CN114357419A - Face verification method and device, storage medium and computer equipment - Google Patents
Face verification method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN114357419A CN114357419A CN202210010020.1A CN202210010020A CN114357419A CN 114357419 A CN114357419 A CN 114357419A CN 202210010020 A CN202210010020 A CN 202210010020A CN 114357419 A CN114357419 A CN 114357419A
- Authority
- CN
- China
- Prior art keywords
- face
- verification
- matching
- face image
- stored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012795 verification Methods 0.000 title claims abstract description 163
- 238000000034 method Methods 0.000 title claims abstract description 88
- 230000008569 process Effects 0.000 claims abstract description 38
- 230000006399 behavior Effects 0.000 claims description 6
- 230000001815 facial effect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
According to the face verification method, the face verification device, the storage medium and the computer equipment, when face verification is carried out, the obtained target face image can be matched with the face template of the verified person stored in the cache space, if matching is successful, the current target face image is the face image corresponding to the verified person, at the moment, the verification process can be directly ended, and repeated verification is avoided; if the matching fails, the current target face image is the face image corresponding to the unverified person, at this time, the target face image can be verified according to the face templates of all the persons stored in the memory, and the face templates of the verified persons are stored in the cache space, so that when the next round of face verification is performed, face matching is performed preferentially through the face templates of the verified persons stored in the cache space, therefore, not only can the face verification be quickly realized, but also the whole verification process can be effectively prevented from being repeated.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face verification method, a face verification device, a storage medium and computer equipment.
Background
With the rapid development of the internet technology, it is also very important to ensure the security of the user account by means of face verification. The face verification is a branch of the face recognition field, and two face photos can be verified fully automatically by using a face verification algorithm to judge whether the two face photos are the same person. The method can be used for user face identity verification in a plurality of scenes such as internet finance, security inspection, medical treatment, public security and the like.
At present, in the process of using face verification, if a current person passes verification, but the person does not leave a face verification area, the existing face verification is finished, and then the verified person who does not leave the face verification area is repeatedly verified, so that the verification process is increased, the verification time is too long, the verification efficiency is low, and other persons needing verification are affected.
Disclosure of Invention
The present invention aims to solve at least one of the above technical defects, and particularly, in the prior art, repeated verification is performed on a person who has not left a face verification area, which not only increases verification processes, makes verification time too long, and verification efficiency lower, but also affects other technical defects of persons who need verification.
The invention provides a face verification method, which comprises the following steps:
acquiring a target face image;
matching the target face image with a face template of the verified person stored in a cache space;
if the matching is successful, the verification is finished;
and if the matching fails, verifying the target face image based on the face templates of all the persons stored in the memory, and storing the face templates of the verified persons into the cache space.
Optionally, before the obtaining the target face image, the method further includes:
acquiring an image data frame acquired by equipment;
determining the maximum value of the number of effective face images contained in each image data frame;
and configuring the upper limit value of the face template of the verified person stored in the cache space according to the maximum value.
Optionally, the acquiring a target face image includes:
acquiring an image data frame acquired by equipment;
and determining an effective face image in the image data frame, and taking the effective face image as a target face image.
Optionally, if the matching fails, the method further includes:
and deleting the face template of the verified person stored in the cache space.
Optionally, the verifying the target face image based on the face templates of all the people stored in the memory includes:
matching the target face image with face templates of all persons stored in a memory;
if the matching is successful, entering the next verification link;
if the matching fails, the verification process is ended.
Optionally, if the matching is successful, after entering the next verification link, the method further includes:
determining whether an access right corresponding to the successfully matched target face image exists;
if the target face image exists, controlling the access behavior of the target person corresponding to the successfully matched target face image according to the access authority;
if not, the verification process is ended.
Optionally, after the storing the face template of the authenticated person into the cache space, the method further includes:
determining whether the storage time of the face template of the verified person stored in the cache space exceeds a preset storage time and whether a matching record exists in the preset storage time;
and if the preset storage time is exceeded and no matching record exists in the preset storage time, removing the face template of the verified person stored in the cache space.
The invention also provides a face verification device, comprising:
the image acquisition module is used for acquiring a target face image;
the template matching module is used for matching the target face image with a face template of a verified person stored in a cache space;
the verification ending module is used for ending the verification if the matching is successful;
and the face verification module is used for verifying the target face image based on the face templates of all the persons stored in the memory if the matching fails, and storing the face templates of the verified persons into the cache space.
The invention also provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to carry out the steps of the face verification method as described in any one of the above embodiments.
The present invention also provides a computer device comprising: one or more processors, and a memory;
the memory has stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the face verification method as in any one of the above embodiments.
According to the technical scheme, the embodiment of the invention has the following advantages:
according to the face verification method, the device, the storage medium and the computer equipment, when face verification is carried out, a target face image is obtained firstly, then the target face image is matched with the face template of the verified person stored in the cache space, if matching is successful, the current target face image is the face image corresponding to the verified person, at the moment, the verification process can be directly ended, and repeated verification is avoided; if the matching fails, the current target face image is the face image corresponding to the unverified personnel, at the moment, the target face image can be verified according to the face templates of all the personnel stored in the memory, and the face templates of the verified personnel are stored in the cache space, so that when the next round of face verification is carried out, face matching is preferentially carried out through the face templates of the verified personnel stored in the cache space, therefore, the face verification can be quickly realized, the repeated whole verification process can be effectively avoided, the equipment resource occupation is reduced, the verification efficiency is improved, the waiting time of the personnel needing verification is shortened, and the user experience is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a face verification method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an overall verification process according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a face verification apparatus according to an embodiment of the present invention;
fig. 4 is a schematic internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in the process of using face verification, if a current person passes verification, but the person does not leave a face verification area, the existing face verification is finished, and then the verified person who does not leave the face verification area is repeatedly verified, so that the verification process is increased, the verification time is too long, the verification efficiency is low, and other persons needing verification are affected.
Based on this, the following technical solutions are proposed in the present application, specifically referred to as follows:
in an embodiment, as shown in fig. 1, fig. 1 is a schematic flow chart of a face verification method according to an embodiment of the present invention; the invention provides a face verification method, which can comprise the following steps:
s110: and acquiring a target face image.
In this step, before performing face verification, the acquired face images may be acquired, and one or more face images in the acquired face images may be used as target face images to perform face verification.
Generally, for a safety-protected area, the identity of an entry-attempting person can be recognized through face recognition, so as to improve the safety of the area, such as an office building, a cell, an enterprise, and the like. Related safety protocols can be appointed in advance between related personnel in an office building, a community or an enterprise and managers, and the managers reasonably use the personnel information of the related personnel in the office building, the community or the enterprise under the limitation of the safety protocols, for example, the personnel information of the related personnel, such as human face image information, elevator control authority information, regional use authority information and the like, is used for safety control, so that the safety level of the region is improved.
In the process of acquiring images, one or more face images contained in the images acquired at one time may exist, if only one face image exists, face verification only needs to be performed on the one face image, if a plurality of face images exist, face verification can be performed on the plurality of face images at the same time, the specific verification number can be determined according to the speed of a face recognition algorithm and the area size of an acquisition area, and no limitation is made here.
Further, the face verification process of the present application can be implemented through a terminal, wherein the terminal is provided with a face verification system, and when the face verification system is started, the face verification method provided by the present application embodiment can be applied to verification. For example, the face verification system in the present application may include an image acquisition module, a template matching module, a verification end module, a face verification module, and the like. The terminal can also collect account information and face image information input by a user during registration, and send the account information and the face image information to the server for storage or store in a corresponding memory, so that when the face of the user to be verified needs to be verified, the method provided by the embodiment of the application is adopted for face verification.
It is understood that the terminal herein refers to an electronic device capable of acquiring, processing and storing images, and the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a personal computer, a face recognition gate, a security gate, etc.; the server can be one server, or a server cluster formed by a plurality of servers, or a cloud computing service center; the terminal and the server can be in communication connection through a wired or wireless network.
Furthermore, in a scene of face verification, the face verification system on the terminal can be started, and all face images in the area are collected through an image acquisition module in the face verification system, so that the target face image is acquired. Optionally, the image acquisition module may be a camera capable of acquiring an image, such as a 3D camera, or may be a common face recognition camera, which is not limited herein.
Of course, in the image acquisition process, besides the face image, some non-face images, such as object images, animal images, etc., or incomplete face images, are inevitably acquired. Therefore, after the image is collected, the non-face image or the incomplete face image in the collected image can be removed, and the complete and effective face image is reserved. In addition, for the collected incomplete face image, face image acquisition failure information can be returned so that the terminal can collect the complete and effective face image again.
S120: and matching the target face image with the face template of the verified person stored in the cache space, judging whether the matching is successful, if so, executing S130, and if not, executing S140.
In this step, after the target face image is acquired through S110, the target face image may be matched with the face template of the verified person stored in the cache space, and the subsequent operation may be executed according to the matching result.
In particular, the description of the face image determines the specific method and performance of face recognition. At present, two description methods of a characteristic vector and a facial pattern template are mainly adopted, one method is a characteristic vector method, the method comprises the steps of firstly determining the size, the position, the distance and other attributes of facial image facial contour such as eye iris, nose wing, mouth corner and the like, then calculating the geometrical characteristic quantities of the facial image, and forming characteristic vector describing facial image; one is facial pattern template method, which is to store several standard face templates or face organ templates in the library, and when comparing, match the collected face image with all face templates in the library by using normalized correlation measurement. In addition, there are methods that use pattern-recognized autocorrelation networks or features in conjunction with templates.
When the template matching is carried out, a face pattern template method is mainly selected for matching, and when the template matching is carried out specifically, facial feature information in the target face image is compared with the face template of the verified person stored in the cache space, so that the optimal matching object is found out.
The cache space in the application can be other disk space which is different from the memory and can store the face template, and can also be a small section of space opened up on the memory. The face template of the verified person is stored in the cache space, after the target face image is obtained, matching operation is performed on the target face image through the face template of the verified person stored in the cache space in advance, if matching is successful, the target face image obtained currently is the face image of the verified person, the verification process can be finished directly at the moment, repeated complete verification processes are avoided, and verification time is shortened.
In addition, the number of the stored face templates in the cache space can be determined according to the type selection of the product for collecting the image, and the face templates in the cache space can be removed, so that the cyclic use of the cache space is ensured.
S130: and finishing the verification.
In this step, if the target face image is successfully matched with the face template of the verified person stored in the cache space, it indicates that the currently acquired target face image is the face image of the verified person, and at this time, the verification process can be directly ended, so that the repeated complete verification process is avoided, the verification time is shortened, and the verification efficiency is improved.
S140: and verifying the target face image based on the face templates of all the persons stored in the memory, and storing the face templates of the verified persons into a cache space.
In this step, if the matching between the target face image and the face template of the verified person stored in the cache space fails, it indicates that the face template corresponding to the target face image is not stored in the current cache space, that is, the current target face image is not the face image of the verified person, at this time, the target face image may be verified according to the face templates of all the persons stored in the memory, and the face templates of the verified persons are stored in the cache space, so that template matching is performed during the next round of face verification.
It can be understood that, in the application, the terminal may collect account information and face image information input by the user during registration, or receive face image information, elevator control authority information, area use authority information, and the like of all people in the security protected area input by the user, and send the received information to the server for storage, or store the received information in a corresponding memory. If the received information is stored in the memory, when the face recognition system is started, the target face image can be directly verified according to the face templates of all the personnel stored in the memory; if the received information is stored in the server, when the face recognition system is started, face templates of all people can be called from the server to the memory, and when face verification is carried out, the target face image is verified through the face templates of all people stored in the memory.
It is understood that all persons here refer to all persons in the currently secured area, such as office buildings, employees in an enterprise, management personnel, property, cleaning personnel, etc., or residents, properties, etc. in a cell.
In the above embodiment, when performing face verification, a target face image is first obtained, and then the target face image is matched with a face template of a verified person stored in a cache space, and if matching is successful, it indicates that the current target face image is a face image corresponding to the verified person, and at this time, the verification process can be directly ended, thereby avoiding performing repeated verification; if the matching fails, the current target face image is the face image corresponding to the unverified personnel, at the moment, the target face image can be verified according to the face templates of all the personnel stored in the memory, and the face templates of the verified personnel are stored in the cache space, so that when the next round of face verification is carried out, face matching is preferentially carried out through the face templates of the verified personnel stored in the cache space, therefore, the face verification can be quickly realized, the repeated whole verification process can be effectively avoided, the equipment resource occupation is reduced, the verification efficiency is improved, the waiting time of the personnel needing verification is shortened, and the user experience is further improved.
In one embodiment, before the acquiring the target face image in S110, the method may further include:
s101: and acquiring an image data frame acquired by the equipment.
S102: and determining the maximum value of the number of the effective face images contained in each image data frame.
S103: and configuring the upper limit value of the face template of the verified person stored in the cache space according to the maximum value.
In this embodiment, before the face verification, the number of face templates of the verified person stored in the cache space may be configured in advance, so that the template matching may be performed more quickly during the subsequent face verification.
Specifically, when the number of face templates of a verified person stored in the cache space is configured, a plurality of image data frames acquired by the device may be acquired first, then the maximum value of the number of valid face images included in each image data frame is determined, and then the upper limit value of the face template in the cache space is configured according to the maximum value.
For example, when an image data frame transmitted by a camera of a certain selected type is obtained, at most five effective face images can be obtained in one image data frame, at this time, the number of face templates in the cache space can be set to five, when at most six effective face images can be obtained in the image data frame transmitted by the camera of a certain selected type, the number of face templates in the cache space can be set to six, the number of face templates in the cache space mainly depends on the selected type of the camera, and details are not repeated here.
In one embodiment, the acquiring of the target face image in S110 may include:
s111: and acquiring an image data frame acquired by the equipment.
S112: and determining an effective face image in the image data frame, and taking the effective face image as a target face image.
In this embodiment, a facial image acquisition device, such as a camera, may capture a large number of image data frames in real time, and after the facial recognition system acquires the image data frames, the facial recognition system may perform facial recognition on the image data frames and obtain facial information, where the facial information may include coordinate information of a facial image in the image data frames, width, height, and shooting time of the facial image, and other information.
The face information acquired through face recognition comprises complete face information and incomplete face information, in order to improve face recognition accuracy, the incomplete face information can be extracted, the complete face information is reserved, an effective face image can be determined through the complete face information, and the effective face image is used as a target face image for face verification.
In one embodiment, if the matching fails, the method may further include: and deleting the face template of the verified person stored in the cache space.
In this embodiment, after the target face image is matched with the face template of the verified person stored in the cache space, if the matching fails, it indicates that the verified person corresponding to the current target face image is not the verified person stored in the cache space, that is, the verified person stored in the cache space has already left, or the re-verification is not performed, and at this time, the face template of the verified person stored in the cache space may be deleted, so that a space is vacated and a new face template of the verified person is added.
It can be understood that, when the template matching is performed on the acquired target face images, the target face images with the same number can be matched according to the number of the face templates of the verified persons stored in the cache space, if all the target face images are not successfully matched, all the face templates in the current cache space can be deleted, and if one of the target face images is successfully matched and other target face images are not successfully matched, other face templates except the successfully matched face template in the cache space can be deleted.
In an embodiment, as shown in fig. 2, fig. 2 is a schematic flow chart of an overall verification process provided by an embodiment of the present invention; in S140, verifying the target face image based on the face templates of all the persons stored in the memory may include:
s141: and matching the target face image with the face templates of all the persons stored in the memory, judging whether the matching is successful, if so, executing S142, and if not, executing S143.
S142: and entering the next verification link.
S143: and finishing the verification process.
In this embodiment, as shown in fig. 2, when the matching between the target face image and the face template of the verified person stored in the cache space fails, it indicates that the verified person corresponding to the target face image has not performed face verification before, and at this time, the target face image may be matched with the face templates of all persons stored in the memory, so as to determine whether the verified person corresponding to the target face image belongs to one of all persons stored in the memory.
If the matching is successful, the verification personnel corresponding to the current target face image belong to one of all personnel stored in the memory, and at the moment, the next verification link can be continuously entered; if the verification is unsuccessful, it indicates that the verification person corresponding to the current target face image does not belong to one of all persons stored in the memory, and may be a foreign person or a person who is not recorded in the book in time.
In an embodiment, after entering the next verification link if the matching is successful, the method may further include:
s1421: and determining whether the access right corresponding to the successfully matched target face image exists, if so, executing S1422, and if not, executing S1423.
S1422: and controlling the access behavior of the target person corresponding to the successfully matched target face image according to the access authority.
S1423: and finishing the verification process.
In this embodiment, as shown in fig. 2, after the target face image is matched with the face templates of all the persons stored in the memory, if the matching is successful, it indicates that the verification person corresponding to the current target face image belongs to one of all the persons stored in the memory, at this time, it may be further determined whether the successfully matched target face image has a corresponding access right, if so, the access behavior of the target person corresponding to the successfully matched target face image is controlled according to the access right, and if not, the verification process is ended.
Access rights in this application refer, among other things, to mechanisms that restrict access to certain information items or certain controls based on the identities of users in various predefined groups and their membership. The access authority includes but is not limited to elevator control authority, regional access authority and the like, wherein the elevator control authority refers to the authority of an access person to arrive at a certain floor or a plurality of specified floors by taking an elevator, the elevator control authority in the application can be divided into three types, one type is the elevator control authority of only one floor of the access person, one type is the elevator control authority of a plurality of floors of the access person, which floor is specifically selected can be determined according to the selection of the access person, and the other type is the elevator control authority of no floor of the access person; the region access right here refers to a right of an accessing person to reach a specified region, such as a conference room, a studio, and the like.
It can be understood that with the increasing of elevators in commercial and residential buildings, free social personnel, sales promotion personnel, decoration personnel and the like are increased, in order to avoid unnecessary harassment of each merchant and residents, strengthen security of the building, improve intelligent management of property and support environmental protection advocates, the verification process of the access authority can be increased in the face verification process, and further enhance the safety of the building.
Further, if the successfully matched target face image has the corresponding access right, the access behavior of the target person corresponding to the successfully matched target face image can be controlled according to the access right. For example, when the current access permission is a ladder control permission and the obtained target face image which is successfully matched currently has the ladder control permission of a certain floor, the floor selected by the target person corresponding to the target face image can be continuously monitored, if the floor is the floor corresponding to the ladder control permission, the target person is allowed to select the floor, and if the floor is not the floor corresponding to the ladder control permission, the target person is not allowed to select the floor, so that the safety of the building is further improved.
In another implementation manner, when the current access right is the regional access right, if a conference room of a corresponding floor is appointed in advance by a target person corresponding to a target face image which is successfully matched currently, the floor selected by the target person can be matched with the floor where the preset conference room is located when face verification is performed, if matching is successful, the user can enter the conference room of the floor, and when the conference room of the corresponding floor is not appointed in advance by the target person, verification cannot be performed on the user at this time, but the verification process is directly ended, so that verification time is saved, and verification efficiency is improved.
In one embodiment, after saving the face template of the authenticated person in the cache space in S140, the method may further include:
s151: and determining whether the storage time of the face template of the verified person stored in the cache space exceeds a preset storage time, and whether a matching record exists in the preset storage time.
S152: and if the preset storage time is exceeded and no matching record exists in the preset storage time, removing the face template of the verified person stored in the cache space.
In this embodiment, after the face template of the verified person is stored in the cache space, in order to further improve the utilization rate of the cache space, the storage time of the face template in the cache space may be preset, and the actual storage time of the face template stored in the cache space is monitored, if the actual storage time exceeds the preset storage time, it is determined on the basis that whether the face template is matched within the preset storage time, and if the face template is matched, it indicates that the verified person may not leave the identification area, so the face template needs to be stored in the cache space continuously, and the person is prevented from verifying again; if the face template is not matched, it indicates that the currently authenticated person may have left the recognition area, and the face module may be cleared from the cache space, so as to make room.
Further, the preset storage time in the present application may be appropriately prolonged or shortened, which may be determined according to the speed of the face recognition algorithm.
The following describes the face verification device provided in the embodiment of the present application, and the face verification device described below and the face verification method described above may be referred to in a corresponding manner.
In an embodiment, as shown in fig. 3, fig. 3 is a schematic structural diagram of a face verification apparatus according to an embodiment of the present invention; the invention also provides a face verification device, which comprises an image acquisition module 210, a template matching module 220, a verification ending module 230 and a face verification module 240, and specifically comprises the following steps:
and an image obtaining module 210, configured to obtain a target face image.
And the template matching module 220 is configured to match the target face image with a face template of a verified person stored in the cache space.
And a verification ending module 230, configured to end the verification if the matching is successful.
And the face verification module 240 is configured to verify the target face image based on the face templates of all the persons stored in the memory if matching fails, and store the face templates of the verified persons into the cache space.
In the above embodiment, when performing face verification, a target face image is first obtained, and then the target face image is matched with a face template of a verified person stored in a cache space, and if matching is successful, it indicates that the current target face image is a face image corresponding to the verified person, and at this time, the verification process can be directly ended, thereby avoiding performing repeated verification; if the matching fails, the current target face image is the face image corresponding to the unverified personnel, at the moment, the target face image can be verified according to the face templates of all the personnel stored in the memory, and the face templates of the verified personnel are stored in the cache space, so that when the next round of face verification is carried out, face matching is preferentially carried out through the face templates of the verified personnel stored in the cache space, therefore, the face verification can be quickly realized, the repeated whole verification process can be effectively avoided, the equipment resource occupation is reduced, the verification efficiency is improved, the waiting time of the personnel needing verification is shortened, and the user experience is further improved.
In one embodiment, the apparatus may further include:
the first data frame acquisition module is used for acquiring the image data frame acquired by the equipment.
And the maximum value determining module is used for determining the maximum value of the number of the effective face images contained in each image data frame.
And the upper limit value determining module is used for configuring the upper limit value of the face template of the verified person stored in the cache space according to the maximum value.
In one embodiment, the image acquisition module 210 may include:
and the second data frame acquisition module is used for acquiring the image data frame acquired by the equipment.
And the face image determining module is used for determining an effective face image in the image data frame and taking the effective face image as a target face image.
In one embodiment, the apparatus may further include:
and the deleting module is used for deleting the face template of the verified person stored in the cache space.
In one embodiment, the face verification module 240 may include:
and the face matching module is used for matching the target face image with the face templates of all the persons stored in the memory.
And the flow transfer module is used for entering the next verification link if the matching is successful.
And the first ending module is used for ending the verification process if the matching fails.
In one embodiment, the flow turnaround module may further include:
and the access authority determining module is used for determining whether the access authority corresponding to the successfully matched target face image exists.
And if the target person exists, controlling the access behavior of the target person corresponding to the successfully matched target face image according to the access authority.
And the second ending module is used for ending the verification process if the verification process does not exist.
In one embodiment, the apparatus may further include:
and the information acquisition module is used for determining whether the storage time of the face template of the verified person stored in the cache space exceeds the preset storage time and whether a matching record exists in the preset storage time.
And the template clearing module is used for clearing the face template of the verified person stored in the cache space if the preset storage time is exceeded and no matching record exists in the preset storage time.
In one embodiment, the present invention also provides a storage medium having computer readable instructions stored therein, which when executed by one or more processors, cause the one or more processors to perform the steps of the face verification method as described in any one of the above embodiments.
In one embodiment, the present invention also provides a computer device comprising: one or more processors, and a memory.
The memory has stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the face verification method as in any one of the above embodiments.
Fig. 4 is a schematic diagram illustrating an internal structure of a computer device according to an embodiment of the present invention, and fig. 4 is a schematic diagram, where the computer device 300 may be provided as a server. Referring to fig. 4, the computer device 300 includes a processing component 302 that further includes one or more processors and memory resources, represented by memory 301, for storing instructions, such as application programs, that are executable by the processing component 302. The application programs stored in memory 301 may include one or more modules that each correspond to a set of instructions. Further, the processing component 302 is configured to execute instructions to perform the face verification method of any of the embodiments described above.
The computer device 300 may also include a power component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input output (I/O) interface 305. The computer device 300 may operate based on an operating system stored in memory 301, such as Windows Server, Mac OS XTM, Unix, Linux, Free BSDTM, or the like.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, the embodiments may be combined as needed, and the same and similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A face verification method, comprising:
acquiring a target face image;
matching the target face image with a face template of the verified person stored in a cache space;
if the matching is successful, the verification is finished;
and if the matching fails, verifying the target face image based on the face templates of all the persons stored in the memory, and storing the face templates of the verified persons into the cache space.
2. The method of claim 1, wherein before the obtaining the target face image, the method further comprises:
acquiring an image data frame acquired by equipment;
determining the maximum value of the number of effective face images contained in each image data frame;
and configuring the upper limit value of the face template of the verified person stored in the cache space according to the maximum value.
3. The method of claim 1, wherein the obtaining the target face image comprises:
acquiring an image data frame acquired by equipment;
and determining an effective face image in the image data frame, and taking the effective face image as a target face image.
4. The face verification method of claim 1, wherein if the matching fails, the method further comprises:
and deleting the face template of the verified person stored in the cache space.
5. The method of claim 1, wherein the verifying the target face image based on the face templates of all the people stored in the memory comprises:
matching the target face image with face templates of all persons stored in a memory;
if the matching is successful, entering the next verification link;
if the matching fails, the verification process is ended.
6. The face verification method according to claim 5, wherein if the matching is successful, after entering a next verification link, the method further comprises:
determining whether an access right corresponding to the successfully matched target face image exists;
if the target face image exists, controlling the access behavior of the target person corresponding to the successfully matched target face image according to the access authority;
if not, the verification process is ended.
7. The method of claim 1, wherein after storing the face template of the authenticated person into the cache space, the method further comprises:
determining whether the storage time of the face template of the verified person stored in the cache space exceeds a preset storage time and whether a matching record exists in the preset storage time;
and if the preset storage time is exceeded and no matching record exists in the preset storage time, removing the face template of the verified person stored in the cache space.
8. A face authentication apparatus, comprising:
the image acquisition module is used for acquiring a target face image;
the template matching module is used for matching the target face image with a face template of a verified person stored in a cache space;
the verification ending module is used for ending the verification if the matching is successful;
and the face verification module is used for verifying the target face image based on the face templates of all the persons stored in the memory if the matching fails, and storing the face templates of the verified persons into the cache space.
9. A storage medium, characterized by: the storage medium has stored therein computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the face verification method according to any one of claims 1 to 7.
10. A computer device, comprising: one or more processors, and a memory;
the memory has stored therein computer-readable instructions that, when executed by the one or more processors, perform the steps of the face verification method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010020.1A CN114357419A (en) | 2022-01-05 | 2022-01-05 | Face verification method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010020.1A CN114357419A (en) | 2022-01-05 | 2022-01-05 | Face verification method and device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114357419A true CN114357419A (en) | 2022-04-15 |
Family
ID=81107190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210010020.1A Pending CN114357419A (en) | 2022-01-05 | 2022-01-05 | Face verification method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114357419A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070118808A (en) * | 2006-06-13 | 2007-12-18 | (주)코아정보시스템 | Method of certificating face for embedded system |
| CN107657222A (en) * | 2017-09-12 | 2018-02-02 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN108875478A (en) * | 2017-08-14 | 2018-11-23 | 北京旷视科技有限公司 | The testimony of a witness unifies checking method, device and system and storage medium |
| CN109063581A (en) * | 2017-10-20 | 2018-12-21 | 奥瞳系统科技有限公司 | Enhanced Face datection and face tracking method and system for limited resources embedded vision system |
| CN109359548A (en) * | 2018-09-19 | 2019-02-19 | 深圳市商汤科技有限公司 | Plurality of human faces identifies monitoring method and device, electronic equipment and storage medium |
| CN111582047A (en) * | 2020-04-15 | 2020-08-25 | 浙江大华技术股份有限公司 | Face recognition verification passing method and related device thereof |
| CN113076859A (en) * | 2021-03-31 | 2021-07-06 | 深圳供电局有限公司 | Safety monitoring method and system for face recognition, electronic equipment and storage medium |
-
2022
- 2022-01-05 CN CN202210010020.1A patent/CN114357419A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070118808A (en) * | 2006-06-13 | 2007-12-18 | (주)코아정보시스템 | Method of certificating face for embedded system |
| CN108875478A (en) * | 2017-08-14 | 2018-11-23 | 北京旷视科技有限公司 | The testimony of a witness unifies checking method, device and system and storage medium |
| CN107657222A (en) * | 2017-09-12 | 2018-02-02 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN109063581A (en) * | 2017-10-20 | 2018-12-21 | 奥瞳系统科技有限公司 | Enhanced Face datection and face tracking method and system for limited resources embedded vision system |
| CN109359548A (en) * | 2018-09-19 | 2019-02-19 | 深圳市商汤科技有限公司 | Plurality of human faces identifies monitoring method and device, electronic equipment and storage medium |
| CN111582047A (en) * | 2020-04-15 | 2020-08-25 | 浙江大华技术股份有限公司 | Face recognition verification passing method and related device thereof |
| CN113076859A (en) * | 2021-03-31 | 2021-07-06 | 深圳供电局有限公司 | Safety monitoring method and system for face recognition, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 彭其渊: "《高速铁路调度指挥风险分析预警论与方法》", 30 June 2021, 中国铁道出版社, pages: 84 - 85 * |
| 杨晋吉;李荣兵;: "基于Adaboost与Clifford代数的人脸检测", 计算机工程, no. 09, 15 September 2013 (2013-09-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108885698B (en) | Face recognition method and device and server | |
| CN105809415B (en) | Check-in system, method and device based on face recognition | |
| CN110414373B (en) | Deep learning palm vein recognition system and method based on cloud edge-side cooperative computing | |
| CN107170068B (en) | Movable attendance checking method based on scene and image recognition | |
| US12135771B2 (en) | Intelligent gallery management for biometrics | |
| WO2021036436A1 (en) | Facial recognition method and apparatus | |
| WO2020248780A1 (en) | Living body testing method and apparatus, electronic device and readable storage medium | |
| CN110414376B (en) | Method for updating face recognition model, face recognition camera and server | |
| WO2019083508A1 (en) | Facial recognitions based on contextual information | |
| CN108961509A (en) | A kind of cell recognition of face entrance guard security system and its method | |
| CN105516085B (en) | A kind of system and method managing the interim internet behavior of visitor | |
| CN113053013A (en) | Access control method and device based on face recognition, computer equipment and medium | |
| WO2023173785A1 (en) | Access permission verification method, device, and system and identity authentication terminal | |
| CN110569911B (en) | Image recognition method, device, system, electronic equipment and storage medium | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| RU2381553C1 (en) | Method and system for recognising faces based on list of people not subject to verification | |
| CN110980454A (en) | Automatic control method and device for elevator in intelligent community and readable storage medium | |
| CN109166616A (en) | Service resource allocation method, device, computer equipment and storage medium | |
| CN116503922A (en) | Method, system and equipment for accurately positioning personnel residence | |
| CN114357419A (en) | Face verification method and device, storage medium and computer equipment | |
| CN108647613B (en) | Examinee examination method applied to examination room | |
| CN117611106B (en) | Smart park safe operation and maintenance method, system, equipment and medium | |
| WO2019229910A1 (en) | Immigration inspection system in which face authentication is used, immigration inspection method, program, and authentication device | |
| CN212160789U (en) | Face recognition access control system based on raspberry group | |
| WO2020152917A1 (en) | Face authentication device, face authentication method, program, and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |