maps when modifying a sub-region, several feature maps can be selected from the sub-region, and then the feature maps can be blurred, deleted or covered, so that the purpose of modifying the sub-region can be achieved.
- the method can be realized by pixel reduction, coding, etc.
- the deletion method is to directly delete the selected feature map, so that the corresponding sub-region becomes an incomplete sub-region, and the overlay operation is to use a predetermined image to perform the feature map. Overwriting can also achieve the purpose of modifying the sub-area.
- the selected feature map can also be directly replaced by the feature map in the feature library, so that the corresponding sub-region can be distinguished from the original sub-region. Compared with the previous modification, this The point is to replace the entire feature map selected, and the change is larger than the previous modification.
- the encryption scheme may be set in advance, that is, the third threshold value, the fourth threshold value and the modification method are set, so as to be modified according to the encryption scheme in the process of secondary encryption subsequently.
- the modified sub-regions are recombined with other unmodified sub-regions, so as to restore the standard non-critical part, and the standard non-critical part can be recombined with the original key part as a whole, so as to restore the human body.
- Face recognition information here is not the same as the original face recognition information.
- the restored face recognition information is called standard face recognition information. The difference lies in the non-critical parts. In this way, the secondary encryption of the original face recognition information is realized.
- the standard face recognition information obtained after secondary encryption and the user identity information are stored in association, so that the user identity can be confirmed.
- the step S104 includes steps S301 to S303:
- the modified sub-regions are marked first, that is, which sub-regions have been modified, so that when the splicing and combination are performed, the modified sub-regions can be compared with the non-critical parts according to the initial structure of the non-critical part.
- the modified sub-regions are spliced and combined to obtain the restored standard non-critical part, and the restored standard non-critical part has the same structure as the original non-critical part.
- the non-critical parts and the restored non-critical parts are also recombined in sequence, so as to obtain the face recognition information after secondary encryption, and the face recognition information after secondary encryption is the same as the original face recognition information.
- the structure is the same. Specifically, the initial structure of the original face recognition information is obtained first, and a structural template of the original face recognition information is generated according to the initial structure, and the structural template is provided with an area for placing key parts and an area for non-critical parts, Therefore, it is only necessary to fill the original key parts and the restored standard non-key parts into the corresponding positions in the structure template to complete the restoration steps, and finally form the standard face recognition information after secondary encryption.
- This step is to associate the standard face recognition information after secondary encryption with the user identity information, that is, to associate the standard face recognition information with the user identity information one by one, and then save the corresponding relationship, and finally use the standard face after secondary encryption. Identifying information to confirm the identity of the user.
- step S105 when the user performs identity recognition in a certain scene, for example, he needs to pass the access control or unlock the electronic device, then he can input his own face recognition information, and then the face recognition information input by the user in real time is saved with the saved face recognition information.
- the standard face recognition information of the secondary encryption is compared. When the comparison is consistent, it means that the user identity identification has passed, thereby opening the door or unlocking the electronic device.
- the above-mentioned secondary encryption can make even if the face recognition information is stolen, only the standard face recognition information after secondary encryption is stolen.
- the identification information is different from the real face identification information. Except for the current application scenario, the thief cannot use the standard face identification information in other application scenarios, so the security risk is greatly reduced.
- the step S105 includes steps S401-S403:
- This step is to split the real-time input target face recognition information to obtain key parts and non-critical parts.
- the key parts obtained here will be split. It is called the target key part, and the non-critical part obtained by splitting is called the target non-critical part.
- the standard face recognition information after secondary encryption is split, and the key parts and non-key parts can also be obtained.
- the split obtained The critical part is called the original critical part
- the non-critical part obtained by splitting is called the standard non-critical part.
- This step is to first match the real-time input target face recognition information and the key parts of the secondary encrypted standard face recognition information, specifically extract the feature values of the target key part and the original key part, and then extract the target key part and the original key part.
- the first eigenvalue and the second eigenvalue of are matched to calculate the matching degree, and the calculated matching degree here is called the first matching degree.
- a traditional extraction method may be adopted, for example, a histogram feature extraction method or an edge feature extraction method may be adopted, which is not limited in the present application, that is, the present application
- the existing feature value extraction method can be used to extract features, but the present application needs to extract and process key parts and non-key parts respectively, so as to realize identity recognition.
- the calculation method of the matching degree may adopt the cosine similarity calculation method or the Euclidean distance calculation method.
- the target face recognition information input in real time and the key parts of the standard face recognition information after secondary encryption should be It has a high degree of matching, so this embodiment of the present application can set a higher first threshold, so that if the calculated first degree of matching is greater than the first threshold, it means that the basic recognition has passed, but it is still impossible to confirm whether the non-critical part is not. It can be identified and passed, so the subsequent steps need to continue to identify the non-critical parts.
- the target key part of the target face recognition information After the target key part of the target face recognition information is recognized, extract the feature values of the target non-critical part and the standard non-critical part, and match the extracted third feature value and fourth feature value to obtain the first Second matching degree, when the second matching degree exceeds the second threshold, it is determined that the target non-critical part of the target face recognition information has passed the recognition, and it is confirmed that the identity recognition is successful.
- the size of the second matching degree has a greater relationship with the number of modified sub-regions in the secondary encryption process. The more sub-regions are modified, the smaller the second matching degree is. If the second matching degree is less, the greater the second matching degree here, so in this embodiment of the present application, a second threshold may be preset, and then the second matching degree is compared with the second threshold. If the second matching degree is greater than the second threshold, It is considered that the target non-critical part of the target face recognition information has passed the recognition, which actually means that the unmodified sub-region basically matches, so it can be determined that the target non-critical part of the target face recognition information has passed the recognition.
- the second threshold is inversely proportional to the number of modified sub-regions, that is, the greater the number of modified sub-regions, the smaller the second threshold can be, and the smaller the number of modified sub-regions, the smaller the number of modified sub-regions can be.
- the second threshold is set to be larger.
- step S105 before the step S105, it further includes:
- a face comparison request input by a user is received, and standard face recognition information having a mapping relationship with the user identification code in the face comparison request is extracted from the face comparison database.
- the user can first input a face comparison request, such as clicking an authentication instruction, etc., and then obtain the user identification code in the face comparison request, and then obtain the corresponding face comparison database according to the user identification code.
- Standard face recognition information so as to compare the real-time input target face recognition information with the standard face recognition information.
- the method for secondary encryption of the face recognition information further includes:
- the standard face recognition information in the face comparison information database is deleted, the original face recognition information of the user is re-entered, and then the re-entered original face recognition information is subjected to two Secondary encryption, and the standard face recognition information obtained after secondary encryption and user identity information are associated and saved.
- the standard face recognition information when the standard face recognition information needs to be replaced, it is only necessary to re-enter the user's original face recognition information, and then perform secondary encryption on the re-entered original face recognition information according to the aforementioned method, so that after the secondary encryption
- the standard face recognition information is different from the original standard face recognition information after secondary encryption, so that the purpose of changing the face recognition information at any time can be achieved and the purpose of reducing security risks can be achieved.
- Users can regularly change the standard face recognition information to achieve the same effect as the traditional regular password change, which can improve the security of face recognition information. Users can also change the standard face recognition information at any time to achieve the same effect as the traditional password change at any time, and also improve the security of face recognition information. At the same time, compared with the situation where the password is stolen, even if the standard face recognition information is stolen, because it is encrypted twice, it can only cause security risks in the current application scenario, but cannot be used in other application scenarios. The risk of the embezzlement of standard face recognition information with secondary encryption is greatly reduced.
- the embodiment of the present application also provides a secondary encryption device for face recognition information, and the secondary encryption device for face recognition information is used to execute any embodiment of the foregoing method for secondary encryption of face recognition information .
- FIG. 5 is a schematic block diagram of an apparatus for secondary encryption of face recognition information provided by an embodiment of the present application.
- the apparatus 500 for secondary encryption of the face recognition information can be configured in the server.
- the apparatus 500 for secondary encryption of the face recognition information may include:
- An entry unit 501 used to pre-enter the user's original face recognition information and user identity information;
- Splitting unit 502 for splitting the original key part that can be used for identity recognition from the original face recognition information, and using the remaining part in the original face recognition information as the original non-critical part;
- a modification unit 503 configured to split the original non-critical part into several sub-regions, and modify at least one sub-region in the several sub-regions;
- the combining unit 504 is used to recombine the modified sub-region and the unmodified sub-region into a standard non-critical part, and splicing the standard non-critical part and the original key part to realize the original face Secondary encryption of identification information, the standard face recognition information obtained after secondary encryption and the user identity information are associated and stored to obtain a face comparison information database;
- the identification unit 505 is configured to receive the target face recognition information input by the user in real time when identification is required, and compare the target face recognition information input by the user in real time with the standard in the face comparison information database The face recognition information is compared, and when the comparison is consistent, the identity recognition is confirmed to be successful.
- the combining unit 504 includes:
- the splicing unit 601 is used to mark the modified sub-region, and sequentially splicing and combining the modified sub-region and the unmodified sub-region to form the restored standard non-critical part;
- the recombination unit 602 is used to obtain the initial structure of the original face recognition information, set the structure template of the original face recognition information according to the initial structure, and compare the original key parts with the restored standard non-standard information.
- the key part is filled into the structural template to form the standard face recognition information after secondary encryption;
- the association saving unit 603 is configured to associate the standard face recognition information after secondary encryption with the user identity information, and save the corresponding relationship between the standard face recognition information after secondary encryption and the user identity information.
- the identifying unit 505 includes:
- the first splitting unit 701 is used to split the target face recognition information input by the user in real time to obtain the target key part and the target non-critical part;
- the comparison unit 703 is used to extract the first feature value and the second feature value from the target key part and the original key part respectively, and match the first feature value and the second feature value to obtain the first feature value. Matching degree, when the first matching degree exceeds the first threshold, it is determined that the target key part of the target face recognition information has passed; Extract the third feature value and the fourth feature value from the key part and the standard non-critical part, and match the third feature value and the fourth feature value to obtain the second matching degree, when the second matching degree exceeds the second threshold value , then it is determined that the target non-critical part of the target face recognition information has passed the recognition, and it is confirmed that the identity recognition is successful.
- the modifying unit 503 includes:
- a splitting subunit 801 configured to split the original non-critical part into several subregions whose number is not less than a third threshold
- an extraction unit 802 configured to randomly extract several sub-regions whose number is not less than a fourth threshold from the several sub-regions;
- the modification subunit 804 is configured to modify the extracted sub-regions according to a preset modification method.
- the modifying subunit 804 includes:
- the feature map modification unit is used to select several feature maps from each extracted sub-region, perform operations of blurring, deleting or covering the selected feature map, and save the modified sub-region;
- the feature map replacement unit is used to select several feature maps from each extracted sub-region, and randomly select the same number of feature maps from the preset feature library, replace the selected several feature maps, and save them Modified sub area
- the secondary encryption device 500 for the face recognition information further includes:
- the extraction unit is configured to receive a face comparison request input by a user, and extract from the face comparison database standard face recognition information that has a mapping relationship with the user identification code in the face comparison request.
- the secondary encryption device 500 for the face recognition information further includes:
- the replacement unit is used to delete the standard face recognition information in the face comparison information database when the standard face recognition information needs to be replaced, re-enter the user's original face recognition information, and then re-enter the original face recognition information.
- the face recognition information is encrypted twice, and the standard face recognition information obtained after the secondary encryption is stored in association with the user identity information.
- the face recognition information can be changed at any time or periodically as needed, thereby improving the security of the face recognition information.
- the above-mentioned apparatus 500 for secondary encryption of face recognition information can be implemented in the form of a computer program, and the computer program can be executed on a computer device as shown in FIG. 9 .
- FIG. 9 is a schematic block diagram of a computer device provided by an embodiment of the present application.
- the computer device 9 is a server, and the server may be an independent server or a server cluster composed of multiple servers.
- the computer device 900 includes a processor 902 , a memory and a network interface 905 connected by a system bus 901 , wherein the memory may include a non-volatile storage medium 903 and an internal memory 904 .
- the nonvolatile storage medium 903 can store an operating system 9031 and a computer program 9032 .
- the computer program 9032 When executed, it can cause the processor 902 to execute the secondary encryption method of the face recognition information.
- the processor 902 is used to provide computing and control capabilities to support the operation of the entire computer device 900 .
- the internal memory 904 provides an environment for running the computer program 9032 in the non-volatile storage medium 903.
- the processor 902 can execute the secondary encryption method of the face recognition information.
- the network interface 905 is used for network communication, such as providing transmission of data information.
- the network interface 905 is used for network communication, such as providing transmission of data information.
- FIG. 9 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device 900 to which the solution of the present application is applied.
- the specific computer device 900 may include more or fewer components than shown, or combine certain components, or have a different arrangement of components.
- the processor 902 is used to run the computer program 9032 stored in the memory to realize the following functions: pre-enter the user's original face recognition information and user identity information;
- the original key part that can be used for identification, and the remaining part of the original face recognition information is used as the original non-critical part;
- the original non-critical part is divided into several sub-regions, and the At least one sub-region is modified;
- the modified sub-region and the unmodified sub-region are recombined into standard non-critical parts, and the standard non-critical parts are spliced with the original key parts to realize the original Secondary encryption of face recognition information, the standard face recognition information obtained after secondary encryption and the user identity information are associated and saved to obtain a face comparison information database;
- identity recognition is required, real-time input from the user is received
- the target face recognition information is compared, and the target face recognition information input by the user in real time is compared with the standard face recognition information in the face comparison information database. When the comparison is consistent, it is confirmed that the identity recognition
- the embodiment of the computer device shown in FIG. 9 does not constitute a limitation on the specific structure of the computer device.
- the computer device may include more or less components than those shown in the drawings. Either some components are combined, or different component arrangements.
- the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those of the embodiment shown in FIG. 9 , and details are not repeated here.
