CN115512122A

Movatterモバイル変換

Info

Publication number: CN115512122A
Application number: CN202211179371.1A
Authority: CN
Inventors: 郭明宇
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-01-26
Filing date: 2021-01-26
Publication date: 2022-12-23
Also published as: CN112818798B; CN112818798A

Abstract

One or more embodiments of the specification disclose an identity authentication method and apparatus. The method comprises the following steps: and responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user, wherein the identity authentication request carries identity identification information of the user. And acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by the user. And matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

Description

Identity verification method and device

The present application is a divisional application of an invention patent application with an application number of 2021.01.26 and an application number of 202110102536.4 entitled "authentication method and apparatus".

Technical Field

The present disclosure relates to the field of information security technologies, and in particular, to an identity authentication method and apparatus.

Background

The biometric identification and body verification methods such as face and iris identification based on computer vision have the advantages of high speed, high safety and the like, and are popularized in various identity identification scenes. Most of the current face recognition technologies are based on 2D (i.e. two-dimensional) face recognition, or comprehensively recognize 2D faces mainly and other schemes (such as 3D faces) secondarily. The popularization of face recognition makes people have higher requirements on the safety of a face recognition system. However, no matter 2D face recognition is adopted, other technologies are adopted mainly with 2D faces as an auxiliary, or other biometric verification methods are adopted, the privacy protection of the user has inherent defects, and the user privacy is easily leaked.

Therefore, it is desirable to provide a personal authentication method that can effectively protect the privacy of the user.

Disclosure of Invention

In one aspect, one or more embodiments of the present specification provide an identity verification method, including: and responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user, wherein the identity authentication request carries identity identification information of the user. And acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by the user. And matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

In another aspect, one or more embodiments of the present specification provide an authentication apparatus, including: the first obtaining module is used for responding to an identity verification request aiming at a user and obtaining an image to be verified, wherein the image to be verified is shot by the user, and the identity verification request carries identity identification information of the user. And the second acquisition module is used for acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by the user. And the verification module is used for matching the first image characteristic with the reference image characteristic and verifying the identity of the user according to a matching result.

In yet another aspect, one or more embodiments herein provide an authentication apparatus comprising a processor and a memory electrically connected to the processor, the memory storing a computer program, the processor being configured to invoke and execute the computer program from the memory to implement: and responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user, wherein the identity authentication request carries identity identification information of the user. And acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by the user. And matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

In another aspect, the present specification provides a storage medium for storing a computer program, where the computer program is executable by a processor to implement the following processes: and responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user, wherein the identity authentication request carries identity identification information of the user. And acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by the user. And matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

Drawings

In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the description below are only some of the embodiments described in one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort.

FIG. 1 is a schematic flow chart diagram of a method of identity verification according to an embodiment of the present description;

FIG. 2 is a schematic flow chart diagram of a user registration process in an authentication method according to an embodiment of the present description;

FIG. 3 is a schematic corresponding diagram of a reference image and reference image features in a method of identity verification according to an embodiment of the present description;

FIG. 4 is a schematic swim lane diagram of a method of identity verification according to an embodiment of the present description;

FIG. 5 is a schematic block diagram of an authentication device in accordance with an embodiment of the present description;

fig. 6 is a schematic block diagram of an authentication apparatus according to an embodiment of the present specification.

Detailed Description

One or more embodiments of the present specification provide an identity authentication method and apparatus, so as to solve a problem that a user privacy is easily revealed in an existing authentication method.

In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments of the present disclosure without making any creative effort shall fall within the protection scope of one or more of the embodiments of the present disclosure.

Fig. 1 is a schematic flow chart of an authentication method according to an embodiment of the present specification, as shown in fig. 1, the method including:

s102, responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user, wherein the identity authentication request carries identity identification information of the user.

Wherein the authentication request may be initiated actively by the user. Alternatively, the user may initiate an authentication request by triggering a specified authentication option. After the identity authentication equipment receives an identity authentication request initiated by a user, a camera on the equipment is started so that the user can shoot an image to be authenticated through the camera. The image to be verified can be an image of any object with identification, such as a watch, a cup, a cover of a book, etc. of the user.

The identification information of the user can be information such as an identification number, a mobile phone number, an account name, a nickname and the like, and the user needs to input the identification information when initiating an authentication request. The identification information should be consistent with the identification information that the user has registered in advance.

S104, acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information, wherein the reference image characteristic is extracted based on a reference image pre-shot by a user.

The reference image may be an image of any object with identification, such as a watch, a cup, a cover of a book, and the like of a user. When the user registers the reference image features in advance, one or more reference images can be selected according to personal preference or requirements, namely, the reference images have the characteristics of arbitrariness, uniqueness and difficulty in being known by others.

And S106, matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

By adopting the technical scheme of one or more embodiments of the specification, when an identity authentication request of a user is received, the first image feature corresponding to the image to be authenticated and the reference image feature corresponding to the identity identification information of the user are matched by acquiring the image to be authenticated shot by the user, and the identity of the user is authenticated according to the matching result. The reference image features are extracted from the reference image shot by the user in advance, so that the reference image features are unique compared with other users, and the purpose of authenticating the user can be accurately achieved. Moreover, the reference image corresponding to the reference image feature can be selected at will and is not limited to the information of the user, so that the technical scheme does not need to acquire information (such as biological feature information) related to the privacy of the user in the authentication process of the user, and the privacy information of the user is effectively protected while the purpose of authentication is achieved.

In one embodiment, the user is registered with the reference image feature in advance before the user is authenticated. Optionally, the reference image feature is registered according to the following steps:

firstly, identity identification information of a user and a first reference image shot by the user are obtained based on an identity registration request initiated by the user.

The first reference image may be an image of any object with identification, such as a watch, a cup, a cover of a book, and the like of a user. The user can select one or more first reference images according to personal preference or requirements, namely, the first reference images have the characteristics of arbitrariness, uniqueness and difficulty in being known by others.

After receiving an identity registration request initiated by a user, an input entry of identity identification information and a shooting channel of the first reference image can be provided for the user. Wherein, the input entry of the identification information can be a display frame on the registration interface. The shooting channel of the first reference image may be a camera, for example, which is started after receiving the identity registration request. The identification information and the first reference image may be acquired simultaneously or sequentially, which is not limited in this embodiment.

Next, image features corresponding to the first reference image are extracted.

Thirdly, determining the reference image characteristics according to the image characteristics corresponding to the first reference image, and associating and storing the identification information of the user and the reference image characteristics.

If the first reference image only comprises one image, the image feature of the first reference image can be directly extracted as the reference image feature. If the first reference image comprises a plurality of images, the reference image features comprise a plurality of reference image feature segments, firstly, the image features of the first reference images are respectively extracted, and the image features corresponding to the first reference images are combined as the reference image feature segments according to the shooting sequence of the first reference images to obtain the reference image features. The reference image feature segments may be combined into a sequence form or a set form, so that the reference image features are obtained by the combination.

For example, if the first reference image includes image a and image B, the image feature of image a is F1, and the image feature of image B is F2, the reference image feature may be represented as [ F1, F2], where F1 and F2 are both reference image feature segments.

After the identification information of the user and the reference image feature are stored in an associated manner, it is equivalent to that the user successfully registers the corresponding reference image feature, that is, identity registration is completed.

In this embodiment, the reference image feature is obtained based on a first reference image captured by a user in advance, and the user can arbitrarily select the first reference image, so that the first reference image has uniqueness. And the reference image characteristics corresponding to the user have uniqueness, and the user identity authentication process is carried out based on the reference image characteristics, so that the user identity authentication result is more accurate. Moreover, the first reference image is not limited to the information of the user, so that information (such as biological characteristic information) related to the privacy of the user does not need to be acquired in the authentication process of the user, and the privacy information of the user is effectively protected while the purpose of authentication is achieved.

In one embodiment, when the user registers the reference image feature, the registration may be performed by taking the reference image a plurality of times in order to ensure the accuracy of the reference image feature. Alternatively, the registration of the reference image feature may be performed as in steps S201 to S205 shown in fig. 2.

S201, acquiring identity identification information of a user and a first reference image shot by the user based on an identity registration request initiated by the user.

Optionally, after the first reference image is acquired, quality verification may be performed on the first reference image to determine whether the first reference image meets a preset reference image condition, and if yes, the subsequent steps are further performed; if the first reference image does not meet the reference image condition, prompt information that the first reference image does not meet the reference image condition can be output to prompt the user to shoot the first reference image again.

Wherein the reference image condition may include at least one of: the first reference image is different from reference images corresponding to other users, the definition of the first reference image reaches a preset definition threshold, the first reference image comprises at least one target object, and the number of color types in the first reference image is larger than or equal to a third preset threshold.

