CN108694357A - Method, apparatus and computer storage media for In vivo detection - Google Patents

Abstract

Embodiments of the present invention provide a method, device, and computer storage medium for living body detection. The method includes: acquiring input data; using a detection algorithm to perform living body detection on the input data; if the result of the living body detection determines the If the input data is non-living, the input data is automatically marked; and the marked input data is added to the attack sample database. It can be seen that, in the embodiment of the present invention, when the result of the liveness detection is non-living, the input data is marked, and the marked input data is added to the attack sample database, which can realize automatic marking and avoid consuming a lot of manpower, thereby enabling Greatly save labor costs.

Description

Method, device and computer storage medium for living body detection

technical field

The present invention relates to the field of image recognition, and more specifically relates to a method, device and computer storage medium for living body detection.

Background technique

At present, living body detection systems are increasingly used in fields that require identity verification, such as security, finance, and social security. For example, when using face, etc. for identity verification, it is necessary to prevent attacks such as photos and masks.

The detection algorithm adopted by the current living body detection system is obtained through training based on the attack sample database and the biometric sample database, and the attack sample database requires a large amount of manpower to label, which brings a huge human cost.

Contents of the invention

The present invention has been made in consideration of the above-mentioned problems. The invention provides a method, device and computer storage medium for living body detection, which can automatically label input data based on the living body detection results, thereby saving labor costs.

According to a first aspect of the present invention, a method for live detection is provided, comprising:

get input data;

Using a detection algorithm to perform liveness detection on the input data;

If the result of the living body detection determines that the input data is non-living, then automatically label the input data;

Adding the marked input data to the attack sample database.

Exemplarily, the method further includes: if the result of the living body detection determines that the input data is a living body, adding the input data to a biometric sample database.

Exemplarily, the labeling the input data includes: analyzing the input data, and labeling according to a result of the analysis.

Exemplarily, the result of the analysis is the attack type to which the input data belongs, and the analyzing the input data and marking according to the result of the analysis includes: using a classification algorithm to determine the attack type to which the input data belongs attack type, and mark the input data based on the attack type, wherein the classification algorithm is trained from the attack sample database.

Exemplarily, the analyzing the input data and marking according to the analysis result further includes: if the type of attack to which the input data belongs cannot be determined, generating an alarm message, so that the administrator can manually label.

Exemplarily, the method further includes: periodically collecting attack samples, and adding the collected attack samples to the attack sample database.

Exemplarily, the method further includes: performing training according to the added attack sample database and the added biometric sample database to obtain an optimized detection algorithm.

Exemplarily, the method is executed by the cloud.

In a second aspect, a device for living body detection is provided, including:

An acquisition module, used to acquire input data;

A live body detection module, configured to use a detection algorithm to perform live body detection on the input data;

An annotation module, configured to automatically annotate the input data if the result of the liveness detection determines that the input data is non-living;

An adding module, configured to add the marked input data to the attack sample database.

The device can be used to realize the method for living body detection shown in the foregoing first aspect and various examples.

In a third aspect, a device for living body detection is provided, including a memory and a processor, the memory is used to store instruction codes; the processor is used to execute the instruction codes, so as to realize the first aspect and the various examples Methods for liveness detection.

In a fourth aspect, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for living body detection described in the first aspect and various examples is implemented.

It can be seen that, in the embodiment of the present invention, when the result of the liveness detection is non-living, the input data is marked, and the marked input data is added to the attack sample database, which can realize automatic marking and avoid consuming a lot of manpower, thereby enabling Greatly save labor cost

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail with reference to the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute limitations to the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

Fig. 1 is a schematic block diagram of the electronic equipment of the embodiment of the present invention;

FIG. 2 is a schematic flowchart of a method for living body detection according to an embodiment of the present invention;

FIG. 3 is another schematic flowchart of a method for living body detection according to an embodiment of the present invention;

FIG. 4 is a schematic block diagram of a device for living body detection according to an embodiment of the present invention;

Fig. 5 is another schematic block diagram of the device for living body detection according to the embodiment of the present invention.

Detailed ways

In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only some embodiments of the present invention, rather than all embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments described here. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative effort shall fall within the protection scope of the present invention.

Embodiments of the present invention may be applied to electronic devices, and FIG. 1 is a schematic block diagram of an electronic device according to an embodiment of the present invention. The electronic device 10 shown in FIG. 1 includes one or more processors 102, one or more storage devices 104, an input device 106, an output device 108, an image sensor 110, and one or more non-image sensors 114. System 112 and/or other forms of interconnection. It should be noted that the components and structure of the electronic device 10 shown in FIG. 1 are only exemplary rather than limiting, and the electronic device may also have other components and structures as required.

The processor 102 may include a CPU 1021 and a GPU 1022 or other forms of processing units with data processing capabilities and/or instruction execution capabilities, such as Field-Programmable Gate Array (Field-Programmable GateArray, FPGA) or advanced reduced instruction set machine (Advanced RISC (Reduced Instruction Set Computer) Machine, ARM), etc., and the processor 102 can control other components in the electronic device 10 to perform desired functions.

The storage device 104 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory 1041 and/or non-volatile memory 1042 . The volatile memory 1041 may include, for example, a random access memory (Random Access Memory, RAM) and/or a cache memory (cache). The non-volatile memory 1042 may include, for example, a read-only memory (Read-Only Memory, ROM), a hard disk, a flash memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 102 may execute the program instructions to implement various desired functions. Various application programs and various data, such as various data used and/or generated by the application programs, may also be stored in the computer-readable storage medium.

The input device 106 may be a device used by a user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, and a touch screen.

The output device 108 may output various information (such as images or sounds) to the outside (such as a user), and may include one or more of a display, a speaker, and the like.

The image sensor 110 can capture images desired by the user (such as photos, videos, etc.), and store the captured images in the storage device 104 for use by other components.

It should be noted that the components and structure of the electronic device 10 shown in FIG. 1 are only exemplary. Although the electronic device 10 shown in FIG. The number of some devices can be more, etc., and the present invention is not limited to this.

The embodiment of the present invention can also be applied to a server, and the server can be called a cloud or a cloud server. The present invention is not limited thereto.

Fig. 2 is a schematic flow chart of a method for living body detection according to an embodiment of the present invention. The methods shown in Figure 2 include:

S101. Obtain input data.

The input data may be image data or video data, etc. Moreover, the input data includes biometric information, for example, the input data includes a face image and the like.

Exemplarily, the input data may be collected in real time or may be obtained from a user end.

As an example, the method shown in FIG. 2 may be executed by an electronic device. Optionally, the input data may be collected by the electronic device in real time, specifically by an image collection device in real time. For example, the image acquisition device may be a camera or a camera. Optionally, the input data may be obtained by the electronic device from a specific source, for example, a previously collected and stored picture may be obtained from a memory.

As another example, the method shown in FIG. 2 may be executed by a server (or cloud). Optionally, the input data may be acquired by the server from the user end, that is, the input data may be uploaded to the server by the user end. Wherein, the user end may collect input data in real time through an image acquisition device, or the user end may obtain input data from a specific source. Wherein, the user end may be a mobile end where the user is located, such as a smart phone, a tablet computer, and the like.

S102. Using a detection algorithm to perform liveness detection on the input data.

Wherein, the detection algorithm may be obtained through training based on the existing attack sample database and biometric sample database.

Exemplarily, the detection algorithm may be some existing big data-based machine learning methods, for example, a neural network (Neural Network, NN) algorithm, a support vector machine (Support Vector Machine, SVM) and the like.

Taking the neural network algorithm as an example, S102 may input the input data into the neural network to determine whether the input data is a living body.

If the judgment result is yes, that is, the result of the living body detection in S102 determines that the input data is a living body, then the input data is added to the biometric sample database, as shown in FIG. 3 . If the result of the judgment is negative, that is, the result of the living body detection in S102 determines that the input data is non-living (that is, an attack), then execute S103.

S103. If the result of the living body detection determines that the input data is not a living body, automatically mark the input data.

Exemplarily, labeling the input data may include labeling various information such as attributes of the input data (such as: non-living input data) or types (such as attack types, etc.). Wherein, the labeling is automatic labeling, that is, labeling performed by a computer.

Exemplarily, the input data may be analyzed, and marked according to the analysis result.

As an example, a classification algorithm may be used to determine the attack type to which the input data belongs, and to mark the input data based on the attack type. Wherein, the result of the analysis is the attack type to which the input data belongs, and the classification algorithm is obtained by training from the attack sample database.

Wherein, the classification algorithm may also be referred to as an attack type algorithm. Exemplarily, an attack type algorithm may be obtained through training based on an existing attack sample database, and the attack type algorithm may be used to determine the attack type to which the input data belongs. Wherein, the existing attack sample database includes marked attack samples; the attack type algorithm may be a machine learning method based on big data, for example, a neural network algorithm, SVM, and the like.

By way of example, attack types may include paper attacks, mask attacks, screen rip-off attacks, and the like. Wherein, marking the input data based on the attack type may be: marking the input data with the attack type to which it belongs.

Assume that the attack types in the existing attack sample database include attack type A, attack type B, and attack type C. If it is determined by the attack type algorithm that the probability that the input data belongs to attack type A is the highest, then it can be determined that the attack type to which the input data belongs is attack type A.

Exemplarily, if the attack type to which the input data belongs cannot be determined, alarm information is generated, so that managers can manually mark based on the alarm information. For example, if there is a certain gap between the input data and the attack samples of all attack types in the attack sample database (greater than a certain preset threshold), the input data may belong to a new attack type, and an alarm message can be sent to the management personnel at this time . Subsequently, managers can manually verify and label the input data.

Assume that the attack types in the existing attack sample database include attack type A, attack type B, and attack type C. If the absolute value of the difference between the probability P1 of the input data belonging to the attack type A, the probability P2 of the attack type B, and the probability P3 of the attack type C is determined by the attack type algorithm is less than a specific value, or if the probability If P1, probability P2, and probability P3 are all less than a certain preset probability value, it can be determined that the input data belongs to a new attack type.

It can be seen that in the embodiment of the present invention, the input data can be marked according to the existing attack sample database, and only when the attack type of the input data cannot be determined, the manager can manually mark it, which can greatly reduce the Labor costs.

S104. Add the marked input data to the attack sample database.

Then, the marked input data is added to the attack sample database, and the update of the attack sample database can be completed.

Exemplarily, other attack samples may also be collected and added to the attack sample database, for example, attack samples may be collected periodically, and the collected attack samples may be added to the attack sample database. In this way, the collected attack samples are added to the attack sample database, thereby increasing the robustness.

As an example, if the collected attack samples are marked attack samples, the marked attack samples may be added to the attack sample database.

As another example, if the collected attack sample is an unmarked attack sample, the collected attack sample may be marked and then added to the attack sample database.

Exemplarily, after S104, the updated attack sample database may be used for training to obtain an optimized classification algorithm (or attack type algorithm).

Exemplarily, after S104, the updated attack sample database and the updated biometric sample database may be used for training to obtain an optimized detection algorithm.

For example, the classification algorithm (or attack type algorithm) and/or detection algorithm may be optimized regularly. Alternatively, optimization may be performed when the newly added samples in the attack sample database and/or the biometric sample database reach a certain threshold. Alternatively, optimization may be performed when other trigger conditions are fulfilled, which is not limited in the present invention. Wherein, the newly added sample of the attack sample database is the marked input data added to the attack sample database, or the added attack sample; the newly added sample of the biometric sample database is added to the biometric Input data in the sample database.

For example, when the number of marked input data added to the attack sample database reaches a first threshold, and/or, when the number of input data added to the biometric sample database reaches a second threshold, according to The added attack sample database and the added biometric sample database are trained to obtain an optimized detection algorithm.

It can be seen that, in the embodiment of the present invention, when the result of the liveness detection is non-living, the input data is marked, and the marked input data is added to the attack sample database, which can realize automatic marking and avoid consuming a lot of manpower, thereby enabling Greatly save labor costs.

Fig. 4 is a schematic block diagram of a device for living body detection according to an embodiment of the present invention. The device 40 shown in FIG. 4 includes: an acquisition module 401 , a living body detection module 402 , a labeling module 403 and an adding module 404 .

An acquisition module 401, configured to acquire input data;

A live body detection module 402, configured to use a detection algorithm to perform live body detection on the input data acquired by the acquisition module 401;

Labeling module 403, for if the result of liveness detection by the liveness detection module 402 determines that the input data is non-living, then automatically mark the input data;

The adding module 404 is configured to add the input data marked by the marking module 403 to the attack sample database.

Exemplarily, the adding module 404 may also be configured to: add the input data to the biometric sample database if the living body detection module 402 determines that the input data is a living body as a result of the living body detection.

Exemplarily, the labeling module 403 may be specifically configured to: analyze the input data, and perform labeling according to a result of the analysis.

Exemplarily, the result of the analysis is the attack type to which the input data belongs, and the labeling module 403 may be specifically configured to: use a classification algorithm to determine the attack type to which the input data belongs, and classify the input data based on the attack type The data is marked, wherein the classification algorithm is trained from the attack sample database.

Exemplarily, the device 40 may also include a reminder module. If the labeling module 403 cannot determine the type of attack to which the input data belongs, the reminder module can be used to generate alarm information, so as to facilitate manual labeling by managers.

Exemplarily, the device 40 may also include a collection module. The collecting module may be used for: collecting attack samples regularly. Correspondingly, the adding module 404 may also be configured to add the collected attack samples to the attack sample database.

Exemplarily, the apparatus 40 may also include an optimization algorithm module, as shown in FIG. 5 , the optimization algorithm module may be used to: perform training according to the added attack sample database and the added biometric sample database, The optimized detection algorithm is obtained.

Exemplarily, the optimization algorithm module can also be used for training according to the added attack sample database to obtain an optimized attack type algorithm.

Exemplarily, the device 40 shown in FIG. 4 or FIG. 5 is a cloud.

The device 40 shown in FIG. 4 or FIG. 5 can be used to implement the method for living body detection shown in FIG. 2 or FIG. 3 .

In addition, the embodiment of the present invention also provides another device for living body detection. The device may include a processor and a memory, wherein the memory is used to store instruction codes, and when the processor executes the instruction codes, the aforementioned Figure 2 can be realized. Or the method for living body detection shown in FIG. 3 .

In addition, an embodiment of the present invention also provides an electronic device, which may include the apparatus 40 shown in FIG. 4 or FIG. 5 . The electronic device can implement the method for living body detection shown in FIG. 2 or FIG. 3 .

In addition, an embodiment of the present invention also provides a computer storage medium on which a computer program is stored. When the computer program is executed by the processor, the aforementioned method for living body detection shown in FIG. 2 or FIG. 3 can be realized.

It can be seen that, in the embodiment of the present invention, when the result of the liveness detection is non-living, the input data is marked, and the marked input data is added to the attack sample database, which can realize automatic marking and avoid consuming a lot of manpower, thereby enabling Greatly save labor costs.

Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-described example embodiments are exemplary only and are not intended to limit the scope of the invention thereto. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another device, or some features may be omitted, or not implemented.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be understood that in the description of the exemplary embodiments of the invention, in order to streamline the disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure , or in its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the corresponding claims reflect, the inventive point lies in that the corresponding technical problem may be solved by using less than all features of a single disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

It will be appreciated by those skilled in the art that all features disclosed in this specification (including accompanying claims, abstract and drawings) and all features of any method or apparatus so disclosed may be used in any combination, except where the features are mutually exclusive. process or unit. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules in the item analysis device according to the embodiment of the present invention. The present invention can also be implemented as an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

The above is only a specific embodiment of the present invention or a description of the specific embodiment, and the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily Any changes or substitutions that come to mind should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims (18)

1. A method for live detection, characterized in that, comprising: get input data; Using a detection algorithm to perform liveness detection on the input data; If the result of the living body detection determines that the input data is non-living, then automatically label the input data; Adding the marked input data to the attack sample database. 2. The method of claim 1, further comprising: If the result of the living body detection determines that the input data is a living body, then adding the input data to a biometric sample database. 3. The method according to claim 1, wherein said marking said input data comprises: The input data is analyzed, and marked according to the analysis result. 4. The method according to claim 3, wherein the result of the analysis is the attack type to which the input data belongs, The analyzing the input data and labeling according to the analysis result includes: A classification algorithm is used to determine the attack type to which the input data belongs, and the input data is marked based on the attack type, wherein the classification algorithm is obtained by training from the attack sample database. 5. The method according to claim 4, wherein said analyzing said input data, and marking according to the result of said analysis, further comprises: If the type of attack to which the input data belongs cannot be determined, an alarm message is generated to facilitate manual labeling by managers. 6. The method of claim 1, further comprising: Collect attack samples regularly, and add the collected attack samples to the attack sample database. 7. The method according to claim 2 or 6, further comprising: Training is performed according to the added attack sample database and the added biometric sample database to obtain an optimized detection algorithm. 8. The method according to any one of claims 1 to 7, wherein the method is executed by a cloud. 9. A device for living body detection, comprising: An acquisition module, used to acquire input data; A live body detection module, configured to use a detection algorithm to perform live body detection on the input data; An annotation module, configured to automatically annotate the input data if the result of the liveness detection determines that the input data is non-living; An adding module, configured to add the marked input data to the attack sample database. 10. The device according to claim 9, wherein the adding module is further used for: If the result of the living body detection determines that the input data is a living body, then adding the input data to a biometric sample database. 11. The device according to claim 9, wherein the labeling module is specifically used for: The input data is analyzed, and marked according to the analysis result. 12. The device according to claim 11, wherein the result of the analysis is the attack type to which the input data belongs, and the labeling module is specifically used for: A classification algorithm is used to determine the attack type to which the input data belongs, and the input data is marked based on the attack type, wherein the classification algorithm is obtained by training from the attack sample database. 13. The device according to claim 12, further comprising a reminder module for: If the labeling module cannot determine the attack type to which the input data belongs, an alarm message is generated, so that managers can manually label. 14. The device according to claim 9, further comprising an acquisition module for: Regularly collect attack samples; The adding module is further configured to add the collected attack samples to the attack sample database. 15. The device according to claim 10 or 14, further comprising an optimization algorithm module for: Training is performed according to the added attack sample database and the added biometric sample database to obtain an optimized detection algorithm. 16. The device according to any one of claims 9 to 15, wherein the device is a cloud. 17. A device for living body detection, characterized in that it comprises: memory for storing instruction codes; A processor, configured to execute the instruction code, so as to realize the method described in any one of claims 1-8. 18. A computer storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.