- the processor 902 may be a central processing unit (Central Processing Unit, CPU), and the processor 902 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like.
- a computer-readable storage medium may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium.
- the computer-readable storage medium stores a computer program, wherein when the computer program is executed by the processor, the following steps are implemented: pre-recording the user's original face recognition information and user identity information; The original key part of identity recognition, and the remaining part of the original face recognition information is regarded as the original non-critical part; the original non-critical part is divided into several sub-regions, and at least one of the several sub-regions is divided into several sub-regions.
- One sub-region is modified; the modified sub-region and the unmodified sub-region are recombined into standard non-critical parts, and the standard non-critical parts and the original key parts are spliced to realize the original face
- the standard face recognition information obtained after secondary encryption and the user identity information are associated and stored to obtain a face comparison information database; when identification is required, receive the real-time input from the user.
- the target face recognition information the target face recognition information input by the user in real time is compared with the standard face recognition information in the face comparison information database, and when the comparison is consistent, it is confirmed that the identity recognition is successful.
- the disclosed apparatus, apparatus and method may be implemented in other manners.
- the apparatus embodiments described above are only illustrative.
- the division of the units is only logical function division.
- there may be other division methods, or units with the same function may be grouped into one Units, such as multiple units or components, may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
- the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
一种人脸识别信息的二次加密方法、装置、设备及存储介质,涉及身份认证技术领域,方法包括:从人脸识别信息中拆分出关键部分和非关键部分;将所述非关键部分拆分为若干个子区域,抽取至少一个子区域,并对所抽取的子区域进行修改;将修改后的子区域与其他子区域重新组合为非关键部分,并将重新组合的非关键部分与关键部分进行拼接,实现对人脸识别信息的二次加密,将二次加密后的人脸识别信息和用户身份信息进行关联保存;当需要进行身份识别时,接收用户实时输入的人脸识别信息,将用户实时输入的人脸识别信息与二次加密后的人脸识别信息进行比对,当比对通过时,则控制身份识别成功。通过所述方法,提高了人脸识别信息的安全性。
Description
本申请要求于2020年11月06日提交中国专利局、申请号为202011231052.1,发明名称为“人脸识别信息的二次加密方法、装置、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及身份认证技术领域,尤其涉及人脸识别信息的二次加密方法、装置、设备及存储介质。
人脸识别已经广泛应用于手机识别、客户支付等商业场景,这种识别方式使用起来非常便捷。但是方便之余,不免让人对信息安全产生担心。常见的用户密码可以经常变更,以确保密码的安全性,但是,发明人意识到人脸等隐私信息具有唯一性、长期不可更改性等特性,这导致人脸识别信息一旦被盗用,用户在人脸认证识别的各种场景都会产生隐患和风险。
申请内容
本申请实施例提供了人脸识别信息的二次加密方法、装置、设备及存储介质,旨在解决现有人脸识别技术存在安全隐患的问题。
第一方面,本申请实施例提供一种人脸识别信息的二次加密方法,其中,包括:
预先录入用户的原始人脸识别信息和用户身份信息;
从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;
将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;
将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;
当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
第二方面,本申请实施例提供一种人脸识别信息的二次加密装置,其中,包括:
录入单元,用于预先录入用户的原始人脸识别信息和用户身份信息;
拆分单元,用于从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;
修改单元,用于将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;
组合单元,用于将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将 所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;
识别单元,用于当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
第三方面,本申请实施例提供一种计算机设备,包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序,其中,所述处理器执行所述计算机程序时实现如第一方面所述的人脸识别信息的二次加密方法。
第四方面,本申请实施例提供一种计算机可读存储介质,其中,所述计算机可读存储介质存储有计算机程序,所述计算机程序当被处理器执行时使所述处理器执行如第一方面所述的人脸识别信息的二次加密方法。
本申请实施例提供了人脸识别信息的二次加密方法、装置、设备及存储介质,本申请实施例中,用户可以定期或随时更改人脸识别信息,从而提高人脸识别信息的安全性,也不影响识别的便捷性。
为了更清楚地说明本申请实施例技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的人脸识别信息的二次加密方法的流程示意图;
图2为本申请实施例提供的人脸识别信息的二次加密方法的子流程示意图;
图3为本申请实施例提供的人脸识别信息的二次加密方法的另一子流程示意图;
图4为本申请实施例提供的一种人脸识别信息的二次加密方法的另一子流程示意图;
图5为本申请实施例提供的一种人脸识别信息的二次加密装置的示意性框图;
图6为本申请实施例提供的一种人脸识别信息的二次加密装置的子单元示意性框图;
图7为本申请实施例提供的一种人脸识别信息的二次加密装置的另一子单元示意性框图;
图8为本申请实施例提供的一种人脸识别信息的二次加密装置的另一子单元示意性框图;
图9为本申请实施例提供的计算机设备的示意性框图。
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
请参阅图1,图1为本申请实施例提供的一种人脸识别信息的二次加密方法的流程示意图,如图所示,其包括步骤S101~S105:
S101、预先录入用户的原始人脸识别信息和用户身份信息;
S102、从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;
S103、将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;
S104、将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;
S105、当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
具体的,在所述步骤S101中,所述原始人脸识别信息即指用户的脸部特征信息。
所述用户身份信息即代表用户的身份,可以包含用户的姓名、身份证、用户识别码、联系方式、平台登录信息等。
当需要进行身份识别时,用户只需输入人脸识别信息,然后对实时输入的目标人脸识别信息与保存的标准人脸识别信息进行比对,比对一致则根据标准人脸识别信息与用户身份信息的关联关系,可以获取用户身份信息,从而实现身份识别。
在所述步骤S102中,在所述原始人脸识别信息中包含有关键部分(为方便区分,此处称为原始关键部分)和非关键部分(为方便区分,此处称为原始非关键部分),其中关键部分是指能够表征用户特征的最少部分,即只有人脸识别信息包含了关键部分,才能对用户进行唯一识别。非关键部分则是除关键部分之外的可选部分,这部分内容可以帮助识别,但并不是必须的。例如对于人脸识别信息,关键部分可以是面部信息,非关键部分可以是头发、 头发延伸、发型等等。拆分的方式可以是从原始人脸识别信息中的中心开始逐渐进行放大,并将放大后识别成功率达到预设阈值的最小区域作为关键部分,将剩余区域作为非关键部分。放大的方式可以是以标准人脸的形状进行放大,也可以是以矩形或者圆形的形状进行放大。
在所述步骤S103中,将原始非关键部分拆分成了多个子区域,以便对这些子区域进行修改。修改的范围可以是一个子区域,也可以是多个子区域,但不是全部的子区域,以便后续进行识别时,可以对非关键部分进行比对。
本申请实施例对子区域的修改方式可以是增加、删除或者替换等。增加是指在子区域中增加一部分内容,使原有的子区域与修改后的子区域不同,删除是指在子区域中删除一部分内容或者全部内容,使原有的子区域与修改后的子区域不同,替换是指将子区域替换成一个新的子区域,从而使原有的子区域与修改后的子区域不同。通过上述修改,都可以使原子区域与新子区域不同。
在一实施例中,如图2所示,所述步骤S103包括步骤S201~S203:
S201、将所述原始非关键部分拆分成数量不少于第三阈值的若干个子区域;
为了保证修改后的非关键部分与原有的非关键部分之间产生较大的区别,此处需要将非关键部分拆分成多个子区域,且拆分得到的子区域的数量应不少于第三阈值。在进行拆分时,可先记录原始非关键部分的初始机构,然后按照不规则形状进行划分,从而拆分出若干子区域,并对每一个拆分出的子区域进行标号,以便进行还原。
S202、从所述若干个子区域中随机抽取数量不少于第四阈值的若干个子区域;
本步骤中,会从上一步骤中拆分出的子区域中抽取出若干个子区域,抽取的方式为随机抽取,这样可以提高加密的安全性,避免被反向破解,另外抽取出的子区域的数量也应具有限制,此处设置为不少于第四阈值,以便提高加密的安全性。
此处的第四阈值应小于第三阈值,抽取的方式为随机抽取,例如从十个子区域中抽取5个子区域。
S203、按照预设的修改方式对抽取到的若干子区域进行修改。
本步骤中,可以选择增加、删除或替换等修改方式中的一种或几种,对抽取到的若干子区域进行修改。在进行修改时,需对修改的子区域进行标记,这样方便将修改的子区域与未修改的子区域进行组合。
本申请实施例中,为了提高加密的安全性,可以同时使用多种修改方式对多个子区域进行修改,例如使用修改方式一对某个子区域进行修改,使用修改方式二对另外的子区域进行修改,使用修改方式三对其他子区域进行修改。另外,本申请实施例中,还可以同时使用多种修改方式对同一个子区域进行修改,例如对某个子区域进行三种修改。
在一实施例中,所述步骤S203包括:
从每一个抽取到的子区域中选择若干特征图,对所选择的特征图进行模糊、删除或者覆盖的操作,并保存修改后的子区域;
或者,从每一个抽取到的子区域中选择若干特征图,并从预设的特征库中随机选择同样数量的特征图,对选择的若干特征图进行替换,并保存修改后的子区域。
本实施例中,在对子区域进行修改时,可以从该子区域中选择若干特征图,然后对特征图进行模糊、删除或者覆盖的操作,这样可以达到对子区域进行修改的目的,模糊的方式可以采用降低像素、打码等方式实现,删除的方式则是直接将选择的特征图删除,使相应的子区域成为不完整的子区域,覆盖的操作则是使用预定的图像对特征图进行覆盖,同样能达到对子区域进行修改的目的。
另外,本实施例中,还可以直接使用特征库中的特征图对所选择的特征图进行替换,从而使相应的子区域与原始的子区域区别开来,与前面的修改方式相比,此处是对所选择的整个特征图进行替换,其改动相对于前面的修改方式更大。
本申请实施例中,可以提前设置好加密方案,即设置好第三阈值、第四阈值和修改方式,以便后续在进行二次加密的过程中按照加密方案进行修改。
所述步骤S104中,将修改后的子区域与其他未修改的子区域重新组合,从而还原得到标准非关键部分,该标准非关键部分可以作为一个整体与原始关键部分重新组合,从而还原得到人脸识别信息,此处还原得到的人脸识别信息与原始人脸识别信息并不相同,为方便区分将还原得到的人脸识别信息称为标准人脸识别信息,不同的地方在于非关键部分,这样实现了对原始人脸识别信息的二次加密。
然后将二次加密后得到的标准人脸识别信息和用户身份信息进行关联保存,这样可以实现对用户身份的确认。
在一实施例中,如图3所示,所述步骤S104包括步骤S301~S303:
S301、对修改后的子区域进行标记,并按顺序将所述修改后的子区域与所述未修改的子区域进行拼接组合,形成还原后的所述标准非关键部分;
本申请实施例中,先对修改后的子区域进行标记,即标记出哪些子区域进行过修改,这样在进行拼接组合时,就能按照非关键部分的初始结构将修改后的子区域与未修改的子区域进行拼接组合,从而得到还原后的标准非关键部分,并且还原后的标准非关键部分与原始非关键部分结构相同。
S302、获取所述原始人脸识别信息的初始结构,按照所述初始结构设置所述原始人脸识别信息的结构模板,将所述原始关键部分与还原后的所述标准非关键部分填充至所述结构模板中,形成二次加密后的标准人脸识别信息;
此步骤同样是按照顺序将非关键部分与还原后的非关键部分进行重新组合,从而得到二次加密后的人脸识别信息,并且二次加密后的人脸识别信息与原始的人脸识别信息结构相同。具体的,先获取原始人脸识别信息的初始结构,并且根据该初始结构生成原始人脸识别信息的结构模板,在所述结构模板中设置有用于放置关键部分的区域和非关键部分的区域,所以只需将原始关键部分与还原后的标准非关键部分填充到结构模板中的相应位置,即可完成还原的步骤,最终形成二次加密后的标准人脸识别信息。
S303、将二次加密后的标准人脸识别信息和用户身份信息进行关联,并保存所述二次加密后的标准人脸识别信息和用户身份信息的对应关系。
此步骤即将二次加密后的标准人脸识别信息和用户身份信息关联,即将标准人脸识别信 息与用户身份信息一一对应,然后将对应关系保存,最终需要利用二次加密后的标准人脸识别信息来确认用户身份。
所述步骤S105中,当用户在某一场景中进行身份识别时,例如需要通过门禁或者解锁电子设备,那么可以输入自身的人脸识别信息,然后将用户实时输入的人脸识别信息与所保存的二次加密的标准人脸识别信息进行比对,当比对一致时,代表用户身份识别通过,从而打开门禁或者解锁电子设备。
由于人脸识别信息也可能会被盗用,所以通过上述的二次加密可以使得即使人脸识别信息被盗,被盗的也仅仅是经过二次加密后的标准人脸识别信息,此标准人脸识别信息与真实的人脸识别信息有所区别,盗取人除了在当前应用场景下,无法在其他应用场景中使用该标准人脸识别信息,所以大大降低了安全风险。
在一实施例中,如图4所示,所述步骤S105包括步骤S401~S403:
S401、对所述用户实时输入的目标人脸识别信息进行拆分,得到其中的目标关键部分和目标非关键部分;
此步骤是将实时输入的目标人脸识别信息进行拆分,从而得到关键部分和非关键部分,为了与二次加密后的标准人脸识别信息进行区分,所以此处将拆分得到的关键部分称为目标关键部分,将拆分得到的非关键部分称为目标非关键部分。
S402、对所述标准人脸识别信息进行拆分,得到其中的原始关键部分和标准非关键部分;
此步骤中,将二次加密后的标准人脸识别信息进行拆分,同样可以得到关键部分和非关键部分,为了与实时输入的目标人脸识别信息进行区分,所以此处将拆分得到的关键部分称为原始关键部分,将拆分得到的非关键部分称为标准非关键部分。
S403、分别从所述目标关键部分和原始关键部分中提取第一特征值和第二特征值,并将所述第一特征值和所述第二特征值进行匹配得到第一匹配度,当第一匹配度超过第一阈值时,则判定所述目标人脸识别信息的目标关键部分识别通过;所述目标人脸识别信息的关键部分识别通过后,分别从所述目标非关键部分和标准非关键部分中提取第三特征值和第四特征值,并将所述第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时,则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功;
此步骤是先对实时输入的目标人脸识别信息和二次加密后的标准人脸识别信息中的关键部分进行匹配,具体是分别提取目标关键部分和原始关键部分的特征值,然后将提取到的第一特征值和第二特征值进行匹配,从而计算出匹配度,此处计算出的匹配度称为第一匹配度。本申请实施例中对于关键部分和非关键部分的特征值提取方法,可以采用传统的提取方法,例如可以采用直方图特征提取方式或者边缘特征提取方式,本申请对此并不限定,即本申请可以采用现有的特征值提取方法来提取特征,只是本申请需要针对关键部分和非关键部分分别进行提取和处理,从而实现身份识别。匹配度的计算方式可以采用余弦相似度计算方式或者欧式距离计算方式。
由于对于二次加密后的标准人脸识别信息而言,其中的关键部分并未进行过修改,所以实时输入的目标人脸识别信息与二次加密后的标准人脸识别信息中的关键部分应该具有较高 的匹配度,故本申请实施例可以设置一个较高的第一阈值,这样如果计算出的第一匹配度大于第一阈值时,代表基本识别通过,但还不能确认非关键部分是否能够识别通过,所以后续步骤需要继续对非关键部分进行识别。
当所述目标人脸识别信息的目标关键部分识别通过后,提取所述目标非关键部分和标准非关键部分的特征值,并将提取到的第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时,则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功。
显然第二匹配度的大小与二次加密过程中修改的子区域的数量有较大关系,若修改的子区域越多,那么此处的第二匹配度就越小,若修改的子区域越少,那么此处的第二匹配度就越大,所以本申请实施例可以预先设置一个第二阈值,然后将第二匹配度与第二阈值进行比较,如果第二匹配度大于第二阈值,则认为所述目标人脸识别信息的目标非关键部分识别通过,实际上就代表了未修改的子区域基本匹配,所以可以判定所述目标人脸识别信息的目标非关键部分识别通过。
所述的第二阈值与修改的子区域的数量成反比,即修改的子区域的数量越多,那么可以将第二阈值设置成较小,修改的子区域的数量越少,则可以将第二阈值设置成较大。
在一实施例中,所述步骤S105之前,还包括:
接收用户输入的人脸比对请求,从所述人脸比对数据库中提取与所述人脸比对请求中用户识别码具有映射关系的标准人脸识别信息。
本实施例中,用户可先输入人脸比对请求,例如点击认证指令等,然后获取人脸比对请求中的用户识别码,再根据该用户识别码从人脸比对数据库中获取对应的标准人脸识别信息,从而对实时输入的目标人脸识别信息与标准人脸识别信息进行比对。
在一实施例中,所述的人脸识别信息的二次加密方法还包括:
当需要更换标准人脸识别信息时,将所述人脸比对信息数据库中的标准人脸识别信息删除,重新录入用户的原始人脸识别信息,然后对重新录入的原始人脸识别信息进行二次加密,并将二次加密后得到的标准人脸识别信息和用户身份信息进行关联保存。
本步骤中,当需要更换标准人脸识别信息时,只需重新录入用户的原始人脸识别信息,然后按照前述的方法对重新录入的原始人脸识别信息进行二次加密,使得二次加密后的标准人脸识别信息与原有的二次加密后的标准人脸识别信息不同,这样就可以实现随时更换人脸识别信息的目的,实现降低安全风险的目的。
用户可以定期更换标准人脸识别信息,实现与传统定期更换密码同样的效果,这样可以提高人脸识别信息的安全性。用户也可以随时更换标准人脸识别信息,实现与传统随时更换密码同样的效果,也能提高人脸识别信息的安全性。同时相比较于密码被盗用的情况,即使标准人脸识别信息被盗,由于其经过二次加密,所以也只能在当前应用场景下可能产生安全风险,而无法在其他应用场景下使用,所以二次加密的标准人脸识别信息被盗用产生的风险大大降低。
也就是说,本申请实施例中,在不同的应用场景下,可以采用不同的加密方案,这样即 使某个标准人脸识别信息被盗,也不会影响该用户在其他应用场景下的信息安全,从而降低了安全隐患。
本申请实施例还提供一种人脸识别信息的二次加密装置,该一种人脸识别信息的二次加密装置用于执行前述一种人脸识别信息的二次加密方法的任一实施例。具体地,请参阅图5,图5是本申请实施例提供的人脸识别信息的二次加密装置的示意性框图。该人脸识别信息的二次加密装置500可以配置于服务器中。
该人脸识别信息的二次加密装置500可以包括:
录入单元501,用于预先录入用户的原始人脸识别信息和用户身份信息;
拆分单元502,用于从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;
修改单元503,用于将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;
组合单元504,用于将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;
识别单元505,用于当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
在一实施例中,如图6所示,所述组合单元504包括:
拼接单元601,用于对修改后的子区域进行标记,并按顺序将所述修改后的子区域与所述未修改的子区域进行拼接组合,形成还原后的所述标准非关键部分;
重新组合单元602,用于获取所述原始人脸识别信息的初始结构,按照所述初始结构设置所述原始人脸识别信息的结构模板,将所述原始关键部分与还原后的所述标准非关键部分填充至所述结构模板中,形成二次加密后的标准人脸识别信息;
关联保存单元603,用于将二次加密后的标准人脸识别信息和用户身份信息进行关联,并保存所述二次加密后的标准人脸识别信息和用户身份信息的对应关系。
在一实施例中,如图7所示,所述识别单元505包括:
第一拆分单元701,用于对所述用户实时输入的目标人脸识别信息进行拆分,得到其中的目标关键部分和目标非关键部分;
第二拆分单元702,用于对所述标准人脸识别信息进行拆分,得到其中的原始关键部分和标准非关键部分;
比对单元703,用于分别从所述目标关键部分和原始关键部分中提取第一特征值和第二特征值,并将所述第一特征值和所述第二特征值进行匹配得到第一匹配度,当第一匹配度超过第一阈值时,则判定所述目标人脸识别信息的目标关键部分识别通过;所述目标人脸识别信息的关键部分识别通过后,分别从所述目标非关键部分和标准非关键部分中提取第三特征 值和第四特征值,并将所述第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时,则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功。
在一实施例中,如图8所示,所述修改单元503包括:
拆分子单元801,用于将所述原始非关键部分拆分成数量不少于第三阈值的若干个子区域;
抽取单元802,用于从所述若干个子区域中随机抽取数量不少于第四阈值的若干个子区域;
修改子单元804,用于按照预设的修改方式对抽取到的若干子区域进行修改。
在一实施例中,所述修改子单元804包括:
特征图修改单元,用于从每一个抽取到的子区域中选择若干特征图,对所选择的特征图进行模糊、删除或者覆盖的操作,并保存修改后的子区域;
或者,特征图替换单元,用于从每一个抽取到的子区域中选择若干特征图,并从预设的特征库中随机选择同样数量的特征图,对选择的若干特征图进行替换,并保存修改后的子区域
在一实施例中,所述的人脸识别信息的二次加密装置500还包括:
提取单元,用于接收用户输入的人脸比对请求,从所述人脸比对数据库中提取与所述人脸比对请求中用户识别码具有映射关系的标准人脸识别信息。
在一实施例中,所述的人脸识别信息的二次加密装置500还包括:
更换单元,用于当需要更换标准人脸识别信息时,将所述人脸比对信息数据库中的标准人脸识别信息删除,重新录入用户的原始人脸识别信息,然后对重新录入的原始人脸识别信息进行二次加密,并将二次加密后得到的标准人脸识别信息和用户身份信息进行关联保存。
基于本申请实施例提供的人脸识别信息的二次加密装置500,可以根据需要随时或定期更换人脸识别信息,从而提高人脸识别信息的安全性。
上述人脸识别信息的二次加密装置500可以实现为计算机程序的形式,该计算机程序可以在如图9所示的计算机设备上运行。
请参阅图9,图9是本申请实施例提供的计算机设备的示意性框图。该计算机设备9是服务器,服务器可以是独立的服务器,也可以是多个服务器组成的服务器集群。
参阅图9,该计算机设备900包括通过系统总线901连接的处理器902、存储器和网络接口905,其中,存储器可以包括非易失性存储介质903和内存储器904。
该非易失性存储介质903可存储操作系统9031和计算机程序9032。该计算机程序9032被执行时,可使得处理器902执行人脸识别信息的二次加密方法。
该处理器902用于提供计算和控制能力,支撑整个计算机设备900的运行。
该内存储器904为非易失性存储介质903中的计算机程序9032的运行提供环境,该计算机程序9032被处理器902执行时,可使得处理器902执行人脸识别信息的二次加密方法。
该网络接口905用于进行网络通信,如提供数据信息的传输等。本领域技术人员可以理 解,图9中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备900的限定,具体的计算机设备900可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
其中,所述处理器902用于运行存储在存储器中的计算机程序9032,以实现如下功能:预先录入用户的原始人脸识别信息和用户身份信息;从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
本领域技术人员可以理解,图9中示出的计算机设备的实施例并不构成对计算机设备具体构成的限定,在其他实施例中,计算机设备可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。例如,在一些实施例中,计算机设备可以仅包括存储器及处理器,在这样的实施例中,存储器及处理器的结构及功能与图9所示实施例一致,在此不再赘述。
应当理解,在本申请实施例中,处理器902可以是中央处理单元(Central Processing Unit,CPU),该处理器902还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中,通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在本申请的另一实施例中提供计算机可读存储介质。该计算机可读存储介质可以为非易失性的计算机可读存储介质,也可以是易失性的计算机可读存储介质。该计算机可读存储介质存储有计算机程序,其中计算机程序被处理器执行时实现以下步骤:预先录入用户的原始人脸识别信息和用户身份信息;从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,上述描述的设备、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为逻辑功能划分,实际实现时可以有另外的划分方式,也可以将具有相同功能的单元集合成一个单元,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另外,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接,也可以是电的,机械的或其它的形式连接。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到各种等效的修改或替换,这些修改或替换都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以权利要求的保护范围为准。
Claims (20)
- 一种人脸识别信息的二次加密方法,其中,包括:预先录入用户的原始人脸识别信息和用户身份信息;从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
- 根据权利要求1所述的人脸识别信息的二次加密方法,其中,所述将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库,包括:对修改后的子区域进行标记,并按顺序将所述修改后的子区域与所述未修改的子区域进行拼接组合,形成还原后的所述标准非关键部分;获取所述原始人脸识别信息的初始结构,按照所述初始结构设置所述原始人脸识别信息的结构模板,将所述原始关键部分与还原后的所述标准非关键部分填充至所述结构模板中,形成二次加密后的标准人脸识别信息;将二次加密后的标准人脸识别信息和用户身份信息进行关联,并保存所述二次加密后的标准人脸识别信息和用户身份信息的对应关系。
- 根据权利要求1所述的人脸识别信息的二次加密方法,其中,所述将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功,包括:对所述用户实时输入的目标人脸识别信息进行拆分,得到其中的目标关键部分和目标非关键部分;对所述标准人脸识别信息进行拆分,得到其中的原始关键部分和标准非关键部分;分别从所述目标关键部分和原始关键部分中提取第一特征值和第二特征值,并将所述第一特征值和所述第二特征值进行匹配得到第一匹配度,当第一匹配度超过第一阈值时,则判定所述目标人脸识别信息的目标关键部分识别通过;所述目标人脸识别信息的关键部分识别通过后,分别从所述目标非关键部分和标准非关键部分中提取第三特征值和第四特征值,并将所述第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时, 则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功。
- 根据权利要求1所述的人脸识别信息的二次加密方法,其中,所述将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改,包括:将所述原始非关键部分拆分成数量不少于第三阈值的若干个子区域;从所述若干个子区域中随机抽取数量不少于第四阈值的若干个子区域;按照预设的修改方式对抽取到的若干子区域进行修改。
- 根据权利要求4所述的人脸识别信息的二次加密方法,其中,所述按照预设的修改方式对抽取到的若干子区域进行修改,包括:从每一个抽取到的子区域中选择若干特征图,对所选择的特征图进行模糊、删除或者覆盖的操作,并保存修改后的子区域;或者,从每一个抽取到的子区域中选择若干特征图,并从预设的特征库中随机选择同样数量的特征图,对选择的若干特征图进行替换,并保存修改后的子区域。
- 根据权利要求1所述的人脸识别信息的二次加密方法,其中,所述当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功之前,还包括:接收用户输入的人脸比对请求,从所述人脸比对数据库中提取与所述人脸比对请求中用户识别码具有映射关系的标准人脸识别信息。
- 根据权利要求1所述的人脸识别信息的二次加密方法,其中,还包括:当需要更换标准人脸识别信息时,将所述人脸比对信息数据库中的标准人脸识别信息删除,重新录入用户的原始人脸识别信息,然后对重新录入的原始人脸识别信息进行二次加密,并将二次加密后得到的标准人脸识别信息和用户身份信息进行关联保存。
- 一种人脸识别信息的二次加密装置,其中,包括:录入单元,用于预先录入用户的原始人脸识别信息和用户身份信息;拆分单元,用于从所述原始人脸识别信息中拆分出可用于身份识别的原始关键部分,并将所述原始人脸识别信息中的剩余部分作为原始非关键部分;修改单元,用于将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改;组合单元,用于将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库;识别单元,用于当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功。
- 一种计算机设备,包括存储器、处理器及存储在所述存储器上并可在所述处理器上运 行的计算机程序,其中,所述处理器执行所述计算机程序时实现如权利要求1所述的人脸识别信息的二次加密方法。
- 根据权利要求9所述的计算机设备,其中,所述将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库,包括:对修改后的子区域进行标记,并按顺序将所述修改后的子区域与所述未修改的子区域进行拼接组合,形成还原后的所述标准非关键部分;获取所述原始人脸识别信息的初始结构,按照所述初始结构设置所述原始人脸识别信息的结构模板,将所述原始关键部分与还原后的所述标准非关键部分填充至所述结构模板中,形成二次加密后的标准人脸识别信息;将二次加密后的标准人脸识别信息和用户身份信息进行关联,并保存所述二次加密后的标准人脸识别信息和用户身份信息的对应关系。
- 根据权利要求9所述的计算机设备,其中,所述将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功,包括:对所述用户实时输入的目标人脸识别信息进行拆分,得到其中的目标关键部分和目标非关键部分;对所述标准人脸识别信息进行拆分,得到其中的原始关键部分和标准非关键部分;分别从所述目标关键部分和原始关键部分中提取第一特征值和第二特征值,并将所述第一特征值和所述第二特征值进行匹配得到第一匹配度,当第一匹配度超过第一阈值时,则判定所述目标人脸识别信息的目标关键部分识别通过;所述目标人脸识别信息的关键部分识别通过后,分别从所述目标非关键部分和标准非关键部分中提取第三特征值和第四特征值,并将所述第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时,则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功。
- 根据权利要求9所述的计算机设备,其中,所述将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改,包括:将所述原始非关键部分拆分成数量不少于第三阈值的若干个子区域;从所述若干个子区域中随机抽取数量不少于第四阈值的若干个子区域;按照预设的修改方式对抽取到的若干子区域进行修改。
- 根据权利要求12所述的计算机设备,其中,所述按照预设的修改方式对抽取到的若干子区域进行修改,包括:从每一个抽取到的子区域中选择若干特征图,对所选择的特征图进行模糊、删除或者覆盖的操作,并保存修改后的子区域;或者,从每一个抽取到的子区域中选择若干特征图,并从预设的特征库中随机选择同样数量的特征图,对选择的若干特征图进行替换,并保存修改后的子区域。
- 根据权利要求9所述的计算机设备,其中,所述当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功之前,还包括:接收用户输入的人脸比对请求,从所述人脸比对数据库中提取与所述人脸比对请求中用户识别码具有映射关系的标准人脸识别信息。
- 一种计算机可读存储介质,其中,所述计算机可读存储介质存储有计算机程序,所述计算机程序当被处理器执行时使所述处理器执行如权利要求1所述的人脸识别信息的二次加密方法。
- 根据权利要求15所述的计算机可读存储介质,其中,所述将修改后的子区域与未修改的子区域重新组合为标准非关键部分,并将所述标准非关键部分与所述原始关键部分进行拼接,实现对所述原始人脸识别信息的二次加密,将二次加密后得到的标准人脸识别信息和所述用户身份信息进行关联保存得到人脸比对信息数据库,包括:对修改后的子区域进行标记,并按顺序将所述修改后的子区域与所述未修改的子区域进行拼接组合,形成还原后的所述标准非关键部分;获取所述原始人脸识别信息的初始结构,按照所述初始结构设置所述原始人脸识别信息的结构模板,将所述原始关键部分与还原后的所述标准非关键部分填充至所述结构模板中,形成二次加密后的标准人脸识别信息;将二次加密后的标准人脸识别信息和用户身份信息进行关联,并保存所述二次加密后的标准人脸识别信息和用户身份信息的对应关系。
- 根据权利要求15所述的计算机可读存储介质,其中,所述将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功,包括:对所述用户实时输入的目标人脸识别信息进行拆分,得到其中的目标关键部分和目标非关键部分;对所述标准人脸识别信息进行拆分,得到其中的原始关键部分和标准非关键部分;分别从所述目标关键部分和原始关键部分中提取第一特征值和第二特征值,并将所述第一特征值和所述第二特征值进行匹配得到第一匹配度,当第一匹配度超过第一阈值时,则判定所述目标人脸识别信息的目标关键部分识别通过;所述目标人脸识别信息的关键部分识别通过后,分别从所述目标非关键部分和标准非关键部分中提取第三特征值和第四特征值,并将所述第三特征值和第四特征值进行匹配得到第二匹配度,当第二匹配度超过第二阈值时,则判定所述目标人脸识别信息的目标非关键部分识别通过,并确认身份识别成功。
- 根据权利要求15所述的计算机可读存储介质,其中,所述将所述原始非关键部分拆分为若干个子区域,对所述若干子区域中的至少一个子区域进行修改,包括:将所述原始非关键部分拆分成数量不少于第三阈值的若干个子区域;从所述若干个子区域中随机抽取数量不少于第四阈值的若干个子区域;按照预设的修改方式对抽取到的若干子区域进行修改。
- 根据权利要求18所述的计算机可读存储介质,其中,所述按照预设的修改方式对抽取到的若干子区域进行修改,包括:从每一个抽取到的子区域中选择若干特征图,对所选择的特征图进行模糊、删除或者覆盖的操作,并保存修改后的子区域;或者,从每一个抽取到的子区域中选择若干特征图,并从预设的特征库中随机选择同样数量的特征图,对选择的若干特征图进行替换,并保存修改后的子区域。
- 根据权利要求15所述的计算机可读存储介质,其中,所述当需要进行身份识别时,接收所述用户实时输入的目标人脸识别信息,将所述用户实时输入的目标人脸识别信息与所述人脸比对信息数据库中的标准人脸识别信息进行比对,当比对一致时,则确认身份识别成功之前,还包括:接收用户输入的人脸比对请求,从所述人脸比对数据库中提取与所述人脸比对请求中用户识别码具有映射关系的标准人脸识别信息。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011231052.1A CN112183496B (zh) | 2020-11-06 | 2020-11-06 | 人脸识别信息的二次加密方法、装置、设备及存储介质 |
| CN202011231052.1 | 2020-11-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022095355A1 true WO2022095355A1 (zh) | 2022-05-12 |
Family
ID=73916586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/090564 Ceased WO2022095355A1 (zh) | 2020-11-06 | 2021-04-28 | 人脸识别信息的二次加密方法、装置、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112183496B (zh) |
| WO (1) | WO2022095355A1 (zh) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114943639A (zh) * | 2022-05-24 | 2022-08-26 | 北京瑞莱智慧科技有限公司 | 图像获取方法、相关装置及存储介质 |
| CN115049857A (zh) * | 2022-06-02 | 2022-09-13 | 云从科技集团股份有限公司 | 目标识别方法、计算机可读存储介质及电子设备 |
| CN116582281A (zh) * | 2023-07-10 | 2023-08-11 | 中国人民解放军国防科技大学 | 一种基于密码技术的安全人脸识别方法、系统及设备 |
| CN118250402A (zh) * | 2024-05-21 | 2024-06-25 | 互丰科技(北京)有限公司 | 一种基于大数据的人工智能控制方法及装置 |
| WO2024211294A1 (en) * | 2023-04-03 | 2024-10-10 | Verai Systems, LLC | Secure biometric data storage and retrieval system |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183496B (zh) * | 2020-11-06 | 2023-06-20 | 平安科技(深圳)有限公司 | 人脸识别信息的二次加密方法、装置、设备及存储介质 |
| CN113868688B (zh) * | 2021-10-25 | 2025-02-28 | 深圳市新国都支付技术有限公司 | 人脸分层加密方法、装置、设备及存储介质 |
| CN114760068A (zh) * | 2022-04-08 | 2022-07-15 | 中国银行股份有限公司 | 用户的身份验证方法、系统、电子设备及存储介质 |
| CN118015435B (zh) * | 2024-04-10 | 2024-06-04 | 微网优联科技(成都)有限公司 | 基于移动计算平台的实时人脸抓拍方法及系统 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140072185A1 (en) * | 2012-09-07 | 2014-03-13 | David D. Dunlap | Biometric Identification Systems and Methods |
| CN106897590A (zh) * | 2015-12-17 | 2017-06-27 | 阿里巴巴集团控股有限公司 | 人像信息的校验方法及装置 |
| CN109492407A (zh) * | 2017-09-11 | 2019-03-19 | 中兴通讯股份有限公司 | 数据保护、数据解保方法、终端及计算机可读存储介质 |
| CN110119608A (zh) * | 2014-03-27 | 2019-08-13 | 阿里巴巴集团控股有限公司 | 一种生物特征信息处理方法、生物特征信息保存方法及装置 |
| CN112183496A (zh) * | 2020-11-06 | 2021-01-05 | 平安科技(深圳)有限公司 | 人脸识别信息的二次加密方法、装置、设备及存储介质 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204759626U (zh) * | 2015-05-07 | 2015-11-11 | 广州龙天软件科技有限公司 | 一种电子支付终端机 |
| CN107993073B (zh) * | 2017-12-29 | 2020-10-02 | 舟山振凯信息科技有限公司 | 一种人脸识别系统及其工作方法 |
| CN109840424A (zh) * | 2018-12-18 | 2019-06-04 | 合肥天源迪科信息技术有限公司 | 一种数据库加密与脱敏系统 |
| CN110008903B (zh) * | 2019-04-04 | 2022-01-28 | 北京旷视科技有限公司 | 人脸识别方法、装置、系统、存储介质和人脸支付方法 |
| CN110109608B (zh) * | 2019-05-17 | 2020-12-29 | 北京达佳互联信息技术有限公司 | 文本显示方法、装置、终端及存储介质 |
-
2020
- 2020-11-06 CN CN202011231052.1A patent/CN112183496B/zh active Active
-
2021
- 2021-04-28 WO PCT/CN2021/090564 patent/WO2022095355A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140072185A1 (en) * | 2012-09-07 | 2014-03-13 | David D. Dunlap | Biometric Identification Systems and Methods |
| CN110119608A (zh) * | 2014-03-27 | 2019-08-13 | 阿里巴巴集团控股有限公司 | 一种生物特征信息处理方法、生物特征信息保存方法及装置 |
| CN106897590A (zh) * | 2015-12-17 | 2017-06-27 | 阿里巴巴集团控股有限公司 | 人像信息的校验方法及装置 |
| CN109492407A (zh) * | 2017-09-11 | 2019-03-19 | 中兴通讯股份有限公司 | 数据保护、数据解保方法、终端及计算机可读存储介质 |
| CN112183496A (zh) * | 2020-11-06 | 2021-01-05 | 平安科技(深圳)有限公司 | 人脸识别信息的二次加密方法、装置、设备及存储介质 |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114943639A (zh) * | 2022-05-24 | 2022-08-26 | 北京瑞莱智慧科技有限公司 | 图像获取方法、相关装置及存储介质 |
| CN115049857A (zh) * | 2022-06-02 | 2022-09-13 | 云从科技集团股份有限公司 | 目标识别方法、计算机可读存储介质及电子设备 |
| WO2024211294A1 (en) * | 2023-04-03 | 2024-10-10 | Verai Systems, LLC | Secure biometric data storage and retrieval system |
| CN116582281A (zh) * | 2023-07-10 | 2023-08-11 | 中国人民解放军国防科技大学 | 一种基于密码技术的安全人脸识别方法、系统及设备 |
| CN116582281B (zh) * | 2023-07-10 | 2023-09-22 | 中国人民解放军国防科技大学 | 一种基于密码技术的安全人脸识别方法、系统及设备 |
| CN118250402A (zh) * | 2024-05-21 | 2024-06-25 | 互丰科技(北京)有限公司 | 一种基于大数据的人工智能控制方法及装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112183496B (zh) | 2023-06-20 |
| CN112183496A (zh) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022095355A1 (zh) | 人脸识别信息的二次加密方法、装置、设备及存储介质 | |
| US11444774B2 (en) | Method and system for biometric verification | |
| US11790077B2 (en) | Methods, mediums, and systems for establishing and using security questions | |
| US6446210B1 (en) | Method for securing communication by selecting an encoding process using a first computer based upon ability of a second computer and deleting the process thereafter | |
| US10425232B2 (en) | Encrypted biometric registration | |
| US10425408B2 (en) | Encrypted biometric authenication | |
| WO2020181809A1 (zh) | 基于接口校验的数据处理的方法、系统和计算机设备 | |
| US10885525B1 (en) | Method and system for employing biometric data to authorize cloud-based transactions | |
| US10282532B2 (en) | Secure storage of fingerprint related elements | |
| CN107704759A (zh) | 敏感操作的控制方法、装置、存储介质及电子设备 | |
| CN114596639B (zh) | 一种生物特征识别方法、装置、电子设备及存储介质 | |
| CN114238874B (zh) | 数字签章验证方法、装置、计算机设备和存储介质 | |
| US12261954B2 (en) | System and method to validate a rendered object using non-fungible tokens | |
| CN114117385A (zh) | 一种密码生成方法、装置及计算机可读存储介质 | |
| US12184778B2 (en) | System and method for changing encryption keys | |
| US12019719B2 (en) | Method and electronic device for authenticating a user | |
| US10902242B2 (en) | Binding data to a person's identity | |
| CN110738499B (zh) | 用户身份验证方法、装置、计算机设备和存储介质 | |
| US12254122B2 (en) | System and method for password-less authentication through digital driving license | |
| CN114900289B (zh) | 一种数据安全处理方法、系统、设备及介质 | |
| CN113568846A (zh) | 一种加密硬盘销毁方法及装置 | |
| KR20180051742A (ko) | 얼굴 인식 시스템 및 그 방법 | |
| WO2022134007A1 (zh) | 设备鉴权方法、终端设备、服务器和计算机设备 | |
| KR102741177B1 (ko) | 안면 인식을 통해 컴퓨터 단말의 파일 및 디렉토리 접근을 정밀 통제하는 보안장치 및 보안방법 | |
| US20260112198A1 (en) | Generating Certifications For Facial Images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21888059 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21888059 Country of ref document: EP Kind code of ref document: A1 |