CN113705428A

CN113705428A - Living body detection method and apparatus, electronic device, and computer-readable storage medium

Info

Publication number: CN113705428A
Application number: CN202110988130.0A
Authority: CN
Inventors: 舒荣涛; 刘春秋; 谢洪彪; 焦建成
Original assignee: Beijing Sensetime Technology Development Co Ltd
Current assignee: Beijing Sensetime Technology Development Co Ltd
Priority date: 2021-08-26
Filing date: 2021-08-26
Publication date: 2021-11-26
Also published as: WO2023024473A1

Abstract

The application discloses a living body detection method and device, electronic equipment and a computer readable storage medium. The method is applied to a living body detection device, and comprises the following steps: acquiring a living body detection state of an environment where the living body detection device is located, wherein the living body detection state comprises a normal state or an abnormal state, the normal state represents that the environment where the living body detection device is located is not in a state of being attacked by a non-living body, and the abnormal state represents that the environment where the living body detection device is located is in a state of being attacked by the non-living body; acquiring at least two first images to be processed under the condition that the living body detection state of the environment where the living body detection device is located comprises the abnormality, wherein the at least two first images to be processed comprise a target person; and obtaining a first living body detection result of the target person according to at least two first images to be processed.

Description

Living body detection method and apparatus, electronic device, and computer-readable storage medium

Technical Field

The present application relates to the field of security technologies, and in particular, to a method and an apparatus for detecting a living body, an electronic device, and a computer-readable storage medium.

Background

With the development of face recognition technology, face recognition technology has been widely applied to different application scenarios. In the process of face recognition, the living body detection is carried out on the face image, so that whether a person to be detected in the face image is a living body or not can be determined, the attack of the non-living body is avoided, and the safety is improved. Therefore, how to improve the accuracy of the living body detection is of great significance.

Disclosure of Invention

The application provides a living body detection method and device, electronic equipment and a computer readable storage medium.

In a first aspect, a method for in vivo detection is provided, the method being applied to a biopsy device, the method comprising:

acquiring a living body detection state of an environment where the living body detection device is located, wherein the living body detection state comprises a normal state or an abnormal state, the normal state represents that the environment where the living body detection device is located is not in a state of being attacked by a non-living body, and the abnormal state represents that the environment where the living body detection device is located is in a state of being attacked by the non-living body;

acquiring at least two first images to be processed under the condition that the living body detection state of the environment where the living body detection device is located comprises the abnormality, wherein the at least two first images to be processed comprise a target person;

and obtaining a first living body detection result of the target person according to at least two first images to be processed.

In this respect, the living body detecting device in the present embodiment can improve the living body detection criterion by obtaining the first living body detection result of the target person from the at least two first images to be processed in the case where it is determined that the environment in which the living body detecting device is located includes an abnormality, thereby improving the accuracy of the living body detection result.

In combination with any embodiment of the present application, the acquiring a living body detection state of an environment in which the living body detection device is located includes:

acquiring a first threshold and at least one second image to be processed, wherein the maximum timestamp in the at least one second image to be processed is smaller than the minimum timestamps in the at least two first images to be processed;

performing living body detection processing on the at least one second image to be processed to obtain at least one second living body detection result;

determining a first number of first positive results in the at least one second in-vivo test result, the first positive results being the second in-vivo test results that the in-vivo test passed;

determining a first ratio of the first number and a second number, the second number being the number of the second in-vivo detection results;

and determining the living body detection state according to the first ratio and the first threshold value.

In this embodiment, the living body detecting apparatus may calculate an occupancy of a first positive result of the at least one second living body detection result based on the first number and the second number in the case where the first number and the second number are determined, and may determine the living body detection state based on the occupancy of the first positive result of the at least one second living body detection result and the first threshold.

acquiring a binocular image and a second threshold value, wherein the binocular image comprises a first image and a second image, and the first image and the second image both comprise a face to be detected;

determining a first position of the face to be detected in the first image, and determining a second position of the face to be detected in the second image;

obtaining the parallax displacement of the face to be detected in the binocular image according to the first position and the second position;

and obtaining the living body detection state according to the parallax displacement and the second threshold value.

In this embodiment, the second threshold is a criterion for determining whether the parallax displacement of the face to be detected in the binocular image is large or small, that is, the parallax displacement can be determined to be large or small by the second threshold. If the parallax displacement is large, the face to be detected can be determined to be a two-dimensional face, and then the person corresponding to the face to be detected can be determined to be a non-living body; if the parallax displacement is small, the face to be detected can be determined to be a three-dimensional face, and then the person corresponding to the face to be detected can be determined to be a living body. If the person corresponding to the face to be detected is a living body, determining that the living body detection state is normal; and if the person corresponding to the face to be detected is a non-living body, determining that the living body detection state comprises abnormity.

With reference to any embodiment of the present application, the obtaining a first living body detection result of the target person according to at least two first images to be processed includes:

performing living body detection processing on the at least two first images to be processed to obtain at least two third living body detection results of the target person;

and obtaining a first living body detection result of the target person according to the at least two third living body detection results.

In this embodiment, the living body detecting device obtains the first living body detection result from the at least two third living body detection results, and the accuracy of the first living body detection result can be improved.

With reference to any one of the embodiments of the present application, the obtaining the first in-vivo detection result of the target person according to the at least two third in-vivo detection results includes:

acquiring a third threshold;

determining a third number of second positive results of the at least two third in vivo tests, the second positive results being the third in vivo tests results that passed the in vivo test;

determining a second ratio of the third number and a fourth number, the fourth number being the number of the third in-vivo detection results;

and obtaining a first living body detection result of the target person according to the second ratio and the third threshold.

In this embodiment, the living body detecting apparatus calculates, in the case where the third number and the fourth number are determined, a ratio of the second positive results of the at least two third living body detection results, that is, a second ratio, based on the third number and the fourth number. And determining the first in-vivo detection result according to the magnitude relation between the second ratio and the third threshold, thereby improving the accuracy of the first in-vivo detection result.

determining that a first in-vivo detection result of the target person is a living body if the number of second positive results is greater than the number of negative results among the at least two third in-vivo detection results, the second positive result being the third in-vivo detection result that a living body detection passes, and the negative result being the third in-vivo detection result that a living body detection fails;

determining that the first living body detection result of the target person is a non-living body if the number of second positive results of the at least two third living body detection results is less than or equal to the number of negative results.

With reference to any embodiment of the present application, after determining that the living body detection state includes the abnormality, before performing living body detection processing on the at least two first images to be processed to obtain at least two third living body detection results of the target person, the method further includes:

increasing a first living body detection threshold of the living body detection processing to obtain a second living body detection threshold;

the performing living body detection processing on the at least two first images to be processed to obtain at least two third living body detection results of the target person includes:

and performing living body detection processing on the at least two first images to be processed according to the second living body detection threshold value to obtain at least two third living body detection results of the target person.

In this embodiment, the living body detecting apparatus obtains the second living body detection threshold by increasing the first living body detection threshold in a case where it is determined that the living body detection state includes the abnormality, and takes the second living body detection threshold as a basis for determining whether or not the target person is a living body. In this way, the living body detecting apparatus can improve the living body detection criterion by using the second living body detection threshold as a criterion for determining whether the target person is a living body, thereby improving the accuracy of the third living body detection result.

In combination with any embodiment of the present application, the living body detecting device includes an entrance guard device, and the at least two first images to be processed each include a face of the target person; in a case where it is determined that the living body detection state includes the abnormality, the method further includes:

increasing a first face similarity threshold value of the face comparison to obtain a second face similarity threshold value;

acquiring at least one registered face image;

according to the second face similarity threshold value, performing face comparison on the face image to be detected and the at least one registered face image to obtain a face comparison result, wherein the face image to be detected is any one of the at least two first images to be processed;

and determining the passing state of the target person in the access control device according to the face comparison result and the first living body detection result.

In this embodiment, the door control device obtains the second face similarity threshold by increasing the first face similarity threshold when the living body detection state includes an abnormality, and uses the second face similarity threshold as a basis for determining whether or not the target person is a registered person. Therefore, the entrance guard device can improve the face comparison standard by taking the second face similarity threshold as a basis for judging whether the target figure is the registered figure, so that the accuracy of the face comparison result is improved, the identification accuracy of the entrance guard device is improved, and the safety in an abnormal living body detection state is improved.

With reference to any one of the embodiments of the present application, determining the passing status of the target person in the access control device according to the face comparison result and the first in-vivo detection result includes:

determining that the passing state of the target person in the access control device is not passable under the condition that the face comparison result comprises that no image matched with the face image to be detected exists in the at least one registered face image;

determining that the passing state of the target person in the access control device is not passable under the condition that the first living body detection result comprises that the target person is a non-living body;

and determining that the passing state of the target person in the access control device is passable under the condition that the first living body detection result comprises that the target person is a living body and the face comparison result comprises that the image matched with the face image to be detected exists in the at least one registered face image.

In a second aspect, there is provided a living body detecting apparatus including:

an acquisition unit, configured to acquire a living body detection state of an environment in which the living body detection device is located, where the living body detection state includes a normal state indicating that the environment in which the living body detection device is located is not in a state of being attacked by a non-living body or an abnormal state indicating that the environment in which the living body detection device is located is in a state of being attacked by a non-living body;

the acquiring unit is further configured to acquire at least two first images to be processed, where the at least two first images to be processed each include a target person, when the living body detection state of the environment where the living body detection device is located includes the abnormality;

and the first processing unit is used for obtaining a first living body detection result of the target person according to at least two first images to be processed.

In combination with any embodiment of the present application, the obtaining unit is configured to:

In combination with any embodiment of the present application, the first processing unit is configured to:

acquiring a third threshold;

In combination with any one of the embodiments of the present application, the biopsy device further includes: a second processing unit configured to, after determining that the living body detection state includes the abnormality, increase a first living body detection threshold of the living body detection processing to obtain a second living body detection threshold before the living body detection processing is performed on the at least two first images to be processed to obtain at least two third living body detection results of the target person;

the first processing unit is configured to:

In combination with any embodiment of the present application, the living body detecting device includes an entrance guard device, and the at least two first images to be processed each include a face of the target person; the first processing unit is further configured to increase a first face similarity threshold of face comparison to obtain a second face similarity threshold when it is determined that the living body detection state includes the abnormality;

the acquisition unit is also used for acquiring at least one registered face image;

the first processing unit is further configured to perform face comparison on the to-be-detected face image and the at least one registered face image according to the second face similarity threshold value to obtain a face comparison result, where the to-be-detected face image is any one of the at least two first to-be-processed images;

the first processing unit is further used for determining the passing state of the target person in the access control device according to the face comparison result and the first living body detection result.

With reference to any one of the embodiments of the present application, the first processing unit is configured to:

In a third aspect, an electronic device is provided, which includes: a processor and a memory for storing computer program code comprising computer instructions, the electronic device performing the method of the first aspect and any one of its possible implementations as described above, if the processor executes the computer instructions.

In a fourth aspect, another electronic device is provided, including: a processor, transmitting means, input means, output means, and a memory for storing computer program code comprising computer instructions, which, when executed by the processor, cause the electronic device to perform the method of the first aspect and any one of its possible implementations.

In a fifth aspect, there is provided a computer-readable storage medium having stored therein a computer program comprising program instructions which, if executed by a processor, cause the processor to perform the method of the first aspect and any one of its possible implementations.

A sixth aspect provides a computer program product comprising a computer program or instructions which, when run on a computer, causes the computer to perform the method of the first aspect and any of its possible implementations.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments or the background art of the present application, the drawings required to be used in the embodiments or the background art of the present application will be described below.

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic diagram of a pixel coordinate system according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart of a method for detecting a living organism according to an embodiment of the present disclosure;

fig. 3 is a schematic view of a binocular image provided in an embodiment of the present application;

fig. 4 is a schematic view of another binocular image provided in the embodiments of the present application;

FIG. 5 is a schematic structural diagram of a living body detecting apparatus according to an embodiment of the present disclosure;

fig. 6 is a schematic hardware structure diagram of a living body detection apparatus according to an embodiment of the present disclosure.

Detailed Description

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

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more, "at least two" means two or three and three or more, "and/or" for describing an association relationship of associated objects, meaning that three relationships may exist, for example, "a and/or B" may mean: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" may indicate that the objects associated with each other are in an "or" relationship, meaning any combination of the items, including single item(s) or multiple items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural. The character "/" may also represent a division in a mathematical operation, e.g., a/b-a divided by b; 6/3 ═ 2. At least one of the following "or similar expressions.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

With the development of face recognition technology, face recognition technology has been widely applied to different application scenarios, wherein confirming the identity of a person through face recognition is an important application scenario, for example, real-name authentication, identity authentication, and the like are performed through face recognition technology.

The face recognition technology obtains face feature data by performing feature extraction processing on a face image obtained by collecting a face region of a person. And comparing the extracted face feature data with the face feature data in the database to determine the identity of the person in the face image.

However, recently, more and more events occur that attack face recognition technology using non-living face data. The non-living body face data includes: paper face photos, electronic face images, and the like. The face recognition technology is attacked by using the non-living body face data, namely, the non-living body face data is used for replacing the face area of the figure, so that the effect of deceiving the face recognition technology is achieved.

For example, Zhang III places a photo of Li IV in front of a cell phone of Li IV for face recognition unlocking. The mobile phone shoots the photo of the fourth plum through the camera to obtain a face image of the face area containing the fourth plum, further determines the identity of the third plum as the fourth plum, and unlocks the mobile phone. Therefore, Zhang III realizes the unlocking of the Li IV mobile phone by successfully deceiving the face recognition technology of the mobile phone by using the Li IV photo.

Therefore, how to prevent the non-living human face data from attacking the face recognition technology (hereinafter, will be referred to as non-living attack) is very important.

The attack of the non-living human face data to the human face recognition technology can be effectively prevented by carrying out living body detection on the human face data. Conventional live body detection methods include a silent live body detection method and a video live body detection method. The silent liveness detection method refers to a method for performing liveness detection based on a single image. The video living body detection method is a method for completing living body detection based on videos, for example, a person to be detected completes corresponding actions (such as shaking head, blinking, opening mouth) according to corresponding instructions in the process of recording a living body detection video. And processing the living body detection video to determine whether the person to be detected completes corresponding actions, and further determine whether the person to be detected is a living body.

Since the video live detection method takes a long time, the video live detection method is not suitable for a scene in which live detection needs to be completed in a short time (hereinafter, such a scene is referred to as a rapid detection scene). For example, when the entrance guard device determines whether a person to be detected is passable, it is necessary to perform living body detection on the person to be detected. If the time consumed by the live body detection is longer, the user experience is influenced, and compared with a video live body detection method, the silent live body detection method has a lower success rate of live body detection. Therefore, how to improve the user experience and improve the success rate of the living body detection has very important significance. Based on this, the embodiment of the application provides a living body detection method to improve user experience and improve the success rate of living body detection.

For convenience of description, the positions in the image appearing hereinafter each refer to a position in pixel coordinates of the image. In the embodiment of the present application, the abscissa of the pixel coordinate system is used to indicate the number of rows where the pixel points are located, and the ordinate of the pixel coordinate system is used to indicate the number of rows where the pixel points are located.

For example, in the image shown in fig. 1, a pixel coordinate system XOY is constructed with the upper left corner of the image as the origin O of coordinates, the direction parallel to the rows of the image as the direction of the X axis, and the direction parallel to the columns of the image as the direction of the Y axis. The units of the abscissa and the ordinate are pixel points. For example, pixel A in FIG. 1₁₁Has the coordinate of (1, 1), and the pixel point A₂₃Has the coordinates of (3, 2), and the pixel point A₄₂Has the coordinates of (2, 4), and the pixel point A₃₄The coordinates of (2) are (4, 3).

The execution subject of the embodiment of the present application is a living body detection device, wherein the living body detection device may be any electronic device capable of executing the technical solution disclosed in the embodiment of the method of the present application. Alternatively, the living body detecting device may be one of: cell-phone, computer, panel computer, wearable smart machine.

It should be understood that the method embodiments of the present application may also be implemented by means of a processor executing computer program code. The embodiments of the present application will be described below with reference to the drawings. Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting a living body according to an embodiment of the present disclosure.

201. And acquiring the living body detection state of the environment where the living body detection device is positioned, wherein the living body detection state comprises normal or abnormal.

In the embodiment of the present application, the living body detection state of the living body detection environment includes normal or abnormal. If the living body detection state of the living body detection environment comprises normal, representing that the living body detection environment is not in a state of being attacked by a non-living body; if the living body detection state of the living body detection environment comprises an abnormality, the living body detection environment is in a state of being attacked by a non-living body.

For example, the living body detecting device determines that the person to be detected is a non-living body in n consecutive times of living body detection, which indicates that the living body detecting device may be under a non-living body attack, and the environment in which the living body detecting device is located is under a state of being attacked by the non-living body, that is, the living body detecting state of the environment in which the living body detecting device is located includes an abnormality. On the contrary, if the living body detection state of the environment in which the living body detection device is located is not abnormal, the living body detection state of the environment in which the living body detection device is located includes normal.

In the embodiment of the present application, the environment in which the living body detection device is located is the living body detection environment, and the living body detection state is used to represent whether the environment in which the living body detection device is located is under a state of being attacked by a non-living body.

In one manner of acquiring the in-vivo detection state, the in-vivo detection device receives the in-vivo detection state input by the user through the input component. The input assembly comprises at least one of the following components: keyboard, mouse, touch screen, touch pad, audio input ware.

In another way of acquiring the living body detection state, the living body detection device receives the living body detection state transmitted by the terminal. The terminal may be any one of the following: cell-phone, computer, panel computer, server.

202. And acquiring at least two first images to be processed, which each include a target person, when the living body detection state of the environment in which the living body detection device is located includes the abnormality.

In the embodiment of the present application, the first images to be processed each include a target person, that is, the living body detection apparatus needs to determine whether the target person in the first images to be processed is a living body.

In one possible implementation manner, the living body detecting device includes a camera, and the living body detecting device uses the camera to acquire n images as the at least two first images to be processed, where n is an integer greater than 1.

For example, the living body detecting apparatus acquires n images as the at least two first images to be processed using the camera in a case where the living body detection instruction is detected.

In another possible implementation manner, the living body detecting device includes a camera, and the living body detecting device uses the camera to collect a video with a preset time length, and takes images in the video as at least two first images to be processed.

For example, the living body detecting apparatus captures a video for 1 minute using a camera in the case where the living body detection instruction is detected. If the video includes 30 frames of images, the living body detecting device takes at least two frames of images out of the 30 frames of images in the video as at least two first images to be processed.

In another possible implementation manner, the living body detecting device acquires at least two first images to be processed by receiving at least two first images to be processed input by the user through the input member.

In yet another possible implementation manner, the living body detecting device acquires at least two first images to be processed by receiving the at least two first images to be processed transmitted by the terminal.

203. And obtaining a first living body detection result of the target person according to the at least two first images to be processed.

In the embodiment of the present application, the living body detection result (including the first living body detection result described above, and the second living body detection result, the third living body detection result to be mentioned below) includes a living body detection passage or a living body detection non-passage, where the living body detection passage means that the living body detection object is a living body, and the living body detection non-passage means that the living body detection object is a non-living body.

For example, if the first live body test result includes a live body test pass, the target person is a live body; if the first live body test result includes a live body test failure, the target person is a non-live body.

In the embodiment of the present application, the living body detection device performs the living body detection processing on the image, and thereby can obtain the living body detection result of the living body detection object in the image.

Since the probability that the living body detecting device is subjected to the non-living body attack when the living body detecting state includes the abnormality is greater than the probability that the living body detecting device is subjected to the non-living body attack when the living body detecting state includes the normal state, the living body detecting standard should be raised when the living body detecting state includes the abnormality to reduce the success rate of the non-living body attack.

Specifically, considering that the probability of being subjected to a non-live attack when the live body detection state includes an abnormality is higher than the probability of being subjected to a non-live attack when the live body detection state includes a normal state, the live body detection state includes a live body detection criterion for determining whether the person to be detected is a live body when the abnormality is included, and the live body detection criterion for determining whether the person to be detected is a live body when the live body detection state includes an abnormality should be stricter than that when the live body detection state includes an abnormality. This can reduce the false detection rate of the biopsy, thereby improving the accuracy of the biopsy result.

As described above, the silent liveness detection method has a lower success rate of liveness detection than the video liveness detection method, i.e., the standard of liveness detection of the silent liveness detection method is lower than that of the video liveness detection method. Specifically, the silent liveness detection method determines the liveness detection result from a single image, and the video liveness detection method determines the liveness detection result from at least two images, so that the liveness detection standard of the video liveness detection method is higher than that of the silent liveness detection method.

Therefore, the living body detecting apparatus obtains the first living body detection result of the target person from the at least two first images to be processed in the case where the living body detection state includes the abnormality. Thereby, the accuracy of the first living body detection result is improved.

In one possible implementation manner, the living body detecting device performs living body detection processing on a first image to be processed, and obtains a first intermediate living body detection result, wherein the first intermediate living body detection result includes a living body probability that the target person is a living body.

The living body detection device carries out living body detection processing on at least two first images to be processed, and at least two first intermediate living body detection results can be obtained. The living body detection device calculates the mean value of at least two first intermediate living body detection results to obtain a second intermediate living body detection result. Determining that the first living body detection result of the target person is the living body if the living body probability of the second intermediate living body detection result is greater than the living body detection threshold; in a case where the living body probability of the second intermediate living body detection result is less than or equal to the living body detection threshold, it is determined that the first living body detection result of the target person is the target person as a non-living body.

For example, the at least two first intermediate living body detection results include a first intermediate living body detection result a and a first intermediate living body detection result b, where the first intermediate living body detection result a includes a living body probability that the target person is a living body of 0.8, and the first intermediate living body detection result b includes a living body probability that the target person is a living body of 0.76. A second intermediate living body detection result is obtained by calculating an average value of the first intermediate living body detection result a and the first intermediate living body detection result b, wherein the second intermediate living body detection result includes a living body probability that the target person is a living body of 0.78.

If the live body detection threshold is 0.79, the first live body detection result is that the target person is a non-live body since the second intermediate live body detection result is smaller than the live body detection threshold (0.78 smaller than 0.79). If the living body detection threshold is 0.7, the first living body detection result is that the target person is a living body since the living body probability of the second intermediate living body detection result is larger than the living body detection threshold (0.78 larger than 0.7).

In this implementation manner, the living body detecting device obtains the first living body detecting result by calculating the average value of the at least two first intermediate living body detecting results, so that the false detection rate caused by the living body detecting processing on a single image can be reduced, and the accuracy of the first living body detecting result can be improved.

The embodiment of the application is different from the traditional method, and the biopsy result is obtained by performing biopsy processing on a single image under the condition that the biopsy state is not judged, or is obtained by performing biopsy by adopting a video biopsy method under the condition that the biopsy state is not judged. The living body detecting device in the present embodiment can improve the living body detection criterion by obtaining the first living body detection result of the target person from the at least two first images to be processed in the case where it is determined that the environment in which the living body detecting device is located includes an abnormality, thereby improving the accuracy of the living body detection result. And therefore, the video live body detection method can be avoided being adopted under the condition that the live body detection state is normal, and the user experience can be improved.

Optionally, the living body detecting device determines the first living body detection result of the target person by using a silent living body detection method when the living body detection state includes normal. For example, the living body detecting device obtains a first living body detection result from any one of at least two first images to be processed.

As an alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 201:

1. and acquiring a first threshold and at least one second image to be processed, wherein the maximum time stamp in the at least one second image to be processed is smaller than the minimum time stamps in the at least two first images to be processed.

In the embodiment of the present application, the first threshold is a positive number less than or equal to 1. In one implementation of obtaining the first threshold, the living body detecting device obtains the first threshold by receiving the first threshold input by the user through the input component.

In another way of acquiring the first threshold value, the living body detecting device acquires the first threshold value by receiving the first threshold value transmitted by the terminal.

In the embodiment of the application, the maximum timestamp of the at least one second image to be processed is smaller than the minimum timestamp of the at least two first images to be processed, that is, the acquisition time of any one second image to be processed is earlier than that of any one first image to be processed.

In one possible implementation, the living body detecting apparatus takes at least one second image to be processed input by the user through the input component as the at least one second image to be processed.

In another possible implementation manner, the living body detecting device receives at least one second image to be processed sent by the terminal as at least one second image to be processed.

In yet another possible implementation, the liveness detection device includes a camera. The living body detection device acquires at least one second image to be processed by using the camera.

Optionally, the living body detection device acquires at least one second image to be processed by using the camera when detecting the living body detection instruction. For example, the living body detecting apparatus captures at least one second image to be processed by using the camera when detecting the presence of the person a in the living body detection region.

For another example, when the living body detecting apparatus detects that the person a exists in the living body detection region, the living body detecting apparatus captures an image of the person a using the camera to obtain the second image to be processed a. The living body detecting device uses the camera to shoot the person B to obtain a second image to be processed B when detecting that the person B exists in the living body detection area. At this time, the at least one second image to be processed includes a second image to be processed a and a second image to be processed B.

It should be understood that, in the embodiment of the present application, the step of acquiring the first threshold and the step of acquiring the at least one second to-be-processed image may be performed separately or simultaneously. For example, the image processing apparatus may acquire the first threshold before acquiring the at least one second to-be-processed image. For another example, the image processing apparatus may first acquire at least one second image to be processed, and then acquire the first threshold. For another example, the image processing apparatus acquires the at least one second image to be processed during the acquisition of the first threshold, or acquires the first threshold during the acquisition of the at least one second image to be processed.

2. And performing living body detection processing on the at least one second image to be processed to obtain at least one second living body detection result.

In the embodiment of the application, each second image to be processed includes a person to be detected. The persons to be detected contained in the different second images to be processed may be the same or different. For example, the at least one second image to be processed includes an image a and an image b. It may be that image a contains three and image b contains lie four. The image a and the image b may include three sheets. It should be understood that the person to be detected and the target person may be the same or different.

In one possible implementation manner, the living body detection device performs living body detection processing on a second image to be processed, and a second living body detection result can be obtained. The living body detection device can obtain at least one second living body detection result by carrying out living body detection processing on at least one second image to be processed.

For example, the at least one second image to be processed includes an image a and an image b. If the living body detection device obtains the living body detection result a by performing the living body detection processing on the image a during the step 2, at least one second living body detection result includes the living body detection result a.

If the living body detecting device obtains the living body detection result A by performing the living body detection processing on the image a and obtains the living body detection result B by performing the living body detection processing on the image B in the process of executing the step 2. At this time, the at least one second in-vivo test result includes an in-vivo test result a and an in-vivo test result B.

3. And determining a first number of first positive results in the at least one second in-vivo test result, wherein the first positive results are second in-vivo test results passed by the in-vivo test.

4. A first ratio of the first number to a second number is determined, the second number being a number of second in-vivo test results.

5. And determining the living body detection state according to the first ratio and the first threshold.

The larger the proportion of the first positive result in the at least one second in-vivo detection result is, the lower the probability that the in-vivo detection device is attacked by the non-living body is. In this embodiment, the first ratio represents a ratio of the first positive result to the second in-vivo detection result, and the first threshold is a criterion for determining whether the first ratio is large or small, that is, the first threshold can be used for determining whether the first ratio is large or small. If the first ratio is large, the occupation ratio of the first positive result in the at least one second in-vivo detection result is large, and the in-vivo detection state comprises normal; if the first ratio is small, indicating that the percentage of the first positive result in the at least one second in-vivo detection result is small, the in-vivo detection state includes an abnormality.

In one possible implementation manner, the living body detection device determines that the first ratio is large when the first ratio is larger than the first threshold, and further determines that the living body detection state is normal; the living body detection device determines that the first ratio is small when the first ratio is less than or equal to the first threshold value, and further determines that the living body detection state is abnormal.

In another possible implementation manner, the living body detection device determines that the first ratio is large when the first ratio is greater than or equal to the first threshold, and further determines that the living body detection state is normal; the living body detection device determines that the first ratio is small when the first ratio is smaller than the first threshold value, and further determines that the living body detection state is abnormal.

In yet another possible implementation, the living body detecting device calculates a square of the first ratio to obtain a first intermediate value. The living body detection device determines that the first ratio is large under the condition that the first intermediate value is larger than the first threshold value, and further determines that the living body detection state is normal; the living body detecting device determines that the first ratio is small when the first intermediate value is less than or equal to the first threshold value, and further determines that the living body detection state is abnormal.

The living body detecting apparatus can calculate the proportion of the first positive result in the at least one second living body detection result from the first number and the second number in the case where the first number and the second number are determined by performing steps 1 to 5. The in-vivo detection state may then be determined according to the first threshold and a percentage of the first positive result in the at least one second in-vivo detection result.

As an alternative embodiment, in the case that the in-vivo detection state includes an abnormality, the in-vivo detection state further includes an abnormality level, wherein the abnormality level is used for representing the degree of abnormality of the environment in which the in-vivo detection device is located.

For example, the abnormality levels include a first level, a second level, and a third level, wherein the third level is characterized by a higher degree of abnormality than the second level, and the second level is characterized by a higher degree of abnormality than the first level.

As another example, an anomaly rating includes general, higher, and special, where special is characterized by a higher degree of anomaly than general and higher is characterized by a higher degree of anomaly than general.

In a case where the living body detection state of the environment in which the living body detection device is located includes an abnormality, the living body detection device further determines an abnormality level of the living body detection state by performing the steps of:

6. and acquiring a first mapping relation between the abnormal grade and the first ratio.

In an embodiment of the present application, the first mapping relationship represents a mapping between a proportion of the first positive result in the at least one second in-vivo detection result and an abnormality level.

7. And obtaining the abnormal grade of the living body detection state according to the first mapping relation and the first ratio.

As still another alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 201:

8. when a first living body detection instruction carrying living body detection state information is detected, the living body detection state indicated by the first living body detection instruction is used as the living body detection state of the environment where the living body detection device is located.

In an embodiment of the application, the first biopsy instruction is used for instructing the biopsy device to perform biopsy, and the instruction carries biopsy status information. For example, the first living body detection instruction carries the living body detection state information that the living body detection state includes an abnormality; the first living body detection instruction carries living body detection state information that the living body detection state includes normal.

In one possible implementation, the first liveness detection instruction is input by a user to the liveness detection device through the input assembly.

In another possible implementation manner, the first living body detection instruction is obtained by fusing the first intermediate living body detection instruction with the living body detection state information. The first intermediate living body detection instruction is generated by the living body detection device in a case where it is determined that the human being to be detected exists within the living body detection area. The living body detection state information is randomly generated by the living body detection device.

For example, the living body detecting device generates a first intermediate living body detection instruction in a case where it is determined that a person to be detected exists within the living body detection area, and randomly generates living body detection state information in which the living body detection state includes an abnormality. And fusing the living body detection state information and the first intermediate living body detection instruction to obtain a first living body detection instruction. At this time, the living body detection state information carried by the first living body detection instruction is that the living body detection state includes an abnormality.

In order to improve the living body detection accuracy, the living body detection standard adopted by the living body detection device when the living body detection state is abnormal is more strict than the living body detection standard adopted when the living body detection state is normal, so that the difficulty of non-living body attack on the living body detection device by an attacker (namely, a person who performs non-living body attack on the living body detection device) can be increased, and the success rate of the non-living body attack is reduced. In order to improve the success rate of the non-living body attack, an attacker may adopt a specific non-living body attack to prevent the living body detection device from determining that the living body detection state is abnormal, so as to prevent the living body detection device from adopting a stricter living body detection standard.

For example, the living body detecting device includes an entrance guard device. If the results of three consecutive biopsy include a biopsy failure, the access control device determines that the biopsy status includes an abnormality. After opening the tee bend and passing and carry out many times non-living body attack to entrance guard's device, know the logic of the definite living body detection state of entrance guard's device, adopted specific non-living body attack, it is specific: non-live attacks were performed twice every third time, and live identification was performed once every third time. In this way, the door control device can be prevented from determining that the in-vivo detection state includes an abnormality, thereby preventing the in-vivo detection device from performing the in-vivo detection using a stricter in-vivo detection standard.

In this implementation, since the in-vivo detection state information is randomly generated, the in-vivo detection state is determined randomly, so that a specific non-in-vivo attack can be effectively avoided, thereby improving the accuracy of in-vivo detection.

As another alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 201:

9. and acquiring a binocular image and a second threshold value, wherein the binocular image comprises a first image and a second image, and the first image and the second image both comprise a face to be detected.

In the embodiment of the present application, binocular images refer to two images obtained by photographing the same scene from different positions at the same time by two different imaging apparatuses (which will be referred to as binocular imaging apparatuses hereinafter). Specifically, the binocular imaging device shoots the same scene from different positions at the same time to obtain a first image and a second image.

In one implementation of acquiring binocular images, the liveness detection device receives binocular images input by a user through an input assembly.

In another implementation of obtaining the binocular images, the living body detecting device receives the binocular images sent by the terminal.

In yet another implementation of acquiring binocular images, the liveness detection device includes a binocular camera. The living body detection device acquires binocular images through the binocular camera.

In the embodiment of the present application, the effect of the second threshold is different from the effect of the first threshold, and the value of the second threshold may be the same as or different from the value of the first threshold. The second threshold is a positive number.

In one implementation of obtaining the second threshold, the living body detecting device obtains the second threshold by receiving the second threshold input by the user through the input component.

In another manner of acquiring the second threshold value, the living body detecting apparatus acquires the second threshold value by receiving the second threshold value transmitted by the terminal.

It should be understood that, in the embodiment of the present application, the step of acquiring the second threshold and the step of acquiring the binocular image may be performed separately or simultaneously. For example, the image processing apparatus may acquire the second threshold value first and then acquire the binocular image. For another example, the image processing apparatus may acquire the binocular image first and then acquire the second threshold. For another example, the image processing apparatus acquires the binocular image during acquisition of the second threshold value, or acquires the second threshold value during acquisition of the binocular image.

10. And determining a first position of the face to be detected in the first image, and determining a second position of the face to be detected in the second image.

In the embodiment of the application, the face to be detected is the face of a person to be detected. The position of the face to be detected in the image (including the first image and the second image) refers to the position of the face to be detected in the pixel coordinate system of the image. The position of the face to be detected under the pixel coordinate system of the first image is the first position, and the position of the face to be detected under the pixel coordinate system of the second image is the second position.

In one possible implementation manner, the living body detecting device determines, as the first position, a position of a face frame including a face to be detected in the first image by performing face detection processing on the first image. The living body detection device determines the position of a face frame containing the face to be detected in the second image as a second position by carrying out face detection processing on the second image.

11. And obtaining the parallax displacement of the face to be detected in the binocular image according to the first position and the second position.

In the embodiment of the present application, the parallax displacement refers to a distance obtained according to the position of the same object in the binocular image. For example, the image shown in fig. 3 and the image shown in fig. 4 are binocular images, and both the image shown in fig. 3 and the image shown in fig. 4 include a human face to be detected. The position of the face to be detected in the image shown in fig. 3 is the position of the first face frame to be detected including the face to be detected in the image shown in fig. 3, that is, the position of the point a. The position of the face to be detected in the image shown in fig. 4 is the position of the second face frame to be detected including the face to be detected in the image shown in fig. 4, that is, the position of the point B.

The parallax displacement of the face to be detected at this time in the image shown in the image 3 and the image shown in fig. 4 is the distance between the point a (coordinates of (2, 1)) and the point B (coordinates of (3, 2)):

after the living body detection device obtains the first position and the second position, the parallax displacement of the face to be detected in the binocular image can be obtained according to the first position and the second position.

12. The living body detection state is obtained based on the parallax displacement and the second threshold value.

If the binocular image obtained by shooting the three-dimensional object by the binocular imaging device is called a first type of binocular image, the binocular image obtained by shooting the two-dimensional object by the binocular imaging device is called a second type of binocular image. The parallax displacement of the three-dimensional object in the first type of binocular image is smaller than the parallax displacement of the two-dimensional object in the second type of binocular image. Therefore, the size of the parallax displacement of the face to be detected in the binocular image can be judged, the face to be detected is judged to be a two-dimensional face or a three-dimensional face, the face to be detected can be determined to be a living body or a non-living body, and therefore the living body detection state can be determined.

In the embodiment of the application, the second threshold is a basis for determining whether the parallax displacement of the face to be detected in the binocular image is large or small, that is, the parallax displacement can be determined to be large or small through the second threshold. If the parallax displacement is large, the binocular image acquired by the living body detection device can be determined to be a second type of binocular image, namely the face to be detected is a two-dimensional face, and then the person to be detected can be determined to be a non-living body; if the parallax displacement is small, the binocular images acquired by the living body detection device can be determined to be first-class binocular images, namely, the face to be detected is a three-dimensional face, and then the person to be detected can be determined to be a living body. If the person to be detected is a living body, determining that the living body detection state is normal; if the person to be detected is not a living body, it can be determined that the living body detection state includes an abnormality.

In a possible implementation manner, the living body detection device determines that the parallax displacement is small when the parallax displacement is smaller than a second threshold value, and further determines that the living body detection state is normal; the living body detection device determines that the parallax displacement is large when the parallax displacement is greater than or equal to a second threshold value, and further determines that the living body detection state is abnormal.

In another possible implementation manner, the living body detection device determines that the parallax displacement is small when the parallax displacement is less than or equal to the second threshold, and further determines that the living body detection state is normal; the living body detection device determines that the parallax displacement is large when the parallax displacement is larger than the second threshold value, and further determines that the living body detection state is abnormal.

In yet another possible implementation manner, the living body detecting device calculates the square of the parallax displacement to obtain a second intermediate value. The living body detection device determines that the parallax displacement is small under the condition that the second intermediate value is smaller than the second threshold value, and further determines that the living body detection state is normal; the living body detection device determines that the parallax displacement is large and further determines that the living body detection state is abnormal, in a case where the second intermediate value is greater than or equal to the second threshold value.

In this embodiment, because the parallax displacement of the two-dimensional object in the binocular image is greater than the parallax displacement of the three-dimensional object in the binocular image, the living body detection device can determine the parallax displacement of the human face to be detected in the binocular image by executing steps 9 to 12, and further determine whether the human body to be detected is a living body or a non-living body according to the parallax displacement and the second threshold value, so as to determine the living body detection state.

Optionally, the living body detecting device further obtains a second mapping relationship between the parallax displacement and the abnormality level when the living body detection state includes an abnormality; and determining the abnormal level of the living body detection state according to the parallax displacement and the second mapping relation.

13. and acquiring a fourth threshold and a third image to be processed.

In the embodiment of the present application, the effect of the fourth threshold is different from both the effect of the first threshold and the effect of the second threshold. The value of the fourth threshold may be the same as or different from the value of the first threshold. The value of the fourth threshold may be the same as or different from the value of the second threshold. The fourth threshold is a positive number.

In one implementation of obtaining the fourth threshold, the liveness detection device receives the fourth threshold input by the user through the input component.

In another implementation of obtaining the fourth threshold, the living body detecting device receives the fourth threshold transmitted by the terminal.

In one way of acquiring the third image to be processed, the living body detecting device receives the third image to be processed input by the user through the input unit.

In another way of acquiring the third image to be processed, the living body detecting device receives the third image to be processed transmitted from the terminal.

In still another mode of acquiring the third image to be processed, the living body detecting device includes a camera. The living body detection device acquires a third image to be processed by using the camera.

Optionally, the living body detection device acquires a third image to be processed by using the camera when detecting the living body detection instruction. For example, in a case where the living body detecting apparatus detects the presence of the person a in the living body detection region, the person a is photographed by using the camera to obtain a third image to be processed.

For another example, when the living body detecting apparatus detects that the person a exists in the living body detection region, the living body detecting apparatus captures an image of the person a using the camera to obtain a third image to be processed.

It should be understood that, in the embodiment of the present application, the step of acquiring the fourth threshold and the step of acquiring the third to-be-processed image may be performed separately or simultaneously. For example, the image processing apparatus may acquire the fourth threshold value first, and then acquire the third to-be-processed image. For another example, the image processing apparatus may acquire the third image to be processed first and then acquire the fourth threshold. For another example, the image processing apparatus acquires the third image to be processed during acquisition of the fourth threshold value, or acquires the fourth threshold value during acquisition of the third image to be processed.

14. And determining the distance between the face to be detected in the third image to be processed and the target hand in the third image to be processed.

In a possible implementation manner, the living body detecting device obtains the third position of the face to be detected in the third image to be processed by performing face detection processing on the third image to be processed. The living body detection device obtains a fourth position of the target hand in the third image to be processed by performing target detection processing on the third image to be processed. And the living body detection device determines the distance between the face to be detected and the target hand according to the third position and the fourth position.

Optionally, if the living body detection device performs face detection processing on the third image to be processed, it is determined that the third image to be processed includes at least two face regions. The living body detection device takes the human face in the human face area with the largest area as the human face to be detected.

Optionally, if the living body detecting device performs the target detection processing on the third image to be processed, it is determined that the third image to be processed includes at least two hands. The living body detection device respectively calculates the distance between each hand and the face to be detected to obtain at least two distances to be confirmed. And taking the minimum value of the at least two distances to be confirmed as the distance between the face to be detected and the target hand.

15. The living body detection state is obtained based on the distance and the fourth threshold value.

Considering that a person usually holds non-living data with a hand when using the non-living data to perform a non-living attack on a living body detection device, and the person usually does not place the hand on the face when performing a living body detection, by judging the size of the distance, it can be determined whether the face to be detected is a living body or a non-living body, and further, the living body detection state can be determined.

In the embodiment of the present application, the fourth threshold is a basis for determining whether the distance between the face to be detected and the target hand is large or small. Judging whether the distance is large or small through a fourth threshold, and if the distance is large, determining that the person to be detected is a living body; if the distance is small, it is determined that the person to be detected is a non-living body. If the person to be detected is a living body, determining that the living body detection state is normal; if the person to be detected is not a living body, it can be determined that the living body detection state includes an abnormality.

In one possible implementation, the living body detection device determines that the living body detection state is normal in a case where the distance is smaller than a fourth threshold; the living body detection device determines that the living body detection state is abnormal in a case where the distance is greater than or equal to a fourth threshold value.

In another possible implementation manner, the living body detection device determines that the living body detection state is normal in a case where the distance is less than or equal to a fourth threshold value; the living body detection device determines that the living body detection state is abnormal in a case where the distance is greater than a fourth threshold value.

In yet another possible implementation, the living body detecting device calculates the square of the distance to obtain a third intermediate value. The living body detection device determines that the living body detection state is normal under the condition that the third intermediate value is smaller than the fourth threshold value; the living body detecting device determines that the living body detection state is abnormal in a case where the third intermediate value is greater than or equal to the fourth threshold value.

In this embodiment, the living body detection apparatus performs steps 13 to 15 to obtain the distance between the face to be detected and the target hand, and determines whether the person to be detected is a living body or a non-living body according to the distance and a fourth threshold, so that the living body detection state can be determined.

Optionally, the living body detecting device further obtains a third mapping relationship between the distance and the abnormality level when the living body detection state includes an abnormality; and determining the abnormal level of the living body detection state according to the distance and the second mapping relation.

As an alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 201: and acquiring a number of people threshold and a fourth image to be processed.

In the embodiment of the present application, the role of the number of people threshold is different from the role of the first threshold, the role of the second threshold, and the role of the fourth threshold. The value of the number of people threshold can be the same as or different from the value of the first threshold. The value of the number of people threshold and the value of the second threshold can be the same or different. The value of the number of people threshold and the value of the fourth threshold can be the same or different. The threshold number of people is a positive number.

In one implementation of obtaining the threshold number of people, the in-vivo detection device receives the threshold number of people input by the user through the input component.

In another implementation of obtaining the people number threshold, the living body detecting device receives the people number threshold sent by the terminal.

In one way of acquiring the fourth image to be processed, the living body detecting device receives the fourth image to be processed input by the user through the input unit.

In another manner of acquiring the fourth image to be processed, the living body detecting apparatus receives the fourth image to be processed transmitted from the terminal.

In still another mode of acquiring the fourth to-be-processed image, the living body detecting device includes a camera. The living body detection device acquires a fourth image to be processed by using the camera.

Optionally, the living body detection device acquires a fourth image to be processed by using the camera when detecting the living body detection instruction. For example, in a case where the living body detecting apparatus detects the presence of the person a in the living body detection region, the person a is photographed by using the camera to obtain a fourth image to be processed.

For another example, when the living body detecting apparatus detects that the person a exists in the living body detection region, the living body detecting apparatus captures an image of the person a using the camera to obtain a fourth image to be processed.

It should be understood that, in the embodiment of the present application, the step of acquiring the number-of-people threshold and the step of acquiring the fourth to-be-processed image may be executed separately or simultaneously. For example, the image processing apparatus may obtain the threshold of the number of people first and then obtain the fourth image to be processed. For another example, the image processing apparatus may first obtain the fourth image to be processed and then obtain the threshold of the number of people. For another example, the image processing apparatus acquires the fourth image to be processed in the process of acquiring the number-of-persons threshold, or acquires the number-of-persons threshold in the process of acquiring the fourth image to be processed.

The living body detecting device determines the number of persons in the fourth image to be processed. Determining that the in-vivo detection state includes an abnormality in a case where the number of persons is greater than a threshold number of persons; in a case where the number of persons is less than or equal to the number-of-persons threshold, it is determined that the living body detection state includes normal.

In this embodiment, the biopsy device determines the biopsy state based on the number of persons in the fourth image to be processed and the number of persons threshold.

As an alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 203:

16. and performing living body detection processing on the at least two first images to be processed to obtain at least two third living body detection results of the target person.

The living body detecting device performs living body detection processing on a first image to be processed to obtain a third living body detection result of the target person. The living body detection device performs living body detection processing on at least two first images to be processed to obtain at least two third living body detection results of the target person.

For example, the at least two first images to be processed include a first image to be processed a and a first image to be processed b. The living body detecting device performs the living body detecting process on the first image a to be processed to obtain a third living body detecting result A, and the living body detecting device performs the living body detecting process on the first image B to be processed to obtain a third living body detecting result B. At this time, the at least two third in-vivo detection results include a third in-vivo detection result a and a third in-vivo detection result B.

17. And obtaining a first living body detection result of the target person according to the at least two third living body detection results.

In one possible implementation manner, the third living body detection results each include a living body probability that the target person is a living body. The living body detecting device determines the third living body detection result in which the probability of the included living body is the largest as a third intermediate living body detection result. Determining that the first living body detection result is that the target person is a living body in the case that the living body probability of the third intermediate living body detection result is greater than the living body detection threshold; in a case where the living body probability of the third intermediate living body detection result is less than or equal to the living body detection threshold, it is determined that the first living body detection result of the target person is the target person as a non-living body.

As an alternative embodiment, the living body detecting apparatus performs the following steps in the process of performing step 17:

18. a third threshold is obtained.

In the embodiment of the present application, the effect of the third threshold is different from the effect of the first threshold, the effect of the second threshold, the effect of the third threshold, and the effect of the fourth threshold. The value of the third threshold may be the same as or different from the value of the first threshold. The value of the third threshold may be the same as or different from the value of the second threshold. The value of the third threshold and the value of the fourth threshold may be the same or different. The third threshold is a positive number.

In one possible implementation, the living body detecting device acquires the third threshold by receiving the third threshold input by the user through the input component.

In another possible implementation manner, the living body detecting device acquires the third threshold value by receiving the third threshold value transmitted by the terminal.

19. And determining a third number of second positive results in the at least two third in-vivo detection results, wherein the second positive results are third in-vivo detection results passed by the in-vivo detection.

20. And determining a second ratio of the third number and a fourth number, wherein the fourth number is the number of the third living body detection results.

21. And obtaining a first living body detection result of the target person according to the second ratio and the third threshold.

The larger the proportion of the second positive result of the at least two third living body detection results is, the higher the living body probability that the target person is a living body is indicated. In this embodiment, the second ratio represents a ratio of the second positive result to at least two third in-vivo detection results, and the third threshold is a criterion for determining whether the second ratio is large or small, that is, the third threshold can be used to determine whether the second ratio is large or small. If the second ratio is large, the ratio of the second positive result in the at least two third living body detection results is large, and the target person is a living body; if the second ratio is small, it indicates that the ratio of the second positive results in the at least two third living body detection results is small, and the target person is a non-living body.

In a possible implementation manner, the living body detection device determines that the second ratio is large when the second ratio is larger than a third threshold, and further determines that the first living body detection result is that the target person is a living body; the living body detection device determines that the second ratio is small when the second ratio is less than or equal to the third threshold, and further determines that the first living body detection result is that the target person is a non-living body.

In another possible implementation manner, the living body detection device determines that the second ratio is large when the second ratio is greater than or equal to a third threshold, and further determines that the first living body detection result is that the target person is a living body; and under the condition that the second ratio is smaller than the third threshold value, the living body detection device determines that the second ratio is small, and further determines that the first living body detection result is that the target person is a non-living body.

In yet another possible implementation, the living body detecting device calculates a square of the second ratio to obtain a fourth intermediate value. The living body detection device determines that the second ratio is large under the condition that the fourth intermediate value is larger than the third threshold value, and further determines that the first living body detection result is that the target person is a living body; the living body detection device determines that the second ratio is small when the fourth intermediate value is less than or equal to the third threshold value, and further determines that the first living body detection result is that the target person is a non-living body.

As another alternative embodiment, the living body detecting apparatus performs one of the following steps in the process of performing step 17:

22. and determining that the first live body test result of the target person is a live body, the second positive result is a third live body test result that the live body test is passed, and the negative result is a third live body test result that the live body test is not passed, in a case where the number of second positive results is greater than the number of negative results among the at least two third live body test results.

23. And determining that the target person is a non-living body as the first living body detection result of the target person in a case where the number of second positive results of the at least two third living body detection results is less than or equal to the negative results.

For example, the at least two third living body detection results include a third living body detection result a, a third living body detection result b, and a third living body detection result c, wherein the third living body detection result a is that the living body detection is failed (i.e., the target person is a non-living body), the third living body detection result b is that the living body detection is passed (i.e., the target person is a living body), and the third living body detection result c is that the living body detection is failed (i.e., the target person is a non-living body).

At this time, the third live body test result a and the third live body test result c are both negative results, and the third live body test result b is the second positive result. Since the number of the second positive results is smaller than the number of the negative results, the living body detecting apparatus determines that the first living body detection result is the target person as the non-living body by performing step 24.

For another example, the at least two third biological detection results include a third biological detection result a, a third biological detection result b, and a third biological detection result c, where the third biological detection result a is a passage of the biological detection (i.e., the target person is a living body), the third biological detection result b is a passage of the biological detection (i.e., the target person is a living body), and the third biological detection result c is a non-passage of the biological detection (i.e., the target person is a non-living body).

At this time, the third live body test result a and the third live body test result b are both the second positive result, and the third live body test result c is the negative result. Since the number of the second positive results is larger than the number of the negative results, the living body detecting apparatus determines that the first living body detection result is that the target person is a living body by performing step 23.

As an alternative embodiment, the living body detecting apparatus, after determining that the living body detection state includes an abnormality, further performs the following steps before performing step 16:

24. the first living body detection threshold of the living body detection process is increased to obtain a second living body detection threshold.

In the present embodiment, the living body detecting apparatus performs living body detection processing on the image to obtain the living body probability that the person to be detected in the image is a living body. Determining that the person to be detected is a living body under the condition that the probability is greater than a first living body detection threshold value; and determining that the person to be detected is a non-living body in the case that the probability is less than or equal to the first living body detection threshold.

That is, in the present embodiment, the first live body detection threshold is a criterion for determining whether or not the human being to be detected is a live body in the live body detection processing. Specifically, the first living body detection threshold is a basis for judging whether the person to be detected is a living body by the living body detection device under the condition that the living body detection state is not determined; the first living body detection threshold value is either a criterion for the living body detection device to determine whether the person to be detected is a living body in a case where it is determined that the living body detection state includes normality. Optionally, the value of the first in-vivo detection threshold is a positive number smaller than 1.

The living body detection device obtains the second living body detection threshold value by increasing the first living body detection threshold value, and increases the basis for judging whether the person to be detected is a living body.

After executing step 24, the living body detecting apparatus executes the following steps in executing step 16:

25. and performing living body detection processing on the at least two first images to be processed according to the second living body detection threshold to obtain at least two third living body detection results of the target person.

In this step, the living body detecting device uses the second living body detection threshold as a criterion for determining whether or not the target person is a living body. Specifically, the living body detection device obtains a living body probability that the target person in the image is a living body by performing living body detection processing on the image. Determining that the target person is a living body in a case where the probability is greater than a second living body detection threshold; in a case where the probability is less than or equal to the second living body detection threshold value, the target person is determined to be a non-living body.

The living body detecting device obtains a second living body detection threshold by increasing the first living body detection threshold in a case where it is determined that the living body detection state includes an abnormality, and uses the second living body detection threshold as a basis for determining whether or not the target person is a living body. In this way, the living body detecting apparatus can improve the living body detection criterion by using the second living body detection threshold as a criterion for determining whether the target person is a living body, thereby improving the accuracy of the third living body detection result.

As an optional implementation manner, the living body detecting device includes an entrance guard device, and the at least two first images to be processed each include a face of the target person. In this embodiment, the entrance guard device further performs, in a case where it is determined that the living body detection state includes an abnormality, the steps of:

26. and increasing the first human face similarity threshold value of the human face comparison to obtain a second human face similarity threshold value.

In this embodiment, the access control device may determine whether the target person is a registered person by comparing the face image of the target person with at least one registered face image, where the registered person includes a trusted person, and the registered face image includes a face image of the registered person.

In the present embodiment, the first face similarity threshold is a criterion for determining whether or not the target person is a registered person in the face comparison. Specifically, the door access device compares the image of the target person with at least one registered face image to obtain the face similarity between the target person and the registered person. Determining that the target character is a registered character under the condition that the face similarity is larger than a first face similarity threshold value; in a case where the face similarity is less than or equal to the first face similarity threshold value, it is determined that the target person is not a registered person. Optionally, the first face similarity threshold value is a positive number smaller than 1.

The entrance guard device obtains a second face similarity threshold by increasing the first face similarity threshold, namely the second face similarity threshold is larger than the first face similarity threshold.

27. At least one registered face image is acquired.

In this embodiment, the registered face images are face images of trusted people, and at least one registered face image includes face images of all trusted people.

For example, the access control device is an access control device of company a, the company a has three employees of zhang san, lie si and wang wu, and the registered face images include a face image of zhang san, a face image of lie si and a face image of wang wu.

In one possible implementation, the living body detecting device takes at least one registered image input by the user through the input component as the at least one registered image.

In another possible implementation manner, the entrance guard device receives at least one registered face image sent by the terminal as at least one registered image.

It should be understood that, in the embodiment of the present application, the access control device does not execute step 26 and step 27 in sequence, and the access control device may execute step 26 and then step 27, may execute step 27 and then step 26, and may execute step 26 and step 27 at the same time.

28. And comparing the face image to be detected with the at least one registered face image according to the second face similarity threshold to obtain a face comparison result, wherein the face image to be detected is any one of the at least two first images to be processed.

In this step, the door access device uses the second face similarity threshold as a basis for determining whether the target person is a registered person. Specifically, the entrance guard device compares the face image to be detected with at least one registered face image to obtain the face similarity between the target person and the registered person. Determining that the target character is a registered character under the condition that the face similarity is larger than a second face similarity threshold value; in the case where the face similarity is less than or equal to the second face similarity threshold value, it is determined that the target person is not a registered person. Optionally, the value of the second face similarity threshold is a positive number smaller than 1.

29. And determining the passing state of the target person in the access control device according to the face comparison result and the first living body detection result.

In a possible implementation manner, the entrance guard device determines that the passing state of the target person in the entrance guard device is not passable under the condition that the face comparison result includes that no image matched with the face image to be detected exists in at least one registered face image. And the entrance guard device determines that the passing state of the target person in the entrance guard device is not passable under the condition that the first living body detection result comprises that the target person is a non-living body. And the entrance guard device determines that the passing state of the target person in the entrance guard device is passable under the condition that the first living body detection result comprises that the target person is a living body and the face comparison result comprises that the image matched with the face image to be detected exists in at least one registered face image.

The entrance guard device obtains a second face similarity threshold by increasing the first face similarity threshold when the living body detection state includes abnormality, and uses the second face similarity threshold as a basis for judging whether the target person is a registered person. Therefore, the entrance guard device can improve the face comparison standard by taking the second face similarity threshold as a basis for judging whether the target figure is the registered figure, so that the accuracy of the face comparison result is improved, the identification accuracy of the entrance guard device is improved, and the safety in an abnormal living body detection state is improved.

As an alternative embodiment, the access control device performs the following steps in the process of performing step 28:

30. at least one reference face image containing a reference face is selected from the at least one registered face image.

Under the condition that the access control device is abnormal, the access control device can be attacked by a non-living body at any time, so that the access control device only allows authorized persons to pass through, and the identification accuracy of the access control device can be improved. The access control device further selects a face image of an authorized person (i.e., at least one reference face image containing a reference face) from the at least one registered face image for subsequent face comparison, so as to improve the identification accuracy of the access control device.

31. And comparing the face image to be detected with the image in the at least one reference face image to obtain the face comparison result.

In the embodiment of the application, because the at least one reference face image contains the authorized person, the face comparison between the face image to be detected and the at least one reference face image can determine whether the face image to be detected contains the authorized person, that is, whether the target person is the authorized person. For example, the at least one reference face image includes a face image of zhang san and a face image of lie xi, and the authorized person includes zhang san and lie xi. And comparing the face image to be detected with the reference face image set to determine whether the face image to be detected contains Zhang III or not and determine whether the face image to be detected contains Li IV or not.

For example, the access control device is an access control device of company a, and company a has three employees of company a, company b, and company c, wherein company a is responsible for company a. Company A stipulates that only Zhang III is allowed to enter the company when an abnormal condition occurs, and further Zhang III is determined to be an authorized person. Then, the entrance guard device selects three face images from the registered face images as reference face images when determining that the living body detection state includes abnormality.

In the embodiment, the entrance guard device selects the face image of the authorized person from the registered face images as the reference face image under the condition that the living body detection state is determined to be abnormal, and the face comparison result is obtained by performing face comparison on the reference face image and the face image to be detected, so that the risk that the entrance guard device is attacked by a non-living body when the living body detection state is abnormal is reduced, and the potential safety hazard is reduced.

Optionally, if the access control device obtains the face comparison result through the step 30 and the step 31, the access control device determines that the passing state of the target person in the access control device is not passable under the condition that the face comparison result includes at least one reference face image without an image matched with the face image to be detected. And the entrance guard device determines that the passing state of the target person in the entrance guard device is not passable under the condition that the first living body detection result comprises that the target person is a non-living body. And the entrance guard device determines that the passing state of the target person in the entrance guard device is passable under the condition that the first living body detection result comprises that the target person is a living body and the face comparison result comprises that the image matched with the face image to be detected exists in at least one reference face image.

As an optional implementation manner, before performing step 28, the access control device further performs the following steps:

32. and obtaining the effective time length.

In one implementation of obtaining the validity duration, the access control device receives the validity duration input by the user through the input component.

In another implementation manner of obtaining the valid duration, the access control device receives the valid duration sent by the control terminal.

After step 32, the access control device performs the following steps in the process of step 28:

33. and in the effective time period, performing face comparison on the face image to be detected and the image in the at least one reference face image to obtain the face comparison result, wherein the starting time of the effective time period is the time for determining that the living body detection state comprises the abnormality, and the duration of the effective time period is the effective duration.

34. And comparing the face image to be detected with at least one registered face image to obtain a face comparison result outside the effective time period.

For example, the access control device determines that the living body detection state includes an abnormality at 9 o' clock, 20 min, 15 sec at 21 st 2021. Assume that the validity period is 2 hours. Then the door control device performs face comparison between the face image to be detected and the image in at least one reference face image within 20 minutes 15 seconds from 9 point at 21 st/11 point at 20 minutes 15 s/2021 st/6 st/21 st to obtain a face comparison result. And from 11 o' clock, 20 min 16 sec at 6/21/2021, comparing the face image to be detected with at least one registered face image to obtain a face comparison result.

Considering that the non-living body attack of a person on the access control device is generally concentrated in a period of time, under the condition that the living body detection state includes abnormity, the face comparison result is obtained by comparing the face image to be detected with the image in at least one reference face image, the probability that the access control device is subjected to the non-living body attack can be reduced, and therefore the safety is improved.

And considering that the duration of the non-living attack is short, if a face comparison result is obtained by comparing the face image to be detected with the image in the at least one reference face image, trusted people except the target people cannot normally pass through the access control device. Therefore, the entrance guard device compares the face of the person to be detected with the image in the at least one reference face image within the effective time to obtain the face comparison result, so that the potential safety hazard can be reduced, the identification accuracy of the entrance guard device can be improved, and the user experience is improved.

As an alternative embodiment, the living body detecting apparatus performs the following steps in a case where the living body detection state includes an abnormal level:

35. and determining a target abnormal living body detection scheme according to the abnormal grade.

In the present embodiment, the abnormal biometric scheme is a biometric scheme executed in a case where the biometric state includes an abnormality. Due to the fact that the probability that the living body detection device is subjected to non-living body attack is different when the abnormal levels are different, the living body detection device determines a target abnormal living body detection scheme according to the abnormal levels, and the living body detection accuracy can be improved.

Optionally, the higher the abnormality degree represented by the abnormality grade is, the higher the living body detection standard of the target abnormal living body detection scheme is.

In one possible implementation, the living body detecting device acquires a fourth mapping relationship between the abnormality level and the abnormal living body detecting pattern. The living body detection device determines a target abnormal living body detection scheme according to the fourth mapping relation and the abnormal level of the living body detection state.

After executing step 35, the living body detecting apparatus executes the following steps in executing step 17:

36. and obtaining a first living body detection result of the target person according to the target abnormal living body detection scheme and the at least two third living body detection results.

For example, assume that the anomaly level includes one of: generally, higher, and particularly, wherein a higher degree of abnormality is characterized in particular than a higher degree of abnormality is characterized in particular, and a higher degree of abnormality is characterized in general than a higher degree of abnormality is characterized in general.

In the case where the abnormality level includes the general, the target abnormal living body detection scheme includes: determining that the first living body detection result is that the target person is a living body in a case where the third number is greater than the number of negative results; in a case where the third number is less than or equal to the number of negative results, it is determined that the first living body detection result is the target person as a non-living body. Wherein the third number is a number of second positive results of the at least two third in-vivo detection results, the second positive results are third in-vivo detection results that the in-vivo detection passes, and the negative results are third in-vivo detection results that the in-vivo detection fails.

In the case where the abnormality level includes a high level, the target abnormal living body detection scheme includes: determining that the first living body detection result is that the target person is a living body if the difference between the third number and the number of the negative results is greater than 2; in a case where a difference between the third number and the number of negative results is less than or equal to 2, it is determined that the first living body detection result is the target person as a non-living body.

In the case where the abnormality level includes a special case, the target abnormal living body detection scheme includes: determining that the first living body detection result is that the target person is a living body, in a case where a difference between the third number and the number of negative results is greater than 3; in a case where a difference between the third number and the number of negative results is less than or equal to 3, it is determined that the first living body detection result is the target person as a non-living body.

In steps 35 and 36, the living body detecting device determines the abnormal living body detecting pattern in accordance with the abnormality level and the pair of abnormal living body detecting patterns, thereby improving the accuracy of the first living body detecting result.

As an alternative embodiment, the living body detecting apparatus further performs the steps of:

37. and sending a prompt instruction to a management terminal when the living body detection state comprises the abnormality, wherein the prompt instruction carries information that the detection state comprises the abnormality.

In this embodiment, the prompt instruction may be used to prompt the relevant person that the living body detection state includes an abnormality through the management terminal. In this way, relevant personnel can take corresponding measures to avoid the living body detection device from being attacked by a non-living body.

In one possible implementation, the liveness detection device includes a camera. And the living body detection device sends the video acquired by the camera in real time to the management terminal under the condition of detecting the remote video instruction sent aiming at the prompt instruction.

In one possible implementation, the liveness detection device includes a speaker. When receiving the voice data transmitted for the prompt instruction, the living body detection device outputs the voice data through the speaker.

For example, the relevant administrator knows that the living body detection state of the living body detection device includes an abnormality through the presentation instruction acquired by the management terminal, and further transmits voice data to the living body detection device through the management terminal to acquire a person who repels a non-living body attack on the living body detection device. The living body detecting device further outputs the voice data through a speaker in a case where the voice data is received.

As an optional implementation mode, the prompt instruction is used for instructing the management terminal to output alarm information so as to prompt relevant personnel to timely deal with the condition that the living body detection state of the living body detection device comprises an abnormality.

As an alternative embodiment, the living body detecting apparatus outputs alarm information in a case where the living body detection state includes an abnormality.

As an optional implementation manner, the entrance guard device stops performing face recognition on the target person when determining that the abnormality level of the living body detection state is the preset abnormality level. In this embodiment, the access control device stops face recognition of the target person, i.e. the access control device stops using the face recognition related function.

If the preset level is special, the entrance guard device stops face recognition of the target person under the condition that the abnormal level of the living body detection state is special.

In this embodiment, the entrance guard device stops using the face recognition function when determining that the abnormality level of the living body detection state is the preset level, and further prohibits any person from passing, thereby reducing the false passing rate. Wherein, the wrong passage means that the entrance guard device determines that people except the target person can pass through.

As an alternative embodiment, the entrance guard device stops using the face recognition function and prompts the target person to input identification information or enter using a key in the case where it is determined that the living body detection state includes an abnormality.

In one possible implementation manner, the inputting of the identity information may be placing a card carrying the identity information in a card identification area, wherein the card carrying the identity information includes one or more of the following: identity card, entrance guard card, worker's card. Therefore, the access control device can acquire the identity information of the target person through the identification card so as to determine whether the target person can pass through.

In another possible implementation manner, the step of inputting the identity information may be that a two-dimensional code carrying the identity information is placed in a two-dimensional code identification area. Therefore, the access control device can acquire the identity information of the target person by identifying the two-dimensional code, so as to determine whether the target person can pass through.

In this embodiment, the entrance guard device stops using the face recognition function in a case where it is determined that the living body detection state includes an abnormality. Therefore, the user cannot pass through the entrance guard device through face recognition, and further cannot attack the entrance guard device by a non-living body, so that the false recognition rate of living body detection is reduced, and the recognition accuracy of the entrance guard device is improved.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

The method of the embodiments of the present application is set forth above in detail and the apparatus of the embodiments of the present application is provided below.

Referring to fig. 5, fig. 5 is a schematic structural diagram of a living body detecting apparatus 1 according to an embodiment of the present disclosure, where the living body detecting apparatus 1 includes an obtaining unit 11 and a first processing unit 12. Optionally, the living body detecting device 1 further includes a second processing unit 13. Wherein:

an acquisition unit 11 configured to acquire a living body detection state of an environment in which the living body detection apparatus 1 is located, the living body detection state including a normal state indicating that the environment in which the living body detection apparatus 1 is located is not in a state of being attacked by a non-living body or an abnormality indicating that the environment in which the living body detection apparatus 1 is located is in a state of being attacked by a non-living body;

the acquiring unit 11 is further configured to acquire at least two first images to be processed, where the living body detection state of the environment in which the living body detection device 1 is located includes the abnormality, and the at least two first images to be processed each include a target person;

the first processing unit 12 is configured to obtain a first living body detection result of the target person according to at least two first images to be processed.

With reference to any embodiment of the present application, the obtaining unit 11 is configured to:

In combination with any embodiment of the present application, the first processing unit 12 is configured to:

acquiring a third threshold;

In combination with any one of the embodiments of the present application, the living body detecting apparatus 1 further includes: a second processing unit 13, configured to, after determining that the living body detection state includes the abnormality, increase a first living body detection threshold of the living body detection processing to obtain a second living body detection threshold before performing the living body detection processing on the at least two first images to be processed to obtain at least two third living body detection results of the target person;

the first processing unit 12 is configured to:

With reference to any embodiment of the present application, the living body detecting apparatus 1 includes an access control apparatus, and the at least two first images to be processed each include a face of the target person; in a case that it is determined that the living body detection state includes the abnormality, the first processing unit 12 is further configured to increase a first face similarity threshold of face comparison to obtain a second face similarity threshold;

the acquiring unit 11 is further configured to acquire at least one registered face image;

the first processing unit 12 is further configured to perform face comparison on the to-be-detected face image and the at least one registered face image according to the second face similarity threshold value to obtain a face comparison result, where the to-be-detected face image is any one of the at least two first to-be-processed images;

the first processing unit 12 is further configured to determine a passing state of the target person in the access control device according to the face comparison result and the first living body detection result.

In this embodiment, the obtaining unit 11 may be a data interface, and each of the first processing unit 12 and the second processing unit 13 may be a processor.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present application may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Fig. 6 is a schematic hardware structure diagram of a living body detection apparatus according to an embodiment of the present disclosure. The biopsy device 2 comprises a processor 21, a memory 22, an input device 23, and an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are coupled by a connector, which includes various interfaces, transmission lines or buses, etc., and the embodiment of the present application is not limited thereto. It should be appreciated that in various embodiments of the present application, coupled refers to being interconnected in a particular manner, including being directly connected or indirectly connected through other devices, such as through various interfaces, transmission lines, buses, and the like.

The processor 21 may be one or more Graphics Processing Units (GPUs), and in the case that the processor 21 is one GPU, the GPU may be a single-core GPU or a multi-core GPU. Alternatively, the processor 21 may be a processor group composed of a plurality of GPUs, and the plurality of processors are coupled to each other through one or more buses. Alternatively, the processor may be other types of processors, and the like, and the embodiments of the present application are not limited.

Memory 22 may be used to store computer program instructions, as well as various types of computer program code for executing the program code of aspects of the present application. Alternatively, the memory includes, but is not limited to, Random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for associated instructions and data.

The input means 23 are for inputting data and/or signals and the output means 24 are for outputting data and/or signals. The input device 23 and the output device 24 may be separate devices or may be an integral device.

It is understood that, in the embodiment of the present application, the memory 22 may be used to store not only the relevant instructions, but also relevant data, for example, the memory 22 may be used to store at least two first images to be processed acquired through the input device 23, or the memory 22 may be used to store the first living body detection result obtained through the processor 21, and the like, and the embodiment of the present application is not limited to the data specifically stored in the memory.

It will be appreciated that fig. 6 shows only a simplified design of a living body detection device. In practical applications, the biopsy devices may also respectively include other necessary components, including but not limited to any number of input/output devices, processors, memories, etc., and all biopsy devices that can implement the embodiments of the present application are within the scope of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It is also clear to those skilled in the art that the descriptions of the various embodiments of the present application have different emphasis, and for convenience and brevity of description, the same or similar parts may not be repeated in different embodiments, so that the parts that are not described or not described in detail in a certain embodiment may refer to the descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in or transmitted over a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)), or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the above method embodiments. And the aforementioned storage medium includes: various media that can store program codes, such as a read-only memory (ROM) or a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Claims

1. A method for in vivo testing, the method being applied to a biopsy device, the method comprising:

2. The method of claim 1, wherein the acquiring the in-vivo detection state of the environment in which the in-vivo detection device is located comprises:

3. The method of claim 1, wherein the acquiring the in-vivo detection state of the environment in which the in-vivo detection device is located comprises:

4. The method according to any one of claims 1 to 3, wherein obtaining the first living body detection result of the target person based on at least two first images to be processed comprises:

5. The method of claim 4, wherein obtaining the first in-vivo detection result of the target person according to the at least two third in-vivo detection results comprises:

acquiring a third threshold;

6. The method of claim 4, wherein obtaining the first in-vivo detection result of the target person according to the at least two third in-vivo detection results comprises:

7. The method according to any one of claims 4 to 6, wherein after determining that the living body detection state includes the abnormality, before the living body detection processing is performed on the at least two first images to be processed to obtain at least two third living body detection results of the target person, the method further comprises:

8. The method according to any one of claims 4 to 7, wherein the living body detection device comprises an entrance guard device, and the at least two first images to be processed each comprise a face of the target person; in a case where it is determined that the living body detection state includes the abnormality, the method further includes:

acquiring at least one registered face image;

9. The method of claim 8, wherein the determining the passing state of the target person in the access control device according to the face comparison result and the first living body detection result comprises:

10. A living body detecting device, characterized in that the living body detecting device comprises:

11. An electronic device, comprising: a processor and a memory for storing computer program code comprising computer instructions which, when executed by the processor, cause the electronic device to perform the method of any of claims 1 to 9.

12. A computer-readable storage medium, in which a computer program is stored, which computer program comprises program instructions which, if executed by a processor, cause the processor to carry out the method of any one of claims 1 to 9.