And S202, extracting image features corresponding to the first reference image.

After the image features corresponding to the first reference image are extracted, the user can be prompted to shoot a second reference image in a mode of starting the camera again. For example, after the image feature corresponding to the first reference image is extracted, the camera is started, and "please shoot the reference image again" is displayed at the designated position of the current interface (i.e., the registration interface).

And S203, acquiring a second reference image shot by the user, and extracting image features corresponding to the second reference image.

And S204, matching the image features corresponding to the second reference image with the image features corresponding to the first reference image to determine a first matching degree between the image features corresponding to the second reference image and the image features corresponding to the first reference image.

S205, judging whether the first matching degree is larger than or equal to a first preset threshold value; if yes, go to S206; if not, S203 is executed.

In this step, if the first matching degree is smaller than the first preset threshold, it indicates that the difference between the reference images shot by the user twice is large, and the reference image cannot be determined, and at this time, the user may be prompted to shoot the second reference image again. In addition, if the user shoots the second reference image for multiple times and the first matching degrees between the image characteristics of the second reference image shot for multiple times and the image characteristics corresponding to the first reference image are all smaller than a first preset threshold value, prompt information for prompting the user that the registration fails can be sent out.

The first preset threshold may be set to a larger value to ensure that the reference image features are successfully registered for the user only when the image features respectively corresponding to the first reference image and the second reference image captured by the user have a higher matching degree.

And S206, determining the image characteristic corresponding to the first reference image and/or the image characteristic corresponding to the second reference image as the reference image characteristic.

In this embodiment, if the first reference image and the second reference image have only one image, the image feature corresponding to the second reference image is the image feature extracted from the second reference image, and the image feature corresponding to the first reference image is the image feature extracted from the first reference image. In step S204, a first matching degree may be determined by matching the image features extracted from the second reference image with the image features extracted from the first reference image.

If the first reference image and the second reference image both comprise a plurality of images, the image feature corresponding to the second reference image may be obtained as follows: and respectively extracting image features from the plurality of second reference images, then combining the extracted image features according to the shooting sequence of each second reference image, and combining the image features into a sequence form or a set form to obtain the image features corresponding to the second reference images. Similarly, the image feature corresponding to the first reference image may be obtained as follows: the image features are extracted from the plurality of first reference images respectively, then the extracted image features are combined according to the shooting sequence of each first reference image, the image features can be combined into a sequence form or a set form, and the image features corresponding to the first reference images are obtained after combination. In step S204, the image features corresponding to the first reference image and the image features corresponding to the second reference image that are combined in a sequence form or an aggregate form by matching may be used to determine the first matching degree.

Image features that are combined into a sequence may be referred to as a sequence of image features. When a plurality of image feature sequences are matched, whether the feature lengths corresponding to the image feature sequences are the same or not can be judged, if yes, the similarity between the image feature sequences is further calculated, and the similarity is the first matching degree between the image feature sequences. The similarity between the image feature sequences can be calculated by using the existing similarity calculation algorithm, which is not described herein again.

The image features combined into a set form may be referred to as an image feature set, and each element in the image feature set corresponds to an image feature of each reference image. When a plurality of image feature sets are matched, whether the feature lengths corresponding to the image feature sets are the same or not can be judged firstly, if yes, the similarity between corresponding elements in the image feature sets is further calculated in sequence according to the sequence of the elements in the image feature sets to obtain a plurality of similarities, and then the first matching degree between the image feature sets is determined according to the similarities. Alternatively, the average of the plurality of similarities may be calculated as the first matching degree.

In one embodiment, when a plurality of image feature sets are matched, the similarity between corresponding elements in each image feature set is sequentially calculated according to the sequence of each element in the image feature set, so as to obtain a plurality of similarities. And then determining the number of the similarities reaching a preset similarity threshold in the plurality of similarities, and if the number of the similarities is greater than or equal to a certain preset threshold, determining that the plurality of image feature sets are matched, further determining that the reference images shot by the user for multiple times are consistent, and registering the reference image features for the user.

Assuming that the image feature set corresponding to the first reference image is represented as [ F1, F2, F3], and the image feature set corresponding to the second reference image is represented as [ F1, F2, F3], when the two image feature sets are matched, the similarity of F1 and F1, the similarity of F2 and F2, and the similarity of F3 and F3 can be respectively calculated to obtain three similarity values, and then the number of similarities reaching a preset similarity threshold value in the three similarities is determined, if the number of similarities is greater than or equal to a preset threshold value, it is determined that the image feature set corresponding to the first reference image is matched with the image feature set corresponding to the second reference image, it is further determined that the first reference image and the second reference image photographed by the user are consistent, a reference image feature can be registered for the user, and the image feature set [ F1, F2, F3] is determined as the reference image feature.

Fig. 3 schematically shows a correspondence between a reference image and a reference image feature. As shown in fig. 3, the reference image includes 3 images, which are respectively a rabbit plush toy, a water cup, and a watch, and the reference image feature is an image feature sequence or an image feature set formed by combining image features respectively corresponding to the 3 reference images. It can be seen that due to the arbitrary selectivity of the reference image, the reference image feature registered by each user has uniqueness, and accurate basis can be provided for identity verification.

In one embodiment, in the case that the reference image includes a plurality of images, the image to be verified should also include a plurality of images, and the first image feature corresponding to the image to be verified includes a plurality of first image feature segments. When the first image features corresponding to the images to be verified are obtained, the image features corresponding to the images to be verified can be respectively extracted, and then the extracted image features are combined as first image feature segments according to the shooting sequence of the images to be verified, so that the first image features corresponding to the images to be verified are obtained.

In this embodiment, the first image feature corresponding to the image to be verified and the reference image feature are matched, so that when the user is authenticated according to the matching result, whether the feature lengths corresponding to the first image feature and the reference image feature are the same or not can be firstly judged; if the first image characteristic and the reference image characteristic are the same, further judging whether the first image characteristic and the reference image characteristic are matched, and carrying out identity verification on the user according to a judgment result; and if not, determining that the authentication of the user is not passed.

Under the condition that the feature lengths corresponding to the first image features and the reference image features are the same, respectively determining second matching degrees between each first image feature segment and the corresponding reference image feature segment, respectively judging whether each second matching degree is greater than or equal to a second preset threshold value, and if the number of the second matching degrees greater than or equal to the second preset threshold value reaches a preset expected number, determining that the identity verification of the user passes. Otherwise, if the number of the second matching degrees which are greater than or equal to the second preset threshold value does not reach the preset expected number, the identity authentication of the user is determined to be failed.

In the above embodiment, by first determining whether the feature lengths corresponding to the first image feature and the reference image feature are the same, and then determining the second matching degrees between each first image feature segment and the corresponding reference image feature segment under the condition that the feature lengths are determined to be the same, and performing the identity authentication on the user according to the values of each second matching degree, the dual authentication manner greatly improves the accuracy of the identity authentication of the user.

In one embodiment, if it is determined that the authentication of the user is not passed, a factor causing the authentication to be failed may be further determined, and a corresponding prompt message may be output based on the factor.

Wherein the factor causing the authentication to fail may include at least one of: the image to be verified is different from the reference image, the shooting sequence of the image to be verified is wrong, the first image characteristic is not matched with the reference image characteristic, and the like. Based on this, the output prompt information can correspondingly comprise at least one of the following items: the image to be verified is different from the reference image, the shooting sequence of the image to be verified is wrong, the first image characteristic is not matched with the reference image characteristic, and the like.

In the embodiment, under the condition that the user fails in authentication, the factor causing the failure of the authentication is determined, and the prompt information is output to the user based on the factor, so that the user can know the reason why the authentication fails based on the prompt information, and further, the image to be authenticated is shot again in a targeted manner, and the experience of the user in authentication is improved.

In one embodiment, after the user successfully registers the reference image feature, the first reference image and/or the second reference image may be determined to be the reference image corresponding to the user, and the identification information of the user and the reference image may be stored in association with each other. The reference image and the reference image feature need to correspond to each other, for example, if the image feature corresponding to the first reference image is determined to be the reference image feature, the first reference image is determined to be the reference image corresponding to the user. And if the image characteristic corresponding to the second reference image is determined to be the reference image characteristic, determining the second reference image to be the reference image corresponding to the user.

In this embodiment, the device for authenticating the user stores the identification information of the user and the reference image in association with each other. In this way, in some special cases, such as the case that the device needs to be updated or replaced, the storage location is changed, etc., the image features in the reference image can be re-extracted to determine the reference image features based on the reference image stored in the device, without the need for the user to re-capture and register the reference image.

In one embodiment, after storing the identification information of the user and the reference image feature in association, if an update request of the user for the reference image feature is received, based on the update request, a third reference image captured by the user may be received, the image feature corresponding to the third reference image may be extracted, and the reference image feature may be updated by using the image feature corresponding to the third reference image.

The updating request carries the identity identification information of the user, the reference image feature corresponding to the identity identification information can be determined based on the identity identification information of the updating request, and then the reference image feature is updated by using the image feature corresponding to the third reference image.

In this embodiment, a user can update the reference image features stored in the device at any time according to a requirement, so that the reference image features have dynamic updating performance, rather than being unchanged, thereby enhancing the security of the reference image features and avoiding the loss of the user caused by the fact that other people acquire the reference image features.

Fig. 4 is a schematic swim lane diagram of an authentication method according to an embodiment of the present specification, which is applied to an interaction between a user and an authentication device, as shown in fig. 4, and includes the following steps:

s1.1, a user initiates an identity registration request. The identity registration request contains identity information of the user.

S1.2, the identity authentication equipment starts a camera.

S1.3, shooting a plurality of reference images by a user.

And S1.4, the identity verification equipment extracts the image features of the reference images and combines the image features according to the shooting sequence corresponding to the reference images so as to obtain the reference image features through combination.

When the step is executed, the identity verification device may also perform accuracy verification on the reference image shot by the user in a manner shown in fig. 2, that is, by acquiring the reference image shot by the user multiple times, matching image features corresponding to the reference image acquired multiple times, and when it is determined that the image features corresponding to the reference image acquired multiple times are matched, determining the reference image feature. The verification process for the reference image has been described in detail in the above embodiments, and therefore, will not be described in detail herein.

S1.5, the identity authentication equipment stores the identity identification information of the user and the reference image characteristics in an associated mode.

By executing S1.1-S1.5, the user interacts with the identity verification device, and the identity registration process is completed.

S2.1, the user initiates an identity authentication request. The identity registration request contains identity information of the user.

And S2.2, starting a camera by the identity authentication equipment.

And S2.3, shooting a plurality of images to be verified by the user.

And S2.4, the identity authentication equipment extracts the image characteristics of the images to be authenticated, and combines the image characteristics according to the shooting sequence corresponding to the images to be authenticated, so that the first image characteristics corresponding to the images to be authenticated are obtained through combination.

And S2.5, the identity authentication equipment verifies the characteristic lengths corresponding to the first image characteristic and the reference image characteristic respectively.

In this step, the feature length is verified, specifically, it is determined whether the feature lengths corresponding to the first image feature and the reference image feature are the same. If the feature lengths corresponding to the first image feature and the reference image feature are the same, S2.6 is further performed. And under the condition that the characteristic lengths corresponding to the first image characteristic and the reference image characteristic are not consistent, prompt information of failed verification can be output.

And S2.6, the identity authentication equipment matches the first image feature with the reference image feature and authenticates the identity of the user according to the matching result.

In this step, the identity verification device may match the first image feature with the corresponding image feature segment in the reference image feature, for example, calculate the matching between the first image feature and the corresponding image feature segment in the reference image feature, respectively, to obtain a plurality of matching degrees. In the plurality of matching degrees, if the number of matching degrees greater than or equal to a certain preset threshold reaches a preset expected number, it is determined that the first image feature and the reference image feature are matched with each other. Otherwise, a mismatch between the first image feature and the reference image feature is determined. The determination method of the matching degree between the first image feature and the reference image feature has been described in detail in the above embodiments, and is not described herein again.

And S2.7, the authentication equipment outputs an authentication result to the user.

In this embodiment, since the reference image feature is extracted from the reference image previously captured by the user, the reference image feature is unique compared with other users, and the purpose of authenticating the user can be accurately achieved. Moreover, the reference image corresponding to the reference image feature can be selected at will and is not limited to the information of the user, so that the technical scheme does not need to acquire information (such as biological feature information) related to the privacy of the user in the authentication process of the user, and the privacy information of the user is effectively protected while the purpose of authentication is achieved.

In summary, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.

Based on the same idea, the identity authentication method provided in one or more embodiments of the present specification further provides an identity authentication device.

Fig. 5 is a schematic block diagram of an authentication apparatus according to an embodiment of the present specification, as shown in fig. 5, the apparatus including:

a first obtainingmodule 510, configured to obtain an image to be verified, which is captured by a user, in response to an authentication request for the user; the identity authentication request carries identity identification information of the user;

a second obtainingmodule 520, configured to obtain a first image feature corresponding to the image to be verified and a pre-stored reference image feature corresponding to the identity information; the reference image features are extracted based on a reference image shot by the user in advance;

and theverification module 530 matches the first image feature with the reference image feature and verifies the identity of the user according to a matching result.

In one embodiment, the apparatus further comprises:

the third acquisition module is used for acquiring the identity identification information of the user and the first reference image shot by the user based on an identity registration request initiated by the user before the authentication request for the user is responded and the image to be authenticated shot by the user is acquired;

the first extraction module is used for extracting image features corresponding to the first reference image;

and the determining and storing module is used for determining the reference image characteristics according to the image characteristics corresponding to the first reference image, and storing the identification information of the user and the reference image characteristics in an associated manner.

In one embodiment, the apparatus further comprises:

a fourth obtaining module, configured to obtain a second reference image captured by the user after the image feature corresponding to the first reference image is extracted;

the second extraction module is used for extracting image features corresponding to the second reference image;

the matching module is used for matching the image features corresponding to the second reference image with the image features corresponding to the first reference image so as to determine a first matching degree between the image features corresponding to the second reference image and the image features corresponding to the first reference image;

the determining and storing module comprises:

and a first determining unit configured to determine, if the first matching degree is greater than or equal to a first preset threshold, that the image feature corresponding to the first reference image and/or the image feature corresponding to the second reference image is the reference image feature.

In one embodiment, the first reference image includes a plurality; the reference image feature comprises a plurality of reference image feature segments;

the determining and storing module comprises:

and a first combining unit configured to combine, as the reference image feature segment, the image features corresponding to the respective first reference images in the order of capturing the respective first reference images, to obtain the reference image features.

In one embodiment, the image to be verified comprises a plurality of images; the first image feature comprises a plurality of first image feature segments;

the second acquisition module includes:

the first extraction unit is used for respectively extracting image characteristics corresponding to the images to be verified;

the second combination unit is used for combining the extracted image characteristics as the first image characteristic segments according to the shooting sequence of the images to be verified to obtain the first image characteristics;

theauthentication module 530 includes:

a determination unit configured to determine whether feature lengths corresponding to the first image feature and the reference image feature are the same;

the verification unit judges whether the first image feature is matched with the reference image feature if the first image feature is matched with the reference image feature, and performs identity verification on the user according to a judgment result; if not, determining that the user identity authentication is not passed.

In one embodiment, the verification unit determines a second matching degree between each first image feature segment and the corresponding reference image feature segment; respectively judging whether each second matching degree is greater than or equal to a second preset threshold value; and if the number of the second matching degrees which are greater than or equal to the second preset threshold reaches a preset expected number, determining that the identity authentication of the user passes.

In one embodiment, the apparatus further comprises:

the judging module is used for judging whether the first reference image meets a preset reference image condition or not before the image feature corresponding to the first reference image is extracted;

the execution module is used for extracting the image characteristics corresponding to the first reference image if the first reference image is the first reference image;

the first output module outputs first prompt information that the first reference image does not accord with the reference image condition if the first reference image does not accord with the reference image condition;

wherein the reference image condition comprises at least one of: the first reference image is different from reference images corresponding to other users, the definition of the first reference image reaches a preset definition threshold, the first reference image comprises at least one target object, and the number of color types in the first reference image is larger than or equal to a third preset threshold.

In one embodiment, the apparatus further comprises:

the first determining module is used for determining a factor causing the failure of the identity authentication if the identity authentication of the user is determined to be failed after the first image feature is matched with the reference image feature and the identity authentication of the user is performed according to a matching result;

the second output module outputs corresponding second prompt information based on the factors; the second prompt message includes at least one of: the image to be verified is different from the reference image, the shooting sequence of the image to be verified is wrong, and the first image characteristic is not matched with the reference image characteristic.

In one embodiment, the apparatus further comprises:

a second determining module that determines the first reference image and/or the second reference image as the reference image corresponding to the user;

and the storage module is used for storing the identification information of the user and the reference image in a correlated manner.

In one embodiment, the apparatus further comprises:

the receiving module is used for receiving a third reference image shot by the user when receiving an updating request of the user for the reference image characteristics after the identification information of the user and the reference image characteristics are stored in the association manner; the update request carries the identity information of the user;

the third extraction module is used for extracting image features corresponding to the third reference image;

the determining and updating module is used for determining the reference image characteristics corresponding to the identity identification information; and updating the reference image feature by using the image feature corresponding to the third reference image.

It should be understood by those skilled in the art that the above-mentioned authentication apparatus can be used to implement the above-mentioned authentication method, and the detailed description thereof should be similar to the above-mentioned method, and therefore, in order to avoid complexity, it is not repeated herein.

By adopting the device in one or more embodiments of the specification, when an identity authentication request of a user is received, the first image feature corresponding to the image to be authenticated and the reference image feature corresponding to the identity identification information of the user are obtained by obtaining the image to be authenticated shot by the user, and then the first image feature corresponding to the image to be authenticated and the reference image feature are matched, and the identity authentication of the user is performed according to the matching result. The reference image features are extracted from the reference image shot by the user in advance, so that the reference image features are unique compared with other users, and the purpose of authenticating the user can be accurately achieved. Moreover, the reference image corresponding to the reference image characteristic can be selected at will and is not limited to the information of the user, so that the device does not need to acquire information (such as biological characteristic information) related to the user privacy in the authentication process of the user, and the privacy information of the user is effectively protected while the purpose of authentication is achieved.

Along the same lines, one or more embodiments of the present specification also provide an authentication device, as shown in fig. 6. The authentication devices may vary greatly in configuration or performance and may include one ormore processors 601 andmemory 602, where one or more stored applications or data may be stored inmemory 602. Wherein thememory 602 may be transient or persistent storage. The application program stored inmemory 602 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the identity verification device. Still further, theprocessor 601 may be arranged in communication with thememory 602 to execute a series of computer executable instructions in thememory 602 on the authentication device. The authentication apparatus may also include one ormore power supplies 603, one or more wired or wireless network interfaces 604, one or more input-output interfaces 605, one ormore keyboards 606.

In particular, in this embodiment, the authentication apparatus comprises a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may comprise one or more modules, and each module may comprise a series of computer-executable instructions for the authentication apparatus, and the one or more programs configured to be executed by the one or more processors comprise computer-executable instructions for:

responding to an identity authentication request aiming at a user, and acquiring an image to be authenticated shot by the user; the identity authentication request carries identity identification information of the user;

acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information; the reference image features are extracted based on a reference image shot by the user in advance;

and matching the first image characteristic with the reference image characteristic, and performing identity verification on the user according to a matching result.

One or more embodiments of the present specification further provide a storage medium, where the storage medium stores one or more computer programs, where the one or more computer programs include instructions, and when the instructions are executed by an electronic device that includes multiple application programs, the electronic device can execute each process of the foregoing embodiment of the identity verification method, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.

The systems, apparatuses, modules or units described in the above embodiments may be specifically implemented by a computer chip or an entity, or implemented 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.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more pieces of software and/or hardware in implementing one or more embodiments of the present description.

One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

One or more embodiments of the present specification are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

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 Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which 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 phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

All 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 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.

The above description is only one or more embodiments of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of one or more embodiments of the present specification.

Claims

1. An identity verification method comprising:

acquiring a first image characteristic corresponding to the image to be verified and a pre-stored reference image characteristic corresponding to the identity identification information; the reference image features are extracted based on a reference image acquired by the user in advance; the reference image is an image of an object with identification degree;

2. The method according to claim 1, before acquiring the image to be authenticated taken by the user in response to the authentication request for the user, further comprising:

acquiring identity identification information of the user and a first reference image shot by the user based on an identity registration request initiated by the user;

extracting image features corresponding to the first reference image;

and determining the reference image characteristics according to the image characteristics corresponding to the first reference image, and storing the identification information of the user and the reference image characteristics in an associated manner.

3. The method according to claim 2, further comprising, after extracting the image feature corresponding to the first reference image:

acquiring a second reference image shot by the user;

extracting image features corresponding to the second reference image;

matching the image features corresponding to the second reference image with the image features corresponding to the first reference image to determine a first matching degree between the image features corresponding to the second reference image and the image features corresponding to the first reference image;

the determining the reference image feature according to the image feature corresponding to the first reference image includes:

if the first matching degree is larger than or equal to a first preset threshold value, determining the image feature corresponding to the first reference image and/or the image feature corresponding to the second reference image as the reference image feature.

4. The method of claim 2, the first reference image comprising a plurality; the reference image feature comprises a plurality of reference image feature segments;

and combining the image features corresponding to the first reference images as the reference image feature segments according to the shooting sequence of the first reference images to obtain the reference image features.

5. The method of claim 4, wherein the image to be verified comprises a plurality; the first image feature comprises a plurality of first image feature segments;

the obtaining of the first image feature corresponding to the image to be verified includes:

respectively extracting image characteristics corresponding to the images to be verified;

combining the extracted image features as the first image feature segments according to the shooting sequence of the images to be verified to obtain the first image features;

the matching the first image feature and the reference image feature, and performing identity verification on the user according to a matching result includes:

judging whether the feature lengths corresponding to the first image feature and the reference image feature are the same or not;

if yes, judging whether the first image characteristic is matched with the reference image characteristic, and carrying out identity verification on the user according to a judgment result; if not, determining that the user identity authentication is not passed.

6. The method of claim 5, wherein said determining whether the first image feature matches the reference image feature and authenticating the user according to the determination comprises:

respectively determining second matching degrees between each first image feature segment and the corresponding reference image feature segment;

respectively judging whether each second matching degree is greater than or equal to a second preset threshold value;

and if the number of the second matching degrees which are greater than or equal to the second preset threshold reaches a preset expected number, determining that the identity authentication of the user passes.

7. The method of claim 2, wherein before extracting the image feature corresponding to the first reference image, the method further comprises:

judging whether the first reference image meets a preset reference image condition or not;

if yes, executing a step of extracting image features corresponding to the first reference image;

if not, outputting first prompt information that the first reference image does not accord with the reference image condition;

8. The method of claim 1, after matching the first image feature with the reference image feature and authenticating the user according to the matching result, further comprising:

if the authentication of the user is determined to be not passed, determining factors causing the authentication to be not passed;

outputting corresponding second prompt information based on the factors; the second prompt message includes at least one of: the image to be verified is different from the reference image, the shooting sequence of the image to be verified is wrong, and the first image characteristic is not matched with the reference image characteristic.

9. The method of claim 3, further comprising:

determining the first reference image and/or the second reference image as the reference image corresponding to the user;

and storing the identification information of the user and the reference image in an associated manner.

10. The method of claim 2, after the associating stores the identification information of the user and the reference image feature, further comprising:

when an updating request of the user for the reference image features is received, receiving a third reference image shot by the user; the update request carries the identity information of the user;

extracting image features corresponding to the third reference image;

determining the reference image characteristics corresponding to the identity identification information; and updating the reference image feature by using the image feature corresponding to the third reference image.

11. An authentication apparatus comprising:

the first acquisition module is used for responding to an identity authentication request aiming at a user and acquiring an image to be authenticated, which is shot by the user; the identity authentication request carries identity identification information of the user;

the second acquisition module is used for acquiring the first image characteristics corresponding to the image to be verified and the prestored reference image characteristics corresponding to the identity identification information; the reference image features are extracted based on a reference image acquired by the user in advance; the reference image is an image of an object with identification degree;

and the verification module is used for matching the first image characteristic with the reference image characteristic and verifying the identity of the user according to a matching result.

12. The apparatus of claim 11, further comprising:

the third acquisition module is used for acquiring the identity identification information of the user and the first reference image shot by the user based on an identity registration request initiated by the user before the image to be verified shot by the user is acquired in response to the identity verification request of the user;

13. The apparatus of claim 12, the first reference image comprising a plurality; the reference image feature comprises a plurality of reference image feature segments;

the determining and storing module comprises:

14. The apparatus of claim 13, the image to be authenticated comprising a plurality; the first image feature comprises a plurality of first image feature segments;

the second acquisition module includes:

the second combination unit is used for combining the extracted image features as the first image feature segments according to the shooting sequence of the images to be verified to obtain the first image features;

the authentication module includes:

a verification unit, which judges whether the first image feature is matched with the reference image feature if the first image feature is matched with the reference image feature, and performs identity verification on the user according to the judgment result; if not, determining that the user identity authentication is not passed.

15. The apparatus according to claim 14, wherein the verification unit determines a second matching degree between each of the first image feature segments and the corresponding reference image feature segment; respectively judging whether each second matching degree is greater than or equal to a second preset threshold value; and if the number of the second matching degrees which are greater than or equal to the second preset threshold reaches a preset expected number, determining that the identity authentication of the user passes.

16. An identity verification device comprising a processor and a memory electrically connected to the processor, the memory storing a computer program, the processor being operable to invoke and execute the computer program from the memory to implement:

17. A storage medium storing a computer program executable by a processor to implement the following: