WO2023045507A1 - Reconnaissance faciale - Google Patents

Reconnaissance faciale Download PDF

Info

Publication number
WO2023045507A1
WO2023045507A1 PCT/CN2022/105266 CN2022105266W WO2023045507A1 WO 2023045507 A1 WO2023045507 A1 WO 2023045507A1 CN 2022105266 W CN2022105266 W CN 2022105266W WO 2023045507 A1 WO2023045507 A1 WO 2023045507A1
Authority
WO
WIPO (PCT)
Prior art keywords
facial image
image
similar
verified
facial
Prior art date
Application number
PCT/CN2022/105266
Other languages
English (en)
Chinese (zh)
Inventor
王元吉
张弼坤
周全
赖利锋
吴磊
Original Assignee
上海商汤智能科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海商汤智能科技有限公司 filed Critical 上海商汤智能科技有限公司
Publication of WO2023045507A1 publication Critical patent/WO2023045507A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Definitions

  • the present disclosure relates to machine learning technology, and in particular to a face recognition method and device, media, electronic equipment, and computer programs.
  • face recognition is required to confirm the identity of the person.
  • face recognition can be carried out through computer vision technology, but for people with similar faces such as twins, misrecognition is prone to occur.
  • a face recognition method comprising: obtaining a face image to be verified; in a face image library, obtaining a target face image similar to the face image to be verified In response to the presence of at least two target facial images in the facial image database, obtain the verification information input by the subject to be verified corresponding to the facial image to be verified; pass the verification of the verification information input by the subject to be verified In the case of , it is determined that the identification of the object to be verified is successful.
  • a face recognition device includes: an image acquisition module, used to acquire a face image to be verified; The target facial image similar to the facial image to be verified; the information receiving module is used to obtain the object to be verified corresponding to the facial image to be verified in response to the presence of at least two target facial images in the facial image database The input verification information; an information verification module, configured to determine that the identification of the object to be verified is successful in response to the verification information input by the object to be verified passing the verification.
  • a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.
  • an electronic device the electronic device includes a memory and a processor, the memory stores a computer program, the processor is configured to execute the computer program stored in the memory, and the When the computer program is executed, the method described in any embodiment of the present disclosure is realized.
  • a computer program product including a computer program stored in a memory, and when the computer program instructions are executed by a processor, the method described in any embodiment of the present disclosure is implemented.
  • Fig. 1 shows a flowchart of a face recognition method provided by at least one embodiment of the present disclosure
  • Fig. 2 shows a flow chart of face registration in a face recognition method provided by at least one embodiment of the present disclosure
  • Fig. 3 shows a flow chart of a face recognition method provided by at least one embodiment of the present disclosure
  • Fig. 4 shows the application system architecture of the face recognition method of at least one embodiment of the present disclosure
  • FIG. 5 shows a flowchart of a face recognition method in at least one embodiment of the present disclosure
  • Fig. 6 shows a schematic structural diagram of a face recognition device provided by at least one embodiment of the present disclosure
  • Fig. 7 shows a schematic structural diagram of a face recognition device provided by at least one embodiment of the present disclosure.
  • the product applying the disclosed technical solution has clearly informed the user of the information processing rules and obtained the user's independent consent before processing the user information.
  • the product applying the disclosed technical solution has obtained the separate consent of the user before processing the sensitive user information, and at the same time meets the requirement of "express consent". For example, at the user information collection device such as a camera, set a clear and prominent sign to inform that the user information has entered the collection range, and the user information will be collected.
  • the user information processing rules may include user Information processor, user information processing purpose, processing method, type of user information processed and other information.
  • An embodiment of the present disclosure provides a face recognition method, which can perform double authentication on similar face images.
  • the similar facial images may be images whose image similarity between facial images reaches a certain threshold, for example, if the image similarity between two facial images reaches more than 0.95, then the two facial images may be called
  • the face images are similar face images.
  • FIG. 1 shows a flowchart of a face recognition method provided by at least one embodiment of the present disclosure. As shown in FIG. 1 , the method may include steps 100 to 106 .
  • step 100 a facial image to be verified is acquired.
  • the face image to be verified may be a face image of an object to be verified whose face is to be recognized.
  • the object to be verified in the scenario of attendance check-in, can be an employee who is clocking in for work; in the scenario of membership billing, the object to be verified can be a member to be paid.
  • the face image of the object to be verified may be collected by an image collection device.
  • the execution device of the face recognition method in this embodiment can be the image acquisition device itself, or other devices, for example, it can also be a cloud server to execute the method, then the image acquisition device can transmit the collected facial images to the cloud server.
  • step 102 a target face image similar to the face image to be verified is obtained from the face image database.
  • the facial image library may include a relatively large number of registered facial images.
  • a face image library can be established for a certain company, and the face images of all employees of the company can be collected in advance and stored in the face image library.
  • the face image of the object to be verified can be compared with each face image in the face image library. If the face image of the object to be verified (that is, the face image to be verified ) in the face image library, it indicates that the object to be verified is an employee of the company, and at the same time, according to the face image information stored in the face image library, the identity of the clock-in employee is obtained, and it is known which employee is currently in Check in.
  • the facial image to be verified obtained in step 100 can be compared with each facial image in the facial image database for similarity comparison, for example, a similarity threshold can be set, if the difference between the two facial images If the image similarity between them is equal to or greater than the similarity threshold, the two face images can be considered to be similar.
  • the facial image similar to the facial image to be verified in the facial image database may be called a target facial image.
  • step 104 in response to the existence of at least two target facial images in the facial image library, the verification information input by the subject to be verified corresponding to the facial image to be verified is acquired.
  • this step can continue to obtain the corresponding face images to be verified.
  • the verification information may include but not limited to: a digital password, a password of numbers+characters, a graphic password, and the like.
  • the object to be verified may input the password "56428".
  • step 106 in response to the verification information input by the object to be verified passing the verification, it is determined that the identification of the object to be verified is successful.
  • this step when verifying the verification information input by the object to be verified, it may be to compare the input verification information with the verification information corresponding to the above-mentioned at least two similar target facial images, as long as the input verification information If one of the verification information in at least two similar target face images is matched, it can be considered that the verification information has passed the verification.
  • the successful identification means that there is a facial image of the object to be verified in the facial image library (in other words, the facial image of the object to be verified corresponding to the facial image to be verified exists in the facial image library), otherwise, If there is no face image of the object to be verified in the face image library, the recognition fails.
  • the face recognition method can be applied to various scenarios. For example, it can be used in the scene of toll billing. Then, when the face recognition is successful, the pass device can be controlled to open the gate to allow the object to be verified to pass. For another example, it can also be used in the scene of attendance check-in, so when the face recognition is successful, the check-in time of the object to be verified can be recorded, and the check-in is successful.
  • the scene of identity verification can also be used in the scene of identity verification.
  • a user wants to use an information query system, he needs to pass face recognition first.
  • the user's face recognition is successful, the user can be allowed to continue to operate.
  • the information query system performs information query.
  • the identity information of the object to be verified can also be continuously obtained.
  • the face image of the object to be verified can be obtained according to the facial image of the object to be verified in the face image library, which is input and stored when the object is registered.
  • the object's name, ID number and other identity information can also be used in the scene of identity verification.
  • the object to be verified is successfully recognized, that is, in The face image of the object to be verified is found in the library, and the identity of the object to be verified is the object identity corresponding to the similar target face image.
  • double verification of the object to be verified is required.
  • the first verification is face verification
  • the result of face verification is that there are at least two similar images.
  • the target facial image proceed to the second verification, which is the verification of the verification information.
  • corresponding passwords may be generated and stored in advance, for example, the facial image P1 corresponds to the password "56428", and the facial image P2 corresponds to the password "12356”.
  • the verification information "56428" input by the object to be verified obtained in step 104 is consistent with the corresponding password of the face image P1 in the face image library, then confirm that the verification information of the object to be verified has passed the verification, and can
  • the obtained identity information of the object to be verified is the object identity information corresponding to the facial image P1.
  • the face recognition method of this embodiment when it is determined that there are at least two similar target face images in the face image library, the verification information of the object to be verified is acquired and verified.
  • This method takes into account both recognition efficiency and recognition accuracy. Not all objects to be verified need to be double-checked. As long as there are no at least two similar target face images in the face image database, they can be identified only by face recognition, thus ensuring the recognition efficiency; And when there are at least two similar objects in the facial image database, the double authentication method of this embodiment can also ensure the recognition accuracy of the similar objects, thereby ensuring recognition efficiency and recognition accuracy at the same time.
  • the registration process involving similar face images and the application process of face recognition are described as follows through another embodiment.
  • the registration of a pair of twins is taken as an example, assuming that the twins include users User-1 and User-2 .
  • the method in the embodiment of the present disclosure is not limited to face recognition of twins, as long as they are similar face images.
  • the face image of user User-1 is stored in the face image library, and the user information corresponding to the face image can also be stored in the face image library,
  • the user information may include but not limited to user information such as user name, age, ID number, and job number. Since the user User-1 is registered first, there is no similar face image in the face image library.
  • FIG. 2 shows a flow chart of face registration in a face recognition method provided by at least one embodiment of the present disclosure, and the method may include steps 200 to 206 .
  • step 200 a new facial image to be registered into the facial image library is acquired.
  • the new face image is the face image of the user User-2 in the above twins.
  • step 202 in response to the presence of at least one similar facial image similar to the new facial image in the facial image library, obtain the verification corresponding to the new facial image and the at least one similar facial image information.
  • the image similarity between User-2's face image and any face image in the face image library can be calculated, and if the image similarity reaches the similarity threshold, the face image library can be regarded as This face image in is similar to User-2's face image as a similar face image similar to User-2's face image.
  • the facial image may be used as a candidate facial image. And display a prompt, for example, it may prompt the manager to confirm whether the facial image to be selected is similar to the facial image of User-2. In case of receiving confirmation information that the facial image to be selected is confirmed to be similar to the facial image of User-2, it is confirmed that the facial image to be selected is a similar facial image similar to the facial image of User-2.
  • the facial image of User-1 since the face image of user User-1 already exists in the face image library, when performing image registration, in the image matching stage, it can be found that the face image of user User-1 is the same as that of user User-2 The facial images of User-1 and User-2 are similar. At this time, a pop-up window can prompt the administrator to confirm, that is, you can manually reconfirm whether the facial images of User-1 and User-2 are really similar. In the case where confirmation information confirming the similarity is received, the facial image of User-1 may be referred to as a similar facial image to the facial image of User-2. It can be understood that this embodiment takes twins as an example, assuming that only User-1's facial image is similar to User-2's facial image in the facial image database, in other examples, the new facial image to be registered The number of similar images can be more than one.
  • the stored verification information of the face image of User-1 and the verification information of the face image of User-2 being registered can be acquired.
  • the terminal device may pop up an input interface for verification information, for managers or User-1 and User-2 to input corresponding verification information. For example, user User-1 enters "56428" as his verification information, and user User-2 enters "12356" as his verification information. As a terminal device, the terminal device has received verification information corresponding to User-1 and User-2 respectively.
  • the terminal device may also generate verification information corresponding to User-1 and User-2 respectively.
  • the terminal device may randomly generate two character strings as verification information corresponding to User-1 and User-2.
  • step 204 the corresponding relationship between the new facial image and the at least one similar facial image and their respective verification information is stored.
  • each The corresponding relationship may include a face image and corresponding verification information.
  • the facial image described in the corresponding relationship may be the image itself, or may also be an identification of the facial image.
  • the image ID ID1 can be generated according to the face image of the user User-1, and the image ID is used to represent the User-1, and the image ID ID2 can be generated based on the face image of the user User-2.
  • Two correspondences can be stored, one of which is "ID1-56428" and the other is "ID2-12356".
  • a similar flag can be set for the facial image of User-1 and the facial image of User-2, and the similar flag can be called similar Flag.
  • This embodiment does not limit the specific form of the similar identifier, for example, it may be represented by a symbol *.
  • the use of the similar identifiers can be combined with reference to the subsequent description of the embodiments.
  • step 206 the verification information corresponding to the new facial image and the at least one similar facial image are sent to the respective devices corresponding to the new facial image and the at least one similar facial image.
  • the verification information corresponding to the new facial image and the similar facial image may also be sent to the corresponding device.
  • the facial image corresponding to certain verification information may be referred to as the first image, and the verification information is sent to the device corresponding to the first image.
  • the verification information of User-1 is 56428
  • the face image of User-1 corresponding to the verification information "56428” is called the first image
  • the device corresponding to the first image may be the mobile phone of user User-1, then "56428" can be sent to User-1's cell phone.
  • the verification information can be sent to the aforementioned email address or mobile phone.
  • the password 12356 is sent to the mobile phone of user User-2, so that he can know his own verification information, so that the verification information can be used in subsequent face recognition applications.
  • the face registration is completed as above, and then the face recognition process of one of the twin users User-1 and User-2 when clocking in is described.
  • FIG. 3 shows a flowchart of a face recognition method provided by at least one embodiment of the present disclosure.
  • the method describes the face recognition process of any user in the twins, and may include steps 300 to 308 .
  • step 300 an image of a face to be verified is acquired.
  • the facial image of the user User-2 captured by the camera may be obtained.
  • step 302 a target face image similar to the face image to be verified is obtained from the face image library.
  • the face image in the face image database whose image similarity with the face image to be verified reaches the similarity threshold can be used as the face of User-2 Image-like target face images.
  • the user-2 face in the face image library can be first A face image with a similar image is used as a candidate face image, and an image with a similar identification in the candidate face image is used as a target face image similar to the user-2's face image.
  • the two face images when searching for a target face image similar to that of User-2 in the face image library, two face images will be obtained, one is User-2 in the face image library. 1's face image, and the other is the image of User-2 in the face image library that was stored in the library at the time of registration. Moreover, the two images both have similar logos, which may be set during the registration process. Then the images of User-1 and User-2 with similar identifications searched from the face image database can be determined as the target face images.
  • setting a similar flag for similar face images can help to further improve the efficiency of face recognition. Specifically, if there are four face images to be selected that reach the similarity threshold in the face image library, and only two of them have a similar logo, and the other two do not have a similar logo, then only the The two images with similar marks are determined as the target face images, so that the amount of data involved in the matching and comparison in the subsequent steps is reduced, saving processing resources, and improving recognition efficiency.
  • step 304 in response to the fact that there are at least two target facial images in the facial image library, the verification information input by the subject to be verified corresponding to the image to be verified is acquired.
  • a password input box may pop up for user User-2 to input his own password information. Assume that User-2 has entered "12356" in this embodiment.
  • step 306 at least two correspondences respectively corresponding to the at least two target facial images stored in advance are obtained, and in response to the acquired verification information input by the subject to be verified and the at least two correspondences If any of the included verification information matches, it is determined that the verification information input by the object to be verified passes the verification.
  • the verification information corresponding to the two target facial images searched above can be obtained, that is, the corresponding relationship between the two target facial images can be obtained.
  • One corresponding relationship is "ID1-56428” and the other corresponding relationship is "ID1-56428”. ID2-12356”.
  • step 308 the user information of the object to be verified is obtained.
  • the specific identity of the user User-2 can also be obtained. For example, according to the corresponding relationship "ID2-12356" in the above matching, it can be obtained
  • the facial image ID2 corresponding to the user User-2 can be obtained from the face image database, for example, the user information such as the name and job number entered when User-2 registered.
  • the verification information of the object to be verified is obtained and verified.
  • This method takes into account both recognition efficiency and recognition accuracy. and, by setting similar labels on similar face images, the efficiency of face recognition can be further improved.
  • the face recognition method of the embodiment of the present disclosure is described by taking the attendance check-in scene as an example, and still taking the check-in of twin users User-1 and User-2 in the previous embodiment as an example.
  • This embodiment mainly provides the application system architecture of the process shown in FIG. 3 , and describes the execution of the method on the basis of the system architecture.
  • FIG. 4 shows the application system architecture of the facial recognition method of at least one embodiment of the present disclosure.
  • the system may include: a cloud server 41 and a terminal device 42 .
  • the terminal device 42 can be an attendance check-in terminal, and employees who go to work in the company can use the terminal device 42 to punch in by swiping their faces.
  • the registration process can refer to the processing illustrated in FIG. 2 .
  • the cloud server 41 can synchronize the corresponding relationship "ID1-56428" and "ID2-12356" between User-1 and User-2 to the terminal device 42 for subsequent use by the terminal device 42.
  • FIG. 5 shows the process of the face recognition method in at least one embodiment of the present disclosure.
  • the cloud server 41 may be responsible for storing the facial image database and performing the first stage of face verification
  • the terminal device 42 may be responsible for performing the second stage of password verification.
  • the execution device of face recognition it can also be that the double verification is performed on the cloud server side, and the terminal device 42 receives the verification information. It can be sent to the cloud server 41 for verification, and the cloud server 41 can transmit the final verification result to the terminal device 42 .
  • the facial image library can be set on the terminal device 42, and no interaction with the cloud is required.
  • the method is described by taking the cloud server and the terminal device as an example to cooperate with each other. As shown in FIG. 5 , the method may include steps 500 to 512 .
  • step 500 the terminal device collects facial images to be verified.
  • the terminal device may collect a face image of the user User-2 through a camera.
  • step 502 the terminal device sends the face image to be verified to the cloud server.
  • step 504 the cloud server searches the face image database for at least two target face images similar to the face image to be verified.
  • the cloud server can search for two similar images in the face image library based on the face images to be verified, namely the face images of User-1 and User-2.
  • step 506 the cloud server instructs the terminal device to perform two-factor authentication.
  • the cloud server may instruct the terminal device to perform the second verification on the object to be verified, wherein the instruction may carry the IDs of the two target face images searched in step 504, for example, ID1 and ID2.
  • the instruction may carry the IDs of the two target face images searched in step 504, for example, ID1 and ID2.
  • ID1 and ID2 The correspondence between the two similar facial images has been pre-synchronized to the terminal device side.
  • step 508 the terminal device acquires the verification information input by the object to be verified.
  • the terminal device can pop up a password input box on the display screen of the device, and the user User-2 can enter a password in this interface (this embodiment takes the verification information as a password form as an example).
  • the password input interface can use a security keyboard, and the password input timing method can be set, and the countdown can be re-scanned if the password is not successfully verified.
  • step 510 the terminal device obtains at least two pre-stored correspondences corresponding to the at least two target face images, and in response to the obtained verification information of the object to be verified exists in the correspondences, determine The verification information input by the object to be verified passes the verification.
  • the terminal device determines that the received verification information "12356" is stored in at least two pre-stored correspondences corresponding to the at least two target face images, and determines that the verification information of the object to be verified has passed the verification, That is, the object is an employee of the company.
  • step 512 the terminal device reports the information of the object to be verified that passes the verification to the cloud server.
  • the object to be verified is ID2
  • the user information of the object to be verified can be obtained according to the identification ID2.
  • the display screen prompts "Zhang Hong, welcome".
  • the information (user information) of these verification objects may be input and stored in the face image library at the initial registration stage.
  • the cloud server synchronizes the corresponding relationship of similar facial images to the terminal device, it can also synchronize the user information to the terminal device, so the terminal device can obtain the user information of the current verification object according to the corresponding relationship.
  • the terminal device can report User-2's user information to the cloud server, for example, report User-2's name, check-in time and other information to the server.
  • the verification information of two different users is found to be the same when comparing the verification information, no matter whether the verification information entered by the user is correct or not, an error will be prompted, and the process will end, prompting the user to change the password.
  • Fig. 6 shows a schematic structural diagram of a face recognition device provided by at least one embodiment of the present disclosure.
  • the device may include: an image acquisition module 61, a similarity search module 62, an information receiving module 63 and information verification Module 64.
  • An image acquisition module 61 configured to acquire a facial image to be verified.
  • the similarity search module 62 is configured to obtain a target facial image similar to the facial image to be verified in the facial image library.
  • the information receiving module 63 is configured to, in response to the existence of at least two target facial images in the facial image database, acquire the verification information input by the subject to be verified corresponding to the facial image to be verified.
  • the information verification module 64 is configured to determine that the identification of the object to be verified is successful in response to the verification information input by the object to be verified passing the verification.
  • the similarity search module 62 when used to obtain a target facial image similar to the facial image to be verified, it includes: An image similarity between facial images; using the facial image in the facial image database whose image similarity with the facial image to be verified reaches a similarity threshold as the target facial image.
  • the similarity search module 62 is configured to, when obtaining a target facial image similar to the facial image to be verified, determine that the facial image to be verified is different from any face in the facial image library.
  • the information verification module 64 is configured to obtain at least two pre-stored correspondences respectively corresponding to the at least two target facial images when the verification information input by the object to be verified passes the verification, Each of the correspondences includes a face image and the verification information corresponding to the face image; in response to the acquired verification information input by the object to be verified and any verification information included in the at least two correspondences The information matches, and it is determined that the verification information input by the object to be verified passes the verification.
  • the information verification module 64 is further configured to acquire user information corresponding to the verification information of the object to be verified based on the corresponding relationship in response to the verification information input by the object to be verified passing the verification.
  • the device may also include: an information registration module 65, configured to obtain a new facial image to be registered in the facial image database; There is already at least one similar facial image similar to the new facial image; obtaining verification information corresponding to the new facial image and the at least one similar facial image; storing the new facial image and the Correspondence between at least one similar face image and respective verification information.
  • an information registration module 65 configured to obtain a new facial image to be registered in the facial image database; There is already at least one similar facial image similar to the new facial image; obtaining verification information corresponding to the new facial image and the at least one similar facial image; storing the new facial image and the Correspondence between at least one similar face image and respective verification information.
  • the information registration module 65 is further configured to: set a similarity identifier for the new facial image and the at least one similar facial image.
  • the similarity search module 62 is used to acquire, in the facial image database, a facial image similar to the facial image to be verified and bearing the similarity mark when acquiring a target facial image similar to the facial image.
  • the face image is used as the target face image.
  • the information registration module 65 is configured to, when acquiring the verification information corresponding to the new facial image and the at least one similar facial image, generate the new facial image similar to the at least one similar facial image. Verification information corresponding to the facial image; or, receiving verification information corresponding to the new facial image and the at least one similar facial image.
  • the information registration module 65 is configured to determine that the new face image is similar to the face in response to at least one similar image similar to the new face image existing in the face image library.
  • the information registration module 65 is further configured to: send the verification information corresponding to the new facial image and the at least one similar facial image to the new facial image similar to the at least one similar facial image.
  • the information verification module 64 is further configured to: determine that the recognition of the object to be verified is successful in response to the existence of one target face image in the face image database.
  • the above-mentioned apparatus may be used to execute any corresponding method described above, and for the sake of brevity, details are not repeated here.
  • An embodiment of the present disclosure also provides an electronic device, the device includes a memory and a processor, the memory is used to store computer-readable instructions, and the processor is used to invoke the computer instructions to implement any embodiment of the present specification face recognition method.
  • An embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the face recognition method of any embodiment of the present specification is implemented.
  • An embodiment of the present disclosure also provides a computer program product, including a computer program stored in a memory, and when the computer program instructions are executed by a processor, the face recognition method of any embodiment of the present specification is implemented.
  • one or more embodiments of the present disclosure may be provided as a method, system or computer program product. Accordingly, one or more embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present disclosure may employ a computer program embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein. The form of the product.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • Embodiments of the subject matter and functional operations described in this disclosure can be implemented in digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this disclosure and their structural equivalents, or in A combination of one or more of .
  • Embodiments of the subject matter described in this disclosure can be implemented as one or more computer programs, i.e. one or more of computer program instructions encoded on a tangible, non-transitory program carrier for execution by or to control the operation of data processing apparatus. Multiple modules.
  • the program instructions may be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for transmission by the data
  • the processing means executes.
  • a computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
  • the processes and logic flows described in this disclosure can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output.
  • the processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • Computers suitable for the execution of a computer program include, for example, general and/or special purpose microprocessors, or any other type of central processing unit.
  • a central processing unit will receive instructions and data from a read only memory and/or a random access memory.
  • the essential components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data.
  • a computer will also include, or be operatively coupled to, one or more mass storage devices for storing data, such as magnetic or magneto-optical disks, or optical disks, to receive data therefrom or to It transmits data, or both.
  • mass storage devices for storing data, such as magnetic or magneto-optical disks, or optical disks, to receive data therefrom or to It transmits data, or both.
  • a computer is not required to have such a device.
  • a computer may be embedded in another device such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a device such as a Universal Serial Bus (USB) ) portable storage devices like flash drives, to name a few.
  • PDA personal digital assistant
  • GPS Global Positioning System
  • USB Universal Serial Bus
  • Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks.
  • semiconductor memory devices such as EPROM, EEPROM, and flash memory devices
  • magnetic disks such as internal hard disks or removable disks
  • magneto-optical disks and CD ROM and DVD-ROM disks.
  • the processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un procédé et un appareil de reconnaissance faciale, un support, un dispositif électronique et un produit programme informatique. Le procédé comprend les étapes consistant à : obtenir une image faciale à vérifier ; obtenir une image faciale cible similaire à l'image faciale à vérifier d'une bibliothèque d'images faciales ; en réponse à la présence d'au moins deux images faciales cibles dans la bibliothèque d'images faciales, obtenir des informations de vérification entrées par un objet à vérifier correspondant à l'image faciale à vérifier ; et en réponse à la réussite de la vérification des informations de vérification entrées par l'objet à vérifier, déterminer que l'objet à vérifier est reconnu avec succès.
PCT/CN2022/105266 2021-09-26 2022-07-12 Reconnaissance faciale WO2023045507A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111131752.8A CN113807303A (zh) 2021-09-26 2021-09-26 人脸识别方法和装置、介质和电子设备
CN202111131752.8 2021-09-26

Publications (1)

Publication Number Publication Date
WO2023045507A1 true WO2023045507A1 (fr) 2023-03-30

Family

ID=78938636

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/105266 WO2023045507A1 (fr) 2021-09-26 2022-07-12 Reconnaissance faciale

Country Status (2)

Country Link
CN (1) CN113807303A (fr)
WO (1) WO2023045507A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113807303A (zh) * 2021-09-26 2021-12-17 北京市商汤科技开发有限公司 人脸识别方法和装置、介质和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140294254A1 (en) * 2013-04-01 2014-10-02 Samsung Electronics Co., Ltd. Display apparatus for performing user certification and method thereof
CN110059560A (zh) * 2019-03-18 2019-07-26 阿里巴巴集团控股有限公司 人脸识别的方法、装置及设备
WO2020006727A1 (fr) * 2018-07-05 2020-01-09 深圳前海达闼云端智能科技有限公司 Procédé et dispositif de reconnaissance faciale, et serveur
CN111340471A (zh) * 2020-05-22 2020-06-26 支付宝(杭州)信息技术有限公司 一种基于人脸识别的支付方法、装置及设备
CN113807303A (zh) * 2021-09-26 2021-12-17 北京市商汤科技开发有限公司 人脸识别方法和装置、介质和电子设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109359548B (zh) * 2018-09-19 2022-07-08 深圳市商汤科技有限公司 多人脸识别监控方法及装置、电子设备及存储介质
CN109660509A (zh) * 2018-10-29 2019-04-19 北京旷视科技有限公司 基于人脸识别的登录方法、装置、系统和存储介质
CN110675539B (zh) * 2019-09-26 2022-08-12 深圳市商汤科技有限公司 身份核验方法及装置、电子设备和存储介质
CN113076859A (zh) * 2021-03-31 2021-07-06 深圳供电局有限公司 人脸识别的安全监控方法及系统、电子设备、存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140294254A1 (en) * 2013-04-01 2014-10-02 Samsung Electronics Co., Ltd. Display apparatus for performing user certification and method thereof
WO2020006727A1 (fr) * 2018-07-05 2020-01-09 深圳前海达闼云端智能科技有限公司 Procédé et dispositif de reconnaissance faciale, et serveur
CN110059560A (zh) * 2019-03-18 2019-07-26 阿里巴巴集团控股有限公司 人脸识别的方法、装置及设备
CN111340471A (zh) * 2020-05-22 2020-06-26 支付宝(杭州)信息技术有限公司 一种基于人脸识别的支付方法、装置及设备
CN113807303A (zh) * 2021-09-26 2021-12-17 北京市商汤科技开发有限公司 人脸识别方法和装置、介质和电子设备

Also Published As

Publication number Publication date
CN113807303A (zh) 2021-12-17

Similar Documents

Publication Publication Date Title
US9742764B1 (en) Performing biometrics in uncontrolled environments
AU2017316312B2 (en) Remote usage of locally stored biometric authentication data
US11900746B2 (en) System and method for providing credential activation layered security
US10014967B2 (en) System and method for authenticating a broadcast device using facial recognition
US20230244730A1 (en) Matchmaking Video Chatting Partners
US20220012512A1 (en) Intelligent gallery management for biometrics
US20210006558A1 (en) Method, apparatus and system for performing authentication using face recognition
US10397208B2 (en) Authentication via item recognition
JP2007156790A (ja) 複数種の生体情報による認証をおこなう認証技術
WO2018072588A1 (fr) Procédé de vérification de signature d'approbation, dispositif mobile, dispositif terminal et système
US11783336B2 (en) Camera device enabled identification and disambiguation system and method
JP6031172B1 (ja) 生体照合システム、生体照合方法、生体照合装置及び制御プログラム
WO2023045507A1 (fr) Reconnaissance faciale
US20210209508A1 (en) System and method for disentangling features specific to users, actions and devices recorded in motion sensor data
SG11201811498QA (en) Agent login method, electronic device and storage medium based on voiceprint identification
EP3543938B1 (fr) Authentification d'une carte de transaction à l'aide d'un fichier multimédia
US10936706B2 (en) Biometric authentication
KR20210128513A (ko) 전자 장치 및 그 제어 방법
US11126705B2 (en) Systems and methods for user authentication using word-gesture pairs
Tymoszek et al. Dashcam pay: a system for in-vehicle payments using face and voice
US20150269698A1 (en) Use of near field communication devices as proof of identity during electronic signature process
CN109614804A (zh) 一种双模态生物特征加密方法、设备及存储设备
CN108985166A (zh) 身份验证方法及装置、电子设备和存储介质
US20210112057A1 (en) Multi-party document validation
WO2016058540A1 (fr) Procédé et appareil d'authentification d'identité et support d'informations

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE