CN107818301B - Method and device for updating biological characteristic template and electronic equipment - Google Patents
Method and device for updating biological characteristic template and electronic equipment Download PDFInfo
- Publication number
- CN107818301B CN107818301B CN201710970203.7A CN201710970203A CN107818301B CN 107818301 B CN107818301 B CN 107818301B CN 201710970203 A CN201710970203 A CN 201710970203A CN 107818301 B CN107818301 B CN 107818301B
- Authority
- CN
- China
- Prior art keywords
- user
- similarity
- biometric
- template
- image
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
Abstract
The embodiment of the application discloses a method, a device and electronic equipment for updating a biological characteristic template, wherein the method comprises the following steps: determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user; determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched with a biometric template of the first user; and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
Description
Technical Field
The present application relates to the field of biometric identification, and more particularly, to a method, an apparatus, and an electronic device for updating a biometric template.
Background
When the biological characteristic identification system carries out identity authentication on a user, the biological characteristic image of a person to be authenticated is collected, the collected biological characteristic image is compared with a biological characteristic template stored in advance, and whether the authentication passes or not is judged according to a comparison result and a corresponding strategy.
With the change of time, the real biological characteristics of the user may be different from the biological characteristics corresponding to the biological characteristic template, and in order to ensure that the biological characteristic template can reflect the latest biological characteristics of the authority owner to the maximum extent, the biological characteristic identification system needs to update the biological characteristic template.
The existing method for updating the biological characteristic template is likely to update the biological characteristic template by using the biological characteristic image of the attacker when the biological characteristic image of the attacker passes through the comparison of the biological characteristic image and the biological characteristic template, so that the prevention and control performance of the biological characteristic identification system on the attack is poor, and the subsequent identity authentication process has higher false passing rate.
Disclosure of Invention
The application aims to provide a method, a device and electronic equipment for updating a biological characteristic template, so that a biological characteristic identification system has better prevention and control performance on attacks and has lower false passing rate.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
in a first aspect, a method for updating a biometric template is provided, including:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
In a second aspect, there is provided an apparatus for updating a biometric template, comprising:
the first processing unit is used for determining a first similarity between a biological feature template of a first user and a first biological feature image set, wherein the first biological feature image set comprises at least one biological feature template of a second user;
a first processing unit, configured to determine a second similarity between a prepared biometric image and the first biometric image set, where the prepared biometric image is a biometric image that has been successfully matched with a biometric template of the first user;
and the second processing unit is used for determining whether to update the biological feature template of the first user by using the prepared biological feature image according to the first similarity and the second similarity.
In a third aspect, an electronic device is provided, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
In a fourth aspect, a computer-readable medium is provided that stores one or more programs that, when executed by an electronic device that includes a plurality of application programs, cause the electronic device to:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
As can be seen from the above technical solutions provided in the embodiments of the present application, whether to update the biometric template of the first user with the prepared biometric image is determined according to a first similarity between the biometric template of the first user and a biometric image set composed of at least one biometric template of the second user and a second similarity between the prepared biometric image and the biometric image set. When judging whether the biological characteristic template of the first user is updated by using the prepared biological characteristic image, the method considers the similarity between the prepared biological characteristic image and the biological characteristic template of the first user and the biological characteristic templates of other users, can improve the prevention and control performance of the biological characteristic recognition system on the attack of other users, and further reduces the false passing rate of the biological characteristic recognition system.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a flow diagram of a method of updating a biometric template according to one embodiment of the present application.
Fig. 2 is a flow chart of a method of updating a biometric template according to a specific embodiment of the present application.
FIG. 3 is a block diagram of an electronic device according to one embodiment of the present application.
Fig. 4 is a block diagram of an apparatus for updating a biometric template according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
Fig. 1 is a flow diagram of a method 100 of updating a biometric template according to one embodiment of the present application. The method of fig. 1 is performed by an apparatus for updating a biometric template. It should be understood that the solution of the embodiment of the present application may be applicable to updating of a face image template, that is, the solution of the embodiment of the present application may be applicable to a face recognition system. Of course, the application of the method of embodiments of the present application to the updating of other biometric templates, including but not limited to fingerprint templates, is not excluded.
As shown in fig. 1, at S102, a first similarity between a biometric template of a first user and a first set of biometric images is determined, the first set of biometric images including a biometric template of at least one second user.
It will be appreciated that the first similarity between the biometric template of the first user and the first set of biometric images reflects the degree of similarity of the biometric template of the first user to the biometric template of the at least one second user as a whole.
Note that the biometric template is a biometric image that is retained or registered by the user in advance. When the identity authentication of the user is needed, the biological characteristic image of the user is collected, and the collected biological characteristic image is compared with the biological characteristic template. If the comparison is passed, the identity authentication is passed, otherwise, the identity authentication is failed.
It should be noted that the biometric image in the embodiment of the present application may be an image of a biometric feature of the user directly acquired, or may be an image obtained by processing the acquired biometric image, and the processing may be, for example, denoising processing.
Optionally, at S102, the first similarity is a similarity score or a similarity level.
Optionally, as an embodiment, the biometric template library stores a biometric template of the first user and at least one biometric template of the second user, and the biometric template of the first user and the biometric template of the at least one biometric template of the second user are obtained from the biometric template library.
Optionally, as an example, the first similarity is determined according to a weight corresponding to at least one biometric template of the second user and a third similarity, and the third similarity is used to describe a similarity between the biometric template of the second user and the biometric template of the first user. For example, assuming that the third similarity is characterized by a similarity score, the maximum value of the third similarity is 1, and assuming that there are 3 second users, the weights corresponding to the biometric templates of the 3 second users are 0.8, 0.6 and 0.3, respectively, and the corresponding third similarities are 0.2, 0.8 and 0.4, respectively, the maximum product of the corresponding weight and the third similarity is determined as the first similarity, i.e., the product of 0.6 and 0.8 is 0.48 as the first similarity. The minimum product of the corresponding weight and the third similarity may also be determined as the first similarity, i.e., 0.12, which is the product of 0.3 and 0.4, is used as the first similarity.
Optionally, as another example, a sum of products of the weight corresponding to the biometric template of the at least one second user and the third similarity is determined as the first similarity. Similarly, assuming that the third similarity is characterized by a similarity score, the maximum value of the third similarity is 1, and assuming that there are 3 second users, the biometric templates of the 3 second users have weights of 0.8, 0.6 and 0.3, respectively, and the third similarities of 0.2, 0.8 and 0.4, respectively, the sum of 0.16, 0.48 and 0.12 is determined as the first similarity.
Optionally, as a further example, the first similarity is characterized by a set of products of weights corresponding to the biometric templates of the at least one second user and the third similarity. Similarly, assuming that the third similarity is represented by a similarity score, the maximum value of the third similarity is 1, and assuming that there are 3 second users, the biometric templates of the 3 second users have weights of 0.8, 0.6 and 0.3 respectively, and the third similarities are 0.2, 0.8 and 0.4 respectively, the first similarity is represented by a set of 0.16, 0.48 and 0.12.
Specifically, in some embodiments, the corresponding weight of the biometric template of the at least one second user may be determined according to at least one of the following parameters: the geographic location of the at least one second user, the type of social relationship of the at least one second user with the first user, and the duration of the social relationship of the at least one second user with the first user.
For example, the weight corresponding to the biometric template of the second user may be determined according to the economic development degree of the city where the second user is located, and the higher the economic development degree is, the higher the weight corresponding to the biometric template is. The weight corresponding to the biometric template of the second user can be determined according to the distance between the geographic position of the second user and the geographic position of the first user, and the closer the distance, the higher the weight corresponding to the biometric template is. The weight corresponding to the biometric template of the second user may be determined according to the type of social relationship of the second user with the first user, for example, the biometric template of the second user having a debt relationship with the first user may be weighted higher than the biometric template of the second user having a normal chat friendship relationship with the first user. The weight corresponding to the biological feature template of the second user can be determined according to the duration of the social relationship between the second user and the first user, and the longer the duration, the higher the weight corresponding to the biological feature template of the second user is.
Alternatively, as an example, the first set of biometric images may be determined by acquiring user relationship network data. User relationship network data herein is used to describe users having a social relationship with a first user. After the user relationship network data is acquired, at least one second user is determined according to the user relationship network data, and at least one biometric template of the second user is acquired, for example, the biometric template of the second user is acquired from the biometric template library described above, and a set formed by the biometric templates of the second user is determined as the first biometric image set.
Specifically, in some embodiments, when at least one second user is determined from the user relationship network data, a user whose biometric template has a social relationship with the first user among all users described by the user relationship network data and whose similarity to the biometric template of the first user is higher than a similarity threshold is determined as the second user.
Specifically, in other embodiments, the user relationship network data is obtained through social software of the user, or the user relationship network data is obtained through a fund flow network of the user, or the user relationship network data is obtained through a network environment in which the user shares WIFI. User relationship network data may describe social relationships between one user and another user in the form of user pairs.
In the embodiment of the present application, the social relationship between one user and another user may be a direct social relationship or an indirect social relationship. An indirect social relationship refers to a social relationship established by two users through one user as an intermediary.
At S104, a second similarity between the preliminary biometric image and the first set of biometric images is determined, the preliminary biometric image being a biometric image that has been successfully matched with the biometric template of the first user.
It will be appreciated that the second similarity between the preliminary biometric image and the first set of biometric images reflects the degree of similarity of the preliminary biometric image to the biometric template of the at least one second user as a whole.
It should be noted that, although the above embodiment has been described with the step S104 being disposed after the step S102 for convenience of description, the execution order of these two steps may be switched according to practical situations, that is, the second similarity between the preliminary biometric image and the first biometric image set is determined, and then the first similarity between the biometric template of the first user and the first biometric image set is determined. Or both steps may be performed simultaneously, i.e. determining a second similarity between the preliminary biometric image and the first set of biometric images while determining a first similarity between the biometric template of the first user and the first set of biometric images.
It is to be understood that the preliminary biometric image may or may not be the biometric image of the first user.
Optionally, as an example, the second similarity is determined according to a weight corresponding to the biometric template of the at least one second user and a fourth similarity, and the fourth similarity is used to describe a similarity between the biometric template of the second user and the prepared biometric image. For example, assuming that the fourth similarity is characterized by a similarity score, the maximum value of the fourth similarity is 1, and assuming that there are 3 second users, the weights corresponding to the biometric templates of the 3 second users are 0.7, 0.5 and 0.2, respectively, and the corresponding fourth similarities are 0.8, 0.5 and 0.9, respectively, the maximum product of the corresponding weight and the fourth similarity is determined as the second similarity, i.e., the product of 0.7 and 0.8 is 0.56 as the second similarity. The minimum product of the corresponding weight and the third similarity may also be determined as the first similarity, i.e., 0.18, which is the product of 0.2 and 0.9, is used as the second similarity.
Optionally, as another example, the sum of the product of the weight corresponding to the biometric template of the at least one second user and the fourth similarity is determined as the second similarity. Also assuming that the fourth similarity is characterized by a similarity score and the maximum value of the fourth similarity is 1, and assuming that there are 3 second users, the biometric templates of the 3 second users have weights of 0.7, 0.5 and 0.2, respectively, and the corresponding fourth similarities of 0.8, 0.5 and 0.9, respectively, the sum of 0.56, 0.25 and 0.18 and 0.99 is determined as the second similarity.
Optionally, as a further example, the second similarity is characterized by a set of products of weights corresponding to the biometric templates of the at least one second user and the fourth similarity. Similarly, assuming that the fourth similarity is characterized by a similarity score and the maximum value of the fourth similarity is 1, and assuming that there are 3 second users, the biometric templates of the 3 second users have weights of 0.7, 0.5 and 0.2, respectively, and the fourth similarities of 0.8, 0.5 and 0.9, respectively, the second similarities are characterized by a set of 0.56, 0.25 and 0.18.
Alternatively, as another example, a second biometric image set is acquired, the second biometric image set including a plurality of biometric images that have been successfully matched with the biometric image template of the first user, and a biometric image with the highest similarity to the biometric image template of the first user among the plurality of biometric images is determined as the preliminary biometric image. Therefore, the probability of updating the biological characteristic template of the first user by using the biological characteristic images of other users can be reduced, and the attack prevention and control performance of the biological characteristic identification system can be improved.
Specifically, in some embodiments, the biometric image is a facial image, and the image quality and the amount of facial information carried by the biometric image included in the second set of biometric images that has been successfully matched with the first biometric template satisfy the preset criteria and do not include a preset facial expression, where the preset facial expression may be a strange expression, such as the expression of glares. Therefore, when the prepared biological characteristic image is used for updating the biological characteristic template of the first user, the updated biological characteristic template of the first user can be ensured to have better image quality, enough information is carried, and the misrecognition rate of the biological characteristic recognition system is further improved.
At S106, it is determined whether to update the biometric template of the first user using the preliminary biometric image according to the first similarity and the second similarity.
It will be appreciated that the preliminary biometric image may or may not be the biometric image of the first user. Determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity at S106 can reduce the possibility of updating the biometric template of the first user by using the prepared biometric image when the prepared biometric image is not the biometric image of the first user, thereby improving the prevention and control performance of the biometric identification system on the attack.
Optionally, in some embodiments, at S106, the determining whether to update the biometric template of the first user using the preliminary biometric image specifically includes: it is determined whether to replace the biometric template of the first user with the preliminary biometric image.
Specifically, in some embodiments, if the first similarity is higher than the second similarity, indicating that the biometric template of the first user has a higher similarity to the first set of biometric images, the biometric template of the first user may be updated with a higher probability of successfully attacking the biometric identification system by the second user if the biometric template of the first user is not updated.
Specifically, in other embodiments, if the first similarity is lower than or equal to the second similarity, it indicates that the biometric template of the first user has a lower similarity to the first set of biometric images, if updating the biometric features of the first user using the prepared biometric image would otherwise result in an increased likelihood that the second user successfully attacks the biometric identification system, and in order to reduce the likelihood that the second user successfully attacks the biometric identification system, the biometric template of the first user is not updated using the prepared biometric image, or is understood as not replacing the biometric template of the first user with the prepared biometric image, i.e., the biometric template of the first user is kept unchanged. For example, in the specific example described above, the first similarity is 0.76, and the second similarity is 0.99, which indicates that the similarity between the prepared biometric image and the first biometric image set is higher than the similarity between the biometric template of the first user and the first biometric image set, and if the biometric template of the first user is updated by using the prepared biometric image, it will make it easier for the second user to attack the biometric recognition system, so the biometric template of the first user is not updated by using the prepared biometric image features.
In particular, in still other embodiments, whether to update the biometric template of the first user with the preliminary biometric image may be determined as a result of a plurality of logical determinations. Still in the above specific example, the first similarity is characterized by a set of 0.16, 0.48 and 0.12, the second similarity is characterized by a set of 0.56, 0.25 and 0.18, the elements at the corresponding positions of the first similarity and the second similarity are sequentially judged to determine the level of the first similarity and the second similarity, wherein 0.16 is less than 0.56, 0.48 is greater than 0.25, 0.12 is less than 0.18, the first similarity is considered to be less than the second similarity, and the biometric template of the first user is not updated by using the prepared biometric image
In this embodiment of the application, optionally, before S106, it is determined that, between the time when the biometric template of the first user is updated last time and the current time, data of the biometric image that has been successfully matched with the biometric template of the first user is greater than or equal to a preset threshold; and/or determining that the time interval between the last updated time of the biometric template of the first user and the current time is greater than or equal to a preset time interval. That is, a time factor is considered in determining whether to update the biometric template of the first user using the preliminary biometric image. Thus, the overhead caused by unnecessary frequent updating of the biometric template of the first user can be avoided.
In all the above embodiments, if the biometric template of the first user is updated using the preliminary biometric image, that is, the preliminary biometric image is determined as a new biometric template of the first user, the biometric template of the first user before the update may be deleted, and the biometric image stored in the biometric template library at a time other than the preliminary biometric image between the update and the previous update may be further deleted.
The method for updating a biometric template according to an embodiment of the present application will be described below with reference to a specific embodiment. Fig. 2 is a flow diagram of a method 200 of updating a biometric template according to a specific embodiment of the present application. In fig. 2, a face with a biometric feature is taken as an example. It is understood that the embodiment shown in fig. 2 is only a specific embodiment of the present application, and the numbering in fig. 2 does not limit the execution sequence of the steps.
As shown in fig. 2, at S202, the original base map of the target user is taken from the base map library.
At S204, user relationship network data is obtained.
It should be noted that the method for acquiring the user relationship network data at S204 is the same as that in the method 100, and is not described herein again.
At S206, the original base map of the target user is compared with the base maps of some or all users described in the user relationship network data, and a similarity score is output.
Optionally, in S206, the comparison result is quantized and output by using another measure besides the similarity value, where the another measure may be, for example, the similarity level.
At S208, selecting the base maps of the N users with the similarity scores higher than the preset threshold value with the original base map of the target user to form a high-risk attack base map set.
The value of N is a positive integer greater than or equal to 1.
At S210, a preliminary picture is selected among pictures uploaded while the user swipes his face.
It should be noted that the pictures uploaded by the user while brushing the face refer to the face pictures that have been successfully matched with the original base picture of the target user, and these pictures may include the face pictures of the non-target users.
Optionally, at S210, a picture satisfying a certain picture quality, having a certain face information amount satisfying a certain criterion, and having no strange and abnormal expressions is selected as a preliminary picture. If there are a plurality of pictures satisfying the above condition, one of the plurality of pictures having the highest similarity to the original base picture of the target user can be selected as the preliminary picture.
At S212, a similarity score between the prepared picture and the high-risk attack base map is calculated, and a similarity score between the original base map of the target user and the high-risk attack base map is calculated.
Optionally, the similarity score between the prepared picture and the high-risk attack base map is recorded as: s _ new _1, s _ new _2, …, s _ new _ N. And (3) recording the similarity degree value between the original base map of the target user and the high-risk attack base map as: s _ base _1, s _ base _2, …, s _ base _ N.
At S214, a sum of products of the similarity score between the prepared picture and the high-risk attack base map and the weight of the high-risk attack base map sum (w _ n _ S _ new _ n) is calculated, and a sum of products of the similarity score between the original base map of the target user and the high-risk attack base map and the weight of the high-risk attack base map sum (w _ n _ S _ base _ n) is calculated.
At S214, w _ n is used to represent the weight of the nth high risk attack floor map.
It should be noted that the method for determining the weight of the high-risk attack base map in the method 200 is the same as the method for determining the weight corresponding to the biometric image of the second user in the method 100, and details are not repeated here.
At S216, it is determined whether sum (w _ n × S _ base _ n) is greater than sum (w _ n × S _ new _ n).
Optionally, as an example, in S214, the product w _ n _ S _ new _ n of the similarity score between the prepared picture and the high-risk attack base graph and the weight of the high-risk attack base graph is respectively calculated, and the product w _ n _ S _ base _ n of the similarity score between the original base graph and the high-risk attack base graph of the target user and the weight of the high-risk attack base graph is calculated. Correspondingly, in S216, w _ n _ S _ new _ n and w _ n _ S _ base _ n are sequentially compared, and whether to update the original base map of the target user using the preliminary picture is determined according to the comparison result.
For example, the sizes of w _1 × w _ base _1 and w _1 × w _ new _1, the sizes of w _2 × w _ base _2 and w _2 × w _ new _2, …, w _ N × w _ base _ N and w _ N _ w _ new _ N are compared in sequence, and whether to update the original base map of the target user using the preliminary picture is determined according to the number of values greater than w _ N × w _ new _ N in w _ N _ w _ base _ N.
At S218, if sum (w _ n × S _ base _ n) is greater than sum (w _ n × S _ new _ n), updating the original base map of the target user with the preliminary picture; and if the sum (w _ n _ s _ base _ n) is less than or equal to the sum (w _ n _ s _ new _ n), abandoning the updating of the original base map of the target user.
Specifically, at S218, if sum (w _ n _ S _ base _ n) is greater than sum (w _ n _ S _ new _ n), it indicates that the similarity between the preliminary picture and the high-risk user base picture is lower than that between the original base picture of the target user, and the face recognition system is less vulnerable to attack when the original base picture of the target user is updated using the preliminary picture. If sum (w _ n _ s _ base _ n) is less than or equal to sum (w _ n _ s _ new _ n), the similarity between the prepared picture and the high-risk user base picture set is higher than that between the original base picture of the target user, and if the original base picture of the target user is updated by using the prepared picture, the face recognition system is more easily attacked, and then the updating of the original base picture of the target user is abandoned.
The method for updating the biometric template according to the embodiment of the present application is described in detail above with reference to fig. 1 and 2. An electronic device according to an embodiment of the present application will be described in detail below with reference to fig. 3. Referring to fig. 3, at a hardware level, the electronic device includes a processor, optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be interconnected by an internal bus, which may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form a device for updating the biological characteristic template on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
The method performed by the apparatus for updating a biometric template disclosed in the embodiment of fig. 1 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method shown in fig. 1, and implement the function of the apparatus for updating a biometric template in the embodiment shown in fig. 1, which is not described herein again in this embodiment of the present application.
Of course, besides the software implementation, the electronic device of the present application does not exclude other implementations, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or a logic device.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method of the embodiment shown in fig. 1, and are specifically configured to perform the following method:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
and determining whether to update the biometric template of the first user by using the prepared biometric image according to the first similarity and the second similarity.
Fig. 4 is a schematic structural diagram of an apparatus for updating a biometric template according to an embodiment of the present application. Referring to fig. 4, in one software implementation, the apparatus 400 for updating a biometric template may include: a first processing unit 401 and a second processing unit 402, wherein,
a first processing unit 401, configured to determine a first similarity between a biometric template of a first user and a first biometric image set, where the first biometric image set includes at least one biometric template of a second user;
a first processing unit 401, configured to determine a second similarity between a prepared biometric image and the first biometric image set, where the prepared biometric image is a biometric image that has been successfully matched with a biometric template of the first user;
a second processing unit 402, configured to determine whether to update the biometric template of the first user using the prepared biometric image according to the first similarity and the second similarity.
According to the device for updating the biological characteristic template, when judging whether the biological characteristic template of the first user is updated by using the prepared biological characteristic image, the similarity between the prepared biological characteristic image and the biological characteristic template of the first user and the biological characteristic templates of other users is considered, the prevention and control performance of the biological characteristic identification system on the attack of other users can be improved, and the false passing rate of the biological characteristic identification system is further reduced.
Optionally, as an embodiment, if the first similarity is higher than the second similarity, the second processing unit 402 updates the biometric template of the first user by using the prepared biometric image;
if the first similarity is lower than or equal to the second similarity, the second processing unit 402 does not update the biometric template of the first user using the prepared biometric image.
Optionally, as an embodiment, the first processing unit 402 determines whether to replace the biometric template of the first user with the preliminary biometric image.
Optionally, as an embodiment, the first processing unit 401:
determining the first similarity according to the weight corresponding to the at least one second user biological feature template and a third similarity, wherein the third similarity is used for describing the similarity between the second user biological feature template and the first user biological feature template; and/or the presence of a gas in the gas,
and determining the second similarity according to the weight corresponding to the at least one second user's biometric template and a fourth similarity, wherein the fourth similarity is used for describing the similarity between the biometric template of the second user and the prepared biometric image.
Optionally, as an embodiment, the first processing unit 401 determines, as the first similarity, a sum of products of a weight corresponding to the biometric template of the at least one second user and the third similarity.
Optionally, as an embodiment, the first processing unit 401 determines, as the second similarity, a sum of products of a weight corresponding to the biometric template of the at least one second user and a fourth similarity.
Optionally, as an embodiment, the first processing unit 401 determines the weight corresponding to the biometric template of the at least one second user according to at least one of the following parameters: the geographic location of the at least one second user, the type of social relationship of the at least one second user with the first user, and the duration of the social relationship of the at least one second user with the first user.
Optionally, as an embodiment, a similarity between the biometric template of the at least one second user and the biometric template of the first user is higher than a similarity threshold.
Optionally, as an embodiment, the first processing unit 401 obtains user relationship network data, where the user relationship network data is used to describe users having social relationships with the first user, and the users having social relationships with the first user include the at least one second user;
and determining the at least one second user according to the user relationship network data, and determining a set formed by the biological feature templates of the at least one second user as the first biological feature image set.
Optionally, as an embodiment, the first processing unit 401:
acquiring a second biological characteristic image set, wherein the second biological characteristic image set comprises a plurality of biological characteristic images which are successfully matched with the biological characteristic image template of the first user;
and determining the biological characteristic image with the highest similarity with the biological characteristic template of the first user in the second biological characteristic image set as the prepared biological characteristic image.
Optionally, as an embodiment, the biometric images are face images, the image qualities and the amount of face information carried of the plurality of biometric images satisfy preset criteria, and the plurality of biometric images do not include preset facial expressions.
Optionally, as an embodiment, the second processing unit 402:
determining that the number of the biological characteristic images successfully matched with the biological characteristic template of the first user is greater than or equal to a preset value between the time when the biological characteristic template of the first user is updated last time and the current time; and/or the presence of a gas in the gas,
and determining that the time interval between the last updated time and the current time of the biometric template of the first user is greater than or equal to a preset time interval.
Optionally, as an embodiment, the first processing unit 401 obtains the biometric template of the first user from a stored biometric template library.
The apparatus 400 for updating a biometric template may also perform the method of the embodiment shown in fig. 1, and implement the functions of the apparatus for updating a biometric template in the embodiment shown in fig. 1, which are not described herein again in this embodiment of the present application.
In short, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (15)
1. A method of updating a biometric template, comprising:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
determining whether to update the biometric template of the first user using the prepared biometric image according to the first similarity and the second similarity;
wherein the first similarity is determined by:
determining the first similarity according to the weight corresponding to the at least one second user biological feature template and a third similarity, wherein the third similarity is used for describing the similarity between the second user biological feature template and the first user biological feature template; and/or the presence of a gas in the gas,
the second similarity is determined by:
and determining the second similarity according to the weight corresponding to the at least one second user's biometric template and a fourth similarity, wherein the fourth similarity is used for describing the similarity between the biometric template of the second user and the prepared biometric image.
2. The method of claim 1, further comprising:
updating the biometric template of the first user using the preliminary biometric image if the first similarity is higher than the second similarity;
if the first similarity is lower than or equal to the second similarity, the biometric template of the first user is not updated by using the prepared biometric image.
3. The method of claim 1 or 2, the determining whether to update the first user's biometric template using the preliminary biometric image, comprising:
determining whether to replace the biometric template of the first user with the preliminary biometric image.
4. The method of claim 1, wherein determining the first similarity according to the weight and the third similarity corresponding to the biometric template of the at least one second user comprises:
and determining the sum of the products of the weight corresponding to the biological feature template of the at least one second user and the third similarity as the first similarity.
5. The method of claim 1, wherein determining the second similarity according to the weight corresponding to the biometric template of the at least one second user and a fourth similarity comprises:
and determining the sum of the product of the weight corresponding to the biological feature template of the at least one second user and the fourth similarity as the second similarity.
6. The method of claim 4 or 5, further comprising:
determining the corresponding weight of the biometric template of the at least one second user according to at least one of the following parameters: the geographic location of the at least one second user, the type of social relationship of the at least one second user with the first user, and the duration of the social relationship of the at least one second user with the first user.
7. The method of claim 1 or 2, the biometric template of the at least one second user having a similarity to the biometric template of the first user above a similarity threshold.
8. The method of claim 7, further comprising:
obtaining user relationship network data, wherein the user relationship network data is used for describing users having social relationship with the first user, and the users having social relationship with the first user comprise the at least one second user;
and determining the at least one second user according to the user relationship network data, and determining a set formed by the biological feature templates of the at least one second user as the first biological feature image set.
9. The method of claim 1 or 2, further comprising:
acquiring a second biological characteristic image set, wherein the second biological characteristic image set comprises a plurality of biological characteristic images which are successfully matched with the biological characteristic image template of the first user;
and determining the biological characteristic image with the highest similarity with the biological characteristic template of the first user in the second biological characteristic image set as the prepared biological characteristic image.
10. The method according to claim 9, wherein the biometric images are facial images, the image quality and the amount of facial information carried by the plurality of biometric images satisfy preset criteria, and the plurality of biometric images do not include preset facial expressions.
11. The method of claim 1 or 2, further comprising, prior to determining whether to update the biometric template of the first user using the preliminary biometric image based on the first similarity and the second similarity:
determining that the number of the biological characteristic images successfully matched with the biological characteristic template of the first user is greater than or equal to a preset value between the time when the biological characteristic template of the first user is updated last time and the current time; and/or the presence of a gas in the gas,
and determining that the time interval between the last updated time and the current time of the biometric template of the first user is greater than or equal to a preset time interval.
12. The method of claim 1 or 2, further comprising:
and acquiring the biological characteristic template of the first user from the stored biological characteristic template library.
13. An apparatus for updating a biometric template, comprising:
the first processing unit is used for determining a first similarity between a biological feature template of a first user and a first biological feature image set, wherein the first biological feature image set comprises at least one biological feature template of a second user;
a first processing unit, configured to determine a second similarity between a prepared biometric image and the first biometric image set, where the prepared biometric image is a biometric image that has been successfully matched with a biometric template of the first user;
a second processing unit that determines whether to update the biometric template of the first user using the prepared biometric image according to the first similarity and the second similarity;
the first processing unit determines the first similarity according to the weight corresponding to the at least one second user biometric template and a third similarity, wherein the third similarity is used for describing the similarity between the biometric template of the second user and the biometric template of the first user; and/or the presence of a gas in the gas,
and determining the second similarity according to the weight corresponding to the at least one second user's biometric template and a fourth similarity, wherein the fourth similarity is used for describing the similarity between the biometric template of the second user and the prepared biometric image.
14. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions that when executed use the processor to perform the following:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
determining whether to update the biometric template of the first user using the prepared biometric image according to the first similarity and the second similarity;
wherein the first similarity is determined by:
determining the first similarity according to the weight corresponding to the at least one second user biological feature template and a third similarity, wherein the third similarity is used for describing the similarity between the second user biological feature template and the first user biological feature template; and/or the presence of a gas in the gas,
the second similarity is determined by:
and determining the second similarity according to the weight corresponding to the at least one second user's biometric template and a fourth similarity, wherein the fourth similarity is used for describing the similarity between the biometric template of the second user and the prepared biometric image.
15. A computer readable medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to:
determining a first similarity between a biometric template of a first user and a first set of biometric images, the first set of biometric images including a biometric template of at least one second user;
determining a second similarity between a preliminary biometric image and the first set of biometric images, the preliminary biometric image being a biometric image that has been successfully matched to the biometric template of the first user;
determining whether to update the biometric template of the first user using the prepared biometric image according to the first similarity and the second similarity;
wherein the first similarity is determined by:
determining the first similarity according to the weight corresponding to the at least one second user biological feature template and a third similarity, wherein the third similarity is used for describing the similarity between the second user biological feature template and the first user biological feature template; and/or the presence of a gas in the gas,
the second similarity is determined by:
and determining the second similarity according to the weight corresponding to the at least one second user's biometric template and a fourth similarity, wherein the fourth similarity is used for describing the similarity between the biometric template of the second user and the prepared biometric image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710970203.7A CN107818301B (en) | 2017-10-16 | 2017-10-16 | Method and device for updating biological characteristic template and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710970203.7A CN107818301B (en) | 2017-10-16 | 2017-10-16 | Method and device for updating biological characteristic template and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107818301A CN107818301A (en) | 2018-03-20 |
| CN107818301B true CN107818301B (en) | 2021-04-02 |
Family
ID=61608090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710970203.7A Active CN107818301B (en) | 2017-10-16 | 2017-10-16 | Method and device for updating biological characteristic template and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107818301B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491813A (en) * | 2018-03-29 | 2018-09-04 | 百度在线网络技术（北京）有限公司 | Method and apparatus for fresh information |
| CN109492560A (en) * | 2018-10-26 | 2019-03-19 | 深圳力维智联技术有限公司 | Facial image Feature fusion, device and storage medium based on time scale |
| CN111125390A (en) * | 2018-11-01 | 2020-05-08 | 北京市商汤科技开发有限公司 | Database updating method and device, electronic equipment and computer storage medium |
| CN109509229B (en) * | 2018-11-12 | 2020-12-15 | 凌云光技术集团有限责任公司 | Template reconstruction device and method based on two-dimensional linear transformation |
| CN109919017B (en) * | 2019-01-28 | 2023-09-01 | 平安科技（深圳）有限公司 | Face recognition optimization method, device, computer equipment and storage medium |
| CN110503031B (en) * | 2019-08-21 | 2021-11-26 | 杭州宇泛智能科技有限公司 | Method for improving face recognition accuracy and passing speed |
| CN112926041B (en) * | 2021-02-08 | 2022-09-09 | 西安电子科技大学 | Remote identity authentication system based on biological characteristics |
| CN116310763B (en) * | 2023-05-10 | 2023-07-21 | 合肥英特灵达信息技术有限公司 | Template image generation method and device, electronic equipment and storage medium |
| CN116597185B (en) * | 2023-07-17 | 2023-12-15 | 荣耀终端有限公司 | Template updating method and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
| CN102576460A (en) * | 2009-09-09 | 2012-07-11 | 日本电气株式会社 | Biometric authentication system, method and program |
| CN103716309A (en) * | 2013-12-17 | 2014-04-09 | 华为技术有限公司 | Security authentication method and terminal |
| CN104823203A (en) * | 2013-09-16 | 2015-08-05 | 眼验有限责任公司 | Biometric template security and key generation |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN107196765A (en) * | 2017-07-19 | 2017-09-22 | 武汉大学 | A kind of remote biometric characteristic identity authentication method for strengthening secret protection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012151680A1 (en) * | 2011-05-10 | 2012-11-15 | Agrafioti Foteini | System and method for enabling continuous or instantaneous identity recognition based on physiological biometric signals |
-
2017
- 2017-10-16 CN CN201710970203.7A patent/CN107818301B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102576460A (en) * | 2009-09-09 | 2012-07-11 | 日本电气株式会社 | Biometric authentication system, method and program |
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
| CN104823203A (en) * | 2013-09-16 | 2015-08-05 | 眼验有限责任公司 | Biometric template security and key generation |
| CN103716309A (en) * | 2013-12-17 | 2014-04-09 | 华为技术有限公司 | Security authentication method and terminal |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN107196765A (en) * | 2017-07-19 | 2017-09-22 | 武汉大学 | A kind of remote biometric characteristic identity authentication method for strengthening secret protection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107818301A (en) | 2018-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107818301B (en) | Method and device for updating biological characteristic template and electronic equipment | |
| CN109544166B (en) | Risk identification method and risk identification device | |
| CN109190539B (en) | Face recognition method and device | |
| CN108280332B (en) | Biological characteristic authentication, identification and detection method, device and equipment of mobile terminal | |
| CN109086975B (en) | Transaction risk identification method and device | |
| CN109086734B (en) | Method and device for positioning pupil image in human eye image | |
| CN111353850B (en) | Risk identification strategy updating method and device and risk merchant identification method and device | |
| CN107491674B (en) | Method and device for user authentication based on characteristic information | |
| CN110020581B (en) | Comparison method and device based on multi-frame face images and electronic equipment | |
| CN110874650B (en) | Alliance learning method, device and system fusing public domain data and private data | |
| CN112395612A (en) | Malicious file detection method and device, electronic equipment and storage medium | |
| CN110032931B (en) | Method and device for generating countermeasure network training and removing reticulation and electronic equipment | |
| CN105790948B (en) | A kind of identity identifying method and device | |
| CN108875549B (en) | Image recognition method, device, system and computer storage medium | |
| CN113497807A (en) | Method and device for detecting user login risk and computer readable storage medium | |
| CN110781153B (en) | Cross-application information sharing method and system based on block chain | |
| CN110222790B (en) | User identity identification method and device and server | |
| TWI697860B (en) | Information sharing method, device and electronic equipment | |
| CN106250755B (en) | Method and device for generating verification code | |
| CN110874647A (en) | Private data evaluation and league learning method, device and system in league learning | |
| CN112488138A (en) | User category identification method and device, electronic equipment and storage medium | |
| US10902106B2 (en) | Authentication and authentication mode determination method, apparatus, and electronic device | |
| CN110895691A (en) | Image processing method and device and electronic equipment | |
| CN112418189B (en) | Face recognition method, device and equipment for wearing mask and storage medium | |
| CN115004245A (en) | Target detection method, target detection device, electronic equipment and computer storage 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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1249789 Country of ref document: HK |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200921 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200921 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |