CN113569622A

CN113569622A - Living body detection method, device and system based on webpage and electronic equipment

Info

Publication number: CN113569622A
Application number: CN202110645515.7A
Authority: CN
Inventors: 时旭
Original assignee: Beijing Kuangshi Technology Co Ltd; Beijing Megvii Technology Co Ltd
Current assignee: Beijing Kuangshi Technology Co Ltd; Beijing Megvii Technology Co Ltd
Priority date: 2021-06-09
Filing date: 2021-06-09
Publication date: 2021-10-29

Abstract

The invention relates to a webpage-based in-vivo detection method, a webpage-based in-vivo detection device, a webpage-based in-vivo detection system and electronic equipment, and belongs to the field of in-vivo detection, wherein the method comprises the following steps: sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to a client; and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream. In the process, the dazzling living body detection is adopted, so that the situation that a user bypasses silent living body detection or double-angle living body detection by hijacking a camera can be avoided, and the safety of living body detection verification can be improved; in addition, because dazzle various live body detection and need not the language of discernment user, consequently, also can avoid the lip language live body detection and can not discern the user experience problem that the dialect arouses, and then can promote user experience.

Description

Living body detection method, device and system based on webpage and electronic equipment

Technical Field

The application belongs to the field of in-vivo detection, and particularly relates to a webpage-based in-vivo detection method, device and system and an electronic device.

Background

The living body detection is involved in various application scenes, such as a face authentication recognition scene, a security check scene, and the like.

As the technology advances, more and more liveness detection is implemented based on web pages, so that in the prior art, there are various web page-based liveness detection methods, such as web page-based silent liveness detection, web page-based lip language liveness detection, web page-based dual-angle liveness detection, and the like.

However, the above-mentioned web-based biopsy method has many disadvantages.

For example, when a user hijacks a camera, the silence live body detection can be bypassed through a video recorded in advance; then, for example, after the user hijacks the camera, the double-angle living body detection can be bypassed through two pictures which are shot in advance; for another example, when the user reads a character prompted by lip liveness detection in the form of a dialect, the lip liveness detection cannot accurately identify the dialect of the user, resulting in a failure in identification.

Therefore, the living body detection method based on the webpage in the prior art has the defects of low safety and influence on user experience.

Disclosure of Invention

In view of this, an object of the present application is to provide a web-based in-vivo detection method, apparatus, system and electronic device, which are beneficial to improving the security of in-vivo detection verification and user experience.

The embodiment of the application is realized as follows:

in a first aspect, an embodiment of the present application provides a living body detection method based on a web page, which is applied to a backend server, and the method includes: sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to a client; and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

In the process, the colorful live body detection is adopted, so that the situation that a user bypasses silent live body detection or double-angle live body detection in a camera hijacking mode can be avoided, and the safety of live body detection verification can be improved; in addition, because dazzle various live body detection and need not the language of discernment user, consequently, also can avoid the lip language live body detection and can not discern the user experience problem that the dialect arouses, and then can promote user experience.

In addition, it is worth pointing out that a large amount of calculation is required in the process of dazzling living body detection, and certain requirements are required on hardware resources. In the embodiment of the present application, the live body detection is implemented based on a web page, that is, the process of the colorful live body detection is handed to the back-end server to be executed in the embodiment of the present application, so that the hardware requirement of the whole live body detection process on the electronic device where the client is located can be reduced, and the detection effect difference caused by the difference of hardware devices can also be avoided. Moreover, in the above process, since the process related to the calculation is almost executed by the back-end server, and the work related to the client is mainly to collect the colorful video stream, when the living body detection model needs to be optimized and updated, corresponding changes are mainly performed on the back-end server side without changing the client side, so that the living body detection method based on the web page provided by the embodiment of the application can also reduce the dependency on the client and the user when the living body detection model is optimized.

With reference to the embodiment of the first aspect, in a possible implementation manner, before the sending the dazzle color video stream capture signal to the client, the method further includes: sending a first video stream acquisition signal to the client; receiving a first video stream, and carrying out gesture detection on the object to be detected based on the first video stream to obtain a gesture detection result;

correspondingly, sending the colorful video stream collecting signal to the client comprises: and when the gesture detection result meets the gesture requirement, sending the colorful video stream acquisition signal to the client.

In the above embodiment, before the living body detection is performed on the object to be detected based on the colorful video stream, the posture of the object to be detected is detected, and the colorful living body detection is performed when it is determined that the posture detection result of the object to be detected meets the posture requirement, which is beneficial to improving the passing rate of the colorful living body detection.

With reference to the embodiment of the first aspect, in one possible implementation manner, the method further includes: and when the gesture detection result is determined not to meet the gesture requirement, sending the gesture detection result and/or gesture adjustment prompt information to the client.

In the above embodiment, when it is determined that the posture detection result of the object to be detected does not meet the posture requirement, feedback is performed to the client, so that the client can take corresponding measures to improve the posture of the object to be detected, and further, the smoothness in subsequent living body detection is favorably improved, and the conformity between the living body detection result and the fact is favorably improved.

With reference to the embodiment of the first aspect, in a possible implementation manner, the receiving a first video stream includes: receiving the first video stream in real time based on a point-to-point connection channel established between the client and the client;

and/or, the receiving of the dazzle color video stream comprises: and receiving the colorful video stream in real time based on a point-to-point connection channel established between the colorful video stream and the client.

In the embodiment, the video stream is transmitted between the client and the back-end server through the point-to-point connection channel, so that the transmission time can be saved, real-time detection is realized for a user, and the improvement of user experience is facilitated.

With reference to the embodiment of the first aspect, in a possible implementation manner, before the performing the dazzle color live detection on the object to be detected based on the dazzle color video stream, the method further includes: and carrying out posture detection on the object to be detected based on the colorful video stream, and determining that the object to be detected meets the posture requirement represented by a posture detection result obtained based on the colorful video stream.

In the embodiment, after the gesture detection result representation of the object to be detected in the colorful video stream is determined to enable the object to be detected to meet the gesture requirement, colorful living body detection is conducted on the living body to be detected according to the colorful video stream, and therefore detection accuracy is guaranteed.

With reference to the embodiment of the first aspect, in a possible implementation manner, the receiving a colorful video stream and performing colorful live detection on an object to be detected based on the colorful video stream includes: and after the colorful video stream is received for a fixed time, colorful living body detection is carried out on the object to be detected based on the colorful video stream. Based on this, be favorable to the acquisition progress that the various video stream of dazzling can be obtained to the rear end server, make the live body detection preparation work, guarantee the data synchronism between rear end server and the client.

In a second aspect, an embodiment of the present application provides a web-based liveness detection method, which is applied to a client, and the method includes: receiving configuration information comprising a colorful color sequence and a colorful video stream acquisition signal; responding to the colorful video stream acquisition signal, and when determining that the colorful video stream acquisition signal has a camera calling right, calling the camera to acquire a colorful video stream comprising the colorful color sequence; and sending the colorful video stream to a back-end server.

With reference to the second aspect, in one possible implementation manner, the method further includes: when the colorful video stream starts to be collected, sending a collection starting signal to the back-end server; and/or sending a collection finishing signal to the back-end server when the collection of the colorful video stream is finished.

In the process, the client sends the start acquisition signal and/or the end acquisition signal to the back-end server, so that the back-end server can acquire the acquisition progress of the colorful video stream, the data synchronism between the back-end server and the client is ensured, the back-end server can make in advance the preparation work of the living body detection, and the improvement of the efficiency of the living body detection is facilitated.

With reference to the second aspect, in a possible implementation manner, before the receiving the configuration information including the sequence of the dazzling colors, the method includes: establishing long connection with a signaling server; and exchanging media information and network information with the back-end server through the signaling server, and establishing a point-to-point connection channel between the back-end server and the signaling server based on the media information and the network information.

With reference to the second aspect, in a possible implementation manner, the receiving configuration information including a sequence of dazzling colors includes: receiving, by the signaling server, configuration information including the sequence of dazzle colors;

and/or, the sending the colorful video stream to a back-end server comprises: and sending the colorful video stream to the back-end server through the point-to-point connecting channel.

In a third aspect, an embodiment of the present application provides a web-based liveness detection apparatus, including: a first transmitting module and a living body detecting module.

The system comprises a first sending module, a second sending module and a display module, wherein the first sending module is used for sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to a client;

and the living body detection module is used for receiving the colorful video stream and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

With reference to the third aspect, in a possible implementation manner, the apparatus further includes a gesture detection module.

The first sending module is further configured to send a first video stream acquisition signal to the client;

the gesture detection module is used for receiving a first video stream and carrying out gesture detection on the object to be detected based on the first video stream to obtain a gesture detection result;

correspondingly, the first sending module is configured to send the dazzling video stream collecting signal to the client when it is determined that the gesture detection result meets the gesture requirement.

With reference to the embodiment of the third aspect, in a possible implementation manner, the first sending module is further configured to send the posture detection result and/or posture adjustment prompt information to the client when it is determined that the posture detection result does not meet the posture requirement.

With reference to the third aspect, in a possible implementation manner, the liveness detection module is configured to receive the first video stream in real time based on a point-to-point connection channel established with the client; and/or the presence of a gas in the gas,

and the gesture detection module is used for receiving the colorful video stream in real time based on a point-to-point connection channel established between the gesture detection module and the client.

With reference to the third aspect, in a possible implementation manner, the living body detection module is configured to perform posture detection on the object to be detected based on the colorful video stream, and determine that a posture detection result obtained based on the colorful video stream represents that the object to be detected meets the posture requirement.

With reference to the third aspect, in a possible implementation manner, the living body detection module is configured to, after receiving the colorful video stream of a fixed duration, perform colorful living body detection on the object to be detected based on the colorful video stream.

In a fourth aspect, an embodiment of the present application provides a web-based liveness detection apparatus, including: the device comprises a receiving module, an acquisition module and a second sending module.

The receiving module is used for receiving configuration information comprising a colorful color sequence and a colorful video stream acquisition signal;

the acquisition module is used for responding to the colorful video stream acquisition signal and calling the camera to acquire a colorful video stream comprising the colorful color sequence when the camera calling right is determined to be possessed by the camera;

and the second sending module is used for sending the colorful video stream to a server.

With reference to the embodiment of the fourth aspect, in a possible implementation manner, the second sending module is further configured to send a start-to-collect signal to the back-end server when the colorful video stream starts to be collected, and/or send an end-to-collect signal to the back-end server when the colorful video stream is collected.

With reference to the embodiment of the fourth aspect, in a possible implementation manner, the apparatus further includes an establishing module, configured to establish a long connection with a signaling server; and exchanging media information and network information with the back-end server through the signaling server, and establishing a point-to-point connection channel between the back-end server and the signaling server based on the media information and the network information.

With reference to the embodiment of the fourth aspect, in a possible implementation manner, the receiving module is configured to receive, by the signaling server, configuration information including the dazzle color sequence; and/or the presence of a gas in the gas,

and the second sending module is used for sending the colorful video stream to the back-end server through the point-to-point connecting channel.

In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a memory and a processor, the memory and the processor connected; the memory is used for storing programs; the processor calls a program stored in the memory to perform the method of the first aspect embodiment and/or any possible implementation manner of the first aspect embodiment; or to carry out the above-described embodiments of the second aspect and/or the methods provided in connection with any one of the possible implementations of the embodiments of the second aspect.

In a sixth aspect, the present application further provides a non-transitory computer-readable storage medium (hereinafter, referred to as a readable storage medium), on which a computer program is stored, where the computer program is executed by a computer to perform the method in the foregoing first aspect and/or any possible implementation manner of the first aspect; or to carry out the above-described embodiments of the second aspect and/or the methods provided in connection with any one of the possible implementations of the embodiments of the second aspect.

In a seventh aspect, an embodiment of the present application further provides a living body detection system based on a web page, including: client, back-end server and signaling server.

The client is used for initiating a long connection establishment request to the signaling server;

the signaling server is used for responding to the long connection establishment request, establishing long connection with the client and establishing long connection with an available back-end server;

the client is also used for exchanging media information and network information with the available back-end server through the signaling server and establishing a point-to-point connection channel with the available back-end server based on the media information and the network information;

and the back-end server is used for sending the configuration information comprising the colorful color sequence to the client through the signaling server.

In combination with the seventh aspect embodiment, in one possible implementation,

the client is further configured to initiate a long connection closing request to the signaling server after the configuration information including the dazzle color sequence is acquired;

and the signaling server is further used for responding to the long connection closing request and respectively closing the long connection between the client and the available backend server.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The foregoing and other objects, features and advantages of the application will be apparent from the accompanying drawings. Like reference numerals refer to like parts throughout the drawings. The drawings are not intended to be to scale as practical, emphasis instead being placed upon illustrating the subject matter of the present application.

Fig. 1 shows one of flowcharts of a method for detecting a living body based on a web page according to an embodiment of the present application.

Fig. 2 shows a second flowchart of a web-based liveness detection method according to an embodiment of the present application.

Fig. 3 shows a third flowchart of a method for detecting a living body based on a web page according to an embodiment of the present application.

Fig. 4 illustrates a web-based liveness detection system according to an embodiment of the present application.

Fig. 5 shows one of the block diagrams of the structure of a web-based liveness detection device according to an embodiment of the present application.

Fig. 6 shows a second block diagram of a living body detecting device based on a web page according to an embodiment of the present application.

Fig. 7 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Description of reference numerals:

100-an electronic device; 110-a processor; 120-a memory; 200-web-based liveness detection system; 210-a client; 220-a back-end server; 230-a signaling server; 400-web-based liveness detection device; 410-a first sending module; 420-a liveness detection module; 500-web-based liveness detection device; 510-a receiving module; 520-an acquisition module; 530-second sending module.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, relational terms such as "first," "second," and the like may be used solely in the description herein to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.

In addition, the defects (the defects with low safety and affecting the user experience) existing in the living body detection technology in the prior art are the results obtained after the applicant has practiced and studied carefully, and therefore, the discovery process of the defects and the solutions proposed by the embodiments of the present application in the following for the defects should be considered as contributions of the applicant to the present application.

In order to solve the above problems, embodiments of the present application provide a method, an apparatus, a system and an electronic device for in-vivo detection based on a web page, which are beneficial to improving the security of in-vivo detection verification and user experience.

The technology can be realized by adopting corresponding software, hardware and a combination of software and hardware.

The following describes embodiments of the present application in detail.

Referring to fig. 1, an embodiment of the present application provides a webpage-based dazzling liveness detection method, which is applied to a back-end server, and the method may include the following steps:

step S110: and sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to the client.

Step S120: and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

When the backend server detects that there is a need for live detection, a dazzle color video stream acquisition signal and configuration information including a dazzle color sequence may be sent to a client (in an application embodiment, the client may be a browser).

Optionally, the living body detection requirement may be generated when the user needs to perform authority authentication or face recognition authentication, or may be generated in a security application scenario or other application scenarios with living body detection requirements.

After the client receives the colorful video stream collecting signal and the configuration information comprising the colorful color sequence, the client can call a camera to collect colorful video streams comprising the colorful color sequence, and the colorful video streams are transmitted back to the rear-end server, so that the colorful video streams are subsequently transmitted by the rear-end server to the rear-end server, and colorful living body detection is carried out on the object to be detected.

Wherein, the object to be detected can be human, animal, etc.

It can be seen that the biopsy referred to in the embodiments of the present application is a dazzle color biopsy. Because the colorful live body detection is adopted, and the colorful color sequence in the corresponding colorful video stream during each detection is temporarily determined by the configuration information, the situation that a user bypasses silent live body detection or double-angle live body detection in a way of hijacking a camera can be avoided, and the safety of live body detection verification can be further improved; in addition, because dazzle various live body detection and need not the user and read the characters, consequently, this application embodiment also can avoid the lip language live body detection and can not discern the user experience problem that the dialect arouses, and then can promote user experience.

In addition, it is worth pointing out that a large amount of calculation is required in the process of dazzling living body detection, and accordingly, certain requirements on hardware resources exist in the detection process. In the embodiment of the application, the calculation process of the colorful live body detection is handed to the back-end server to be executed, so that the hardware requirement of the whole live body detection process on the electronic equipment where the client is located can be reduced, and the detection effect difference caused by the difference of hardware equipment can be avoided.

Furthermore, in the embodiment of the present Application, the above-mentioned live body detection is implemented based on a web page, that is, the user can implement the colorful live body detection without installing an APP (Application program).

Alternatively, the web page may be implemented based on the HTML5 language or a later-appearing upgraded HTML language.

The process related to calculation is almost executed by the back-end server, the process related to the client side is mainly used for collecting colorful video streams, and when the living body detection model needs to be optimized and updated, corresponding change is mainly performed on the back-end server side without changing the client side (in the prior art, APP needs to be updated when the living body detection model is optimized and updated), and compared with the prior art, the process that the user installs and updates the APP is omitted.

The following will explain each step in fig. 1 in detail.

In order to avoid failure of subsequent live body detection or an error (not in accordance with the fact) in a live body detection result due to a problem in the posture of the object to be detected in the colorful video stream, in some embodiments, the back-end server may perform posture detection on the object to be detected before sending the colorful video stream acquisition signal to the client, so as to improve the passing rate of the subsequent live body detection.

Correspondingly, the back-end server can send a colorful video stream acquisition signal to the client when determining that the posture detection result of the object to be detected meets the posture requirement, so as to execute a subsequent living body detection process of the object to be detected based on the colorful video stream.

Specifically, when the back-end server detects that there is a need for live body detection, the first video stream capture signal may be sent to the client before the colorful video stream capture signal is sent to the client.

After receiving the first video stream acquisition signal, the client can call the camera to acquire the first video stream and transmit the first video stream to the back-end server.

After receiving the first video stream, the back-end server can perform gesture detection on the object to be detected based on the first video stream, so as to judge whether the gesture of the object to be detected included in the first video stream meets the gesture requirement or not, and obtain a gesture detection result. That is, in the embodiment of the present application, the first video stream is a video stream for performing gesture detection.

Optionally, when performing gesture detection on the object to be detected based on the first video stream, the image frame may be obtained from the first video stream first.

In some embodiments, the back-end server may sequentially perform gesture detection on the object to be detected in each image frame based on each image frame included in the first video stream, because the first video stream itself includes a plurality of consecutive image frames.

Of course, for the back-end server, if the gesture detection is performed on the object to be detected in each image frame in sequence, a large amount of computing resources and computing time are undoubtedly consumed. In order to solve the problem, in some embodiments, the multiple consecutive image frames included in the first video stream include key frames and non-key frames, and based on this, the back-end server may use the key frames included in the first video stream as processing objects to perform pose detection on the object to be detected included in the key frames, so as to reduce the number of subsequent image frames that need to perform pose detection, thereby reducing consumption of computing resources, and also achieving an effect of shortening detection time.

How to identify the key frames and the non-key frames in the first video stream by the backend server is prior art, and redundant description is omitted here.

In addition, in some optional embodiments, the frame rate (for example, set to 10FPS) and the resolution (for example, set to 640 × 480) of the first video stream may also be adjusted at the client side or at the backend server, so that the number of image frames output by the first video stream at each time is controllable, and further, the number of objects detected as the pose of the backend server is controllable, which is beneficial to controlling the computing resources and the computing time.

When the rear-end server detects the posture of the object to be detected based on the image frames, the rear-end server can analyze each obtained image frame so as to obtain the face attributes included in the image frame.

The face attribute may include at least one of sub-attributes such as a face angle, a face size, a face position, and the like, and each sub-attribute has a corresponding attribute threshold range.

After the face attributes are obtained, the back-end server may compare each seed attribute included in the face attributes with a corresponding attribute threshold, so as to obtain a posture detection result.

If each seed attribute included in the face attributes is within the corresponding attribute threshold range, indicating that the gesture detection result represents that the gesture of the object to be detected meets the gesture requirement; otherwise, the gesture detection result indicates that the gesture of the object to be detected does not meet the gesture requirement.

In the foregoing, when it is determined that the gesture detection result represents that the object to be detected meets the gesture requirement, the back-end server sends a colorful video stream acquisition signal to the client.

Certainly, in some embodiments of the application, when the back-end server determines that the gesture detection result represents that the object to be detected does not meet the gesture requirement, the back-end server may further perform feedback to the client, for example, the back-end server may send the gesture detection result to the client, so that the client may take corresponding measures to improve the gesture of the object to be detected, thereby facilitating improvement of smoothness in subsequent living body detection and improvement of conformity between the living body detection result and the fact.

Certainly, in some embodiments, if the gesture detection result represents that the object to be detected does not meet the gesture requirement, the back-end server may further generate corresponding gesture adjustment prompt information according to the gesture detection result, and send the gesture adjustment prompt information to the client, so that the client may display the gesture adjustment prompt information to the object to be detected (i.e., the user), and thus the user may adjust the gesture of the user according to the gesture adjustment prompt information, which is a process of looking into the mirror.

Optionally, the gesture adjustment prompt information may include an adjustment suggestion used for guiding the user to perform gesture adjustment, such as a similar adjustment suggestion of "approach one point", "head up", "far away from one point", so that the user may quickly adjust the gesture of the user to a suitable position, and thus a gesture detection result after subsequent gesture detection can meet a gesture requirement, thereby facilitating improvement of a matching degree of a detection result when a living body is subsequently performed and a fact.

When the user adjusts the posture of the user, the client can collect new first video stream again or continuously and send the new first video stream to the rear-end server for posture detection, and when the rear-end server detects that the posture of the object to be detected meets the posture requirement, colorful video stream collecting signals are sent to the client.

Of course, in some embodiments, when the back-end server determines that the posture detection result of the object to be detected does not meet the posture requirement, the back-end server may feed back both the posture detection result and the posture adjustment prompt information to the client, so that the client may display the posture detection result and the posture adjustment prompt information to the user.

In some embodiments, the back-end server may be after receiving the various video streams of dazzling for a fixed duration, treat the detected object based on dazzling various video streams and dazzle various live body detection again to guarantee that the received various video streams of dazzling include the complete various color sequence of dazzling, prevent that the live body detection that leads to because dazzling various video streams in the disappearance part dazzles various color sequence fails, be favorable to improving the passing rate of dazzling various live body detection.

As for the fixed duration, it is determined by configuration information including a sequence of flare colors.

In some embodiments, after receiving the dazzle color video stream, the back-end server may perform dazzle color live detection on the object to be detected directly based on the dazzle color video stream.

In other embodiments, in the process of performing colorful live body detection on an object to be detected based on the colorful video stream, the position of the object to be detected may change during detection, so that the posture of the object to be detected no longer meets the posture requirement, thereby affecting the accuracy of subsequent live body detection.

In order to avoid this problem, in some embodiments, before the color live body detection is performed on the object to be detected based on the color video stream, the rear-end server may perform the posture detection on the object to be detected according to the color video stream, and after it is determined that the posture detection result representation of the object to be detected in the color video stream satisfies the posture requirement, the color live body detection is performed on the object to be detected according to the color video stream, so that the detection accuracy is favorably ensured.

Of course, the process of performing the gesture detection on the object to be detected according to the colorful video stream is similar to the process of performing the gesture detection on the object to be detected according to the first video stream, and is not repeated here.

In addition, in some embodiments, if the gesture detection result representation obtained by performing gesture detection on the colorful video stream indicates that the object to be detected does not meet the gesture requirement, the back-end server can still send the gesture detection result and/or the gesture adjustment prompt information to the client to prompt the user to perform gesture adjustment, and send the colorful video stream acquisition signal to the client again, so that the back-end server performs colorful living body detection on the object to be detected based on the subsequently received new colorful video stream.

It is worth pointing out that, because dazzle various live body detection algorithm is the more ripe prior art, the specific process that various live body detection was dazzled to the object of waiting to detect in dazzling various video stream is carried out to the back end server based on dazzling various live body detection algorithm, and it is no longer repeated here.

Optionally, after the color live body detection is performed on the object to be detected in the color video stream, the back-end server may send the obtained final live body detection result to the client for display, so that the user may obtain the final live body detection result.

In some embodiments, the interactive content involved in the web-based liveness detection execution process between the back-end server and the client may be transmitted through a long connection channel.

The interactive content includes, but is not limited to, information, signals, instructions, video streams, and the like.

In this embodiment, the backend server may establish a long connection with the client through the signaling server, so that the backend server sends the dazzle color video stream capture signal, the first video stream capture signal (if any), the posture detection result (if any), the posture adjustment prompt information (if any), the final live body detection result (if any), and the configuration information including the dazzle color sequence to the client based on the long connection channel.

Accordingly, the client may package the collected dazzle color video stream and the first video stream (if any) into a file, and send the dazzle color video stream and the first video stream (if any) to the backend server in the form of a file.

In other embodiments, in order to shorten the transmission time of the video stream, the backend server may further have a function of continuously transmitting and receiving data in real time, so as to improve the living body detection efficiency and the user experience. Accordingly, in this embodiment, the back-end server and the client may establish a point-to-point connection through the signaling server.

The point-to-point connection channel is used as a data channel for continuously transmitting video streams so that direct communication can be realized between the client and the back-end server.

In some alternative embodiments, the process of establishing a point-to-point connection between a back-end server and a client may be as follows.

Both the client and the backend server can use a websocket (a protocol for full duplex communication over a single TCP connection) to request the same signaling server, thereby establishing long connections between the same signaling server and the client and the backend server, respectively.

Of course, in some embodiments, multiple backend servers may exist simultaneously. In this embodiment, the client may first request the signaling server using the websocket and establish a long connection, and then find the currently available backend server and establish a long connection with the currently available backend server.

The currently available backend servers may be determined by a load balancing policy, or may be determined by other policies, such as a polling policy.

After the signaling server establishes long connections with the client and the back-end server, the signaling server will serve as a role of a transfer station, so that media information (Session Description Protocol) and network information (Candidate) can be exchanged between the client and the back-end server.

The media information of the client and the back-end server are respectively generated locally, and may include information such as a standard protocol in the industry, and an encoding/decoding mode of transmitted audio/video.

The network information of the client is obtained by the client accessing the signaling server, and the network information of the back-end server is obtained by the server accessing the signaling server. The network information may include addresses and ports of both parties.

Certainly, the information exchanged between the back-end server and the client through the signaling server is not limited to the media information and the network information, and may further include other configuration type information, for example, in some embodiments, the back-end server may further send, to the client through the signaling server, configuration information including a dazzling color sequence that needs to be used when performing the live body detection this time, so that the client may collect a dazzling video stream including the dazzling color sequence according to the configuration information.

In some embodiments, after the exchange of the information between the backend server and the client is completed, the long connection between the backend server and the signaling server and the long connection between the client and the signaling server may be closed, so as to achieve the effect of saving resources.

After the media information and the network information are exchanged between the back-end server and the client, the back-end server and the client can establish point-to-point connection based on the media information and the network information.

Therefore, the client and the back-end server which establish the point-to-point connection can have the function of transmitting the video stream in real time, and the client can send the colorful video stream and/or the first video stream (if the colorful video stream and the first video stream exist) to the back-end server based on the point-to-point connection channel, so that the living body detection method based on the webpage can be realized.

Of course, it is worth pointing out that, when the video stream is transmitted between the client and the backend server through the point-to-point connection channel, the dazzle color video stream and the first video stream are both persistent video streams.

In addition, after the long connection is closed, other interactive contents except the video stream between the subsequent back-end server and the client can also be transmitted through the point-to-point connection channel.

In addition, referring to fig. 2, an embodiment of the present application further provides a web-based in-vivo detection method, which is applied to a client, and the method may include the following steps:

step S210: configuration information including a glare color sequence and a glare video stream capture signal are received.

Step S220: responding to the colorful video stream collecting signal, and calling the colorful video stream which comprises the colorful color sequence and is collected by the camera when the colorful video stream collecting signal is determined to have the camera calling right.

In the embodiment of the application, after acquiring the colorful video stream acquisition signal, the client calls a camera included in the electronic device bearing the client to acquire the colorful video stream.

In the process of collecting colorful video streams, the client determines the color sequence and the display time of a display screen of the electronic equipment, which need to be displayed in the living body detection process, through the colorful color sequence.

The camera can be a built-in camera or an external camera of the electronic equipment.

In a possible implementation manner, the electronic device may be a mobile terminal such as a mobile phone and a tablet computer, the camera is a front-facing camera of the mobile terminal, and the client is a browser installed in the mobile terminal.

Of course, in some embodiments, before the client calls the camera of the electronic device to capture the colorful video stream, the client needs to determine that the client has the right to call the camera of the electronic device.

Optionally, if the client determines that the client can invoke an API (Application Programming Interface) related to the webrtc1.0 standard included in the electronic device, and the electronic device has an authority to invoke the camera, it indicates that the client has the authority to invoke the camera, otherwise, it indicates that the client does not have the authority to invoke the camera.

Optionally, in some embodiments, in order to ensure data synchronization between the back-end server and the client, when the client starts to collect the colorful video streams, the client may send a start collecting signal to the back-end server, and/or when the client finishes collecting the colorful video streams, the client may send an end collecting signal to the back-end server, so that the back-end server may obtain a collecting progress of the colorful video streams, and a preparation for living body detection is made, which is beneficial to improving efficiency of living body detection.

Step S230: and sending the colorful video stream to a back-end server.

In one embodiment, the client may establish a long connection with the signaling server before receiving the configuration information including the sequence of the dazzle color; then, media information and network information are exchanged with the back-end server through the signaling server, and a point-to-point connection channel is established between the back-end server and the signaling server based on the media information and the network information.

In this embodiment, the client may receive configuration information including a sequence of colors of a dazzle by the signaling server in the form of a long connection; and/or the client side can send the colorful video stream to the back-end server through the point-to-point connection channel.

The implementation principle and the generated technical effect of the in-vivo detection method applied to the client provided in the embodiment of the present application are introduced in the foregoing method embodiment, and are not described herein again.

In addition, referring to fig. 3, an embodiment of the present application further provides a web-based in-vivo detection method, which may include the following steps:

step S310: and sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to the client.

Step S320: configuration information including a glare color sequence and a glare video stream capture signal are received.

Step S330: responding to the colorful video stream collecting signal, and calling the colorful video stream which comprises the colorful color sequence and is collected by the camera when the colorful video stream collecting signal is determined to have the camera calling right.

Step S340: and sending the colorful video stream to a back-end server.

Step S350: and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

The implementation principle and the generated technical effect of the web-based in-vivo detection method provided by the embodiment of the present application are introduced in the foregoing method embodiments, and are not described herein again.

In addition, referring to fig. 4, an embodiment of the present application further provides a web-based biopsy system 200, which may include a client 210, a backend server 220, and a signaling server 230.

The client 210 is configured to initiate a long connection establishment request to the signaling server;

a signaling server 230, configured to respond to the long connection establishment request, establish a long connection with the client 210, and establish a long connection with an available backend server 220;

the client 210 is further configured to exchange media information and network information with the available backend server 220 through the signaling server 230, and establish a peer-to-peer connection channel with the available backend server 220 based on the media information and the network information;

the back-end server 220 is configured to send configuration information including the sequence of the dazzling colors to the client 210 through the signaling server 230.

In addition, in order to achieve the effect of saving resources, in some embodiments, the client 210 is further configured to initiate a long connection close request to the signaling server 230 after acquiring the configuration information including the dazzling color sequence;

the signaling server 230 is further configured to close the long connection with the client 210 and the available backend server 220, respectively, in response to the long connection close request.

The implementation principle and the generated technical effect of the web-based living body detecting system 200 are the same as those of the foregoing method embodiments, and for the sake of brief description, no mention is made in the system embodiments, and reference may be made to the corresponding contents in the foregoing method embodiments.

Of course, in some embodiments, the content executed by the client in each of the foregoing method embodiments may be executed by the client 210 included in the web-based liveness detection system 200 in the present embodiment; and/or the content executed by the back-end server in the foregoing method embodiments may be executed by the back-end server 220 included in the web-based liveness detection system 200 in the embodiment of the present application.

In addition, referring to fig. 5, an embodiment of the present application provides a web-based biopsy device 400. The apparatus may include: a first transmitting module 410 and a liveness detection module 420.

A first sending module 410, configured to send a dazzle color video stream acquisition signal and configuration information including a dazzle color sequence to a client;

and the living body detection module 420 is configured to receive the colorful video stream, and perform colorful living body detection on the object to be detected based on the colorful video stream.

In one possible implementation, the apparatus further comprises a gesture detection module.

The first sending module 410 is further configured to send a first video stream acquisition signal to the client;

correspondingly, the first sending module 410 is configured to send the dazzle color video stream collecting signal to the client when it is determined that the gesture detection result meets the gesture requirement.

In a possible implementation manner, the first sending module 410 is further configured to send the posture detection result and/or posture adjustment prompt information to the client when it is determined that the posture detection result does not satisfy the posture requirement.

In a possible implementation, the liveness detection module 420 is configured to receive the first video stream in real time based on a peer-to-peer connection channel established with the client; and/or the presence of a gas in the gas,

In a possible implementation manner, the living body detecting module 420 is configured to perform posture detection on the object to be detected based on the colorful video stream, and determine that a posture detection result obtained based on the colorful video stream represents that the object to be detected meets the posture requirement.

In a possible implementation manner, the living body detecting module 420 is configured to, after receiving the colorful video stream with a fixed duration, perform colorful living body detection on the object to be detected based on the colorful video stream.

The principle of implementation and the technical effects of the web-based biopsy device 400 provided in the embodiment of the present application are the same as those of the method embodiments described above, and for a brief description, reference may be made to the corresponding contents in the method embodiments described above where no mention is made in the apparatus embodiments.

In addition, referring to fig. 6, an embodiment of the present application provides a web-based biopsy device 500. The apparatus may include: a receiving module 510, an acquisition module 520, and a second sending module 530.

A receiving module 510, configured to receive configuration information including a glare color sequence and a glare video stream acquisition signal;

the collecting module 520 is configured to respond to the dazzle color video stream collecting signal, and when it is determined that the dazzle color video stream collecting signal has a camera calling right, call the camera to collect a dazzle color video stream including the dazzle color sequence;

a second sending module 530, configured to send the dazzle color video stream to a server.

In a possible implementation manner, the second sending module 530 is further configured to send a capture start signal to the back-end server when the capture of the dazzle color video stream is started; and or, still be used for beginning to gather when dazzling various video streams, to the rear end server sends and begins to gather the signal, is favorable to the rear end server to acquire the collection progress that dazzles various video streams to guarantee the data synchronism between rear end server and the customer end, and then make the rear end server can make live body detection preparation work in advance, be favorable to improving the efficiency that the live body detected.

In a possible implementation manner, the apparatus further includes an establishing module, configured to establish a long connection with the signaling server; and exchanging media information and network information with the back-end server through the signaling server, and establishing a point-to-point connection channel between the back-end server and the signaling server based on the media information and the network information.

In a possible implementation, the receiving module 510 is configured to receive, by the signaling server, configuration information including the sequence of the dazzle color; and/or the presence of a gas in the gas,

the second sending module 530 is configured to send the colorful video stream to the back-end server through the point-to-point connection channel.

The web-based biopsy device 500 provided in the embodiment of the present application has the same implementation principle and technical effect as those of the foregoing method embodiments, and for brief description, reference may be made to the corresponding contents in the foregoing method embodiments for the parts that are not mentioned in the embodiment of the device.

In addition, the present application also provides a non-volatile computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a computer, the method for detecting a living body based on a web page as described above is executed.

In addition, referring to fig. 7, an electronic device 100 for implementing a web-based biopsy method and apparatus is further provided in the embodiments of the present application.

Optionally, in some embodiments, the electronic device 100 may be the backend server mentioned in the above embodiments. The server may be, but is not limited to, a web server, a database server, a cloud server, and the like.

In some implementations, the electronic device 100 may be a carrier that carries the clients mentioned in the above embodiments. The carrier includes, but is not limited to, Personal Computers (PCs), smart phones, tablet computers, servers, and the like.

Among them, the electronic device 100 may include: a processor 110, a memory 120.

It should be noted that the components and structure of electronic device 100 shown in FIG. 7 are exemplary only, and not limiting, and electronic device 100 may have other components and structures as desired. For example, in some cases, electronic device 100 may also include a camera, a display screen, and the like.

Optionally, the camera may be a built-in camera or an external camera.

Of course, in some embodiments, the camera may be a front camera, for example, a front camera disposed on a mobile terminal, and in this case, the living body detection method is suitable for an authentication scenario.

In other embodiments, the camera may be a rear camera. At this time, the living body detection method is suitable for security inspection scenes, identity authentication and the like.

The processor 110, memory 120, and other components that may be present in the electronic device 100 are electrically connected to each other, directly or indirectly, to enable the transfer or interaction of data. For example, the processor 110, the memory 120, and other components that may be present may be electrically coupled to each other via one or more communication buses or signal lines.

The memory 120 is used for storing a program, such as a program corresponding to the web-based living body detecting method presented in the foregoing or a web-based living body detecting apparatus presented in the foregoing. Optionally, when the web-based liveness detection device is stored in the memory 120, the web-based liveness detection device includes at least one software function module that can be stored in the memory 120 in the form of software or firmware (firmware).

Alternatively, the software function module included in the web-based liveness detection apparatus may be solidified in an Operating System (OS) of the electronic device 100.

The processor 110 is configured to execute executable modules stored in the memory 120, such as software functional modules or computer programs included in the web-based liveness detection device. When the processor 110 receives the execution instruction, it may execute the computer program, for example, to perform: sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to a client; and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

Of course, in some embodiments, when the processor 110 receives the execution instruction, it may further perform: receiving configuration information comprising a colorful color sequence and a colorful video stream acquisition signal; responding to the colorful video stream acquisition signal, and when determining that the colorful video stream acquisition signal has a camera calling right, calling the camera to acquire a colorful video stream comprising the colorful color sequence; and sending the colorful video stream to a back-end server.

Of course, the method disclosed in any of the embodiments of the present application can be applied to the processor 110, or implemented by the processor 110.

In summary, the embodiments of the present invention provide a method, an apparatus, a system, and an electronic device for live detection based on a web page, where when a live detection is required, a back-end server sends a colorful video stream acquisition signal and configuration information including a colorful color sequence to a client; and then carrying out colorful living body detection on the object to be detected based on the received colorful video stream.

In the process, the dazzling living body detection is adopted, so that the situation that a user bypasses silent living body detection or double-angle living body detection by hijacking a camera can be avoided, and the safety of living body detection verification can be improved; in addition, because dazzle various live body detection and need not the language of discernment user, consequently, also can avoid the lip language live body detection and can not discern the user experience problem that the dialect arouses, and then can promote user experience.

In addition, it is worth pointing out that a large amount of calculation is required in the process of dazzling living body detection, and certain requirements are required on hardware resources.

In the embodiment of the present application, the live body detection is implemented based on a web page, that is, the process of the colorful live body detection is handed to the back-end server to be executed in the embodiment of the present application, so that the hardware requirement of the whole live body detection process on the electronic device where the client is located can be reduced, and the detection effect difference caused by the difference of hardware devices can also be avoided.

Moreover, in the above process, since the process related to the calculation is almost executed by the back-end server, and the process related to the client is mainly to collect the colorful video stream, when the living body detection model needs to be optimized and updated, the corresponding change is mainly performed on the back-end server side, and the change is not required on the client side (in the prior art, the APP needs to be updated when the living body detection model is optimized and updated), and compared with the prior art, the process of updating the APP by the user is omitted, and therefore, the dependence on the client and the user when the living body detection model is optimized can be further reduced.

It should be noted that each embodiment is mainly described as a difference from the other embodiments, and the same and similar parts between the embodiments may be referred to each other.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.

Claims

1. A living body detection method based on a webpage is applied to a back-end server, and the method comprises the following steps:

sending a colorful video stream acquisition signal and configuration information comprising a colorful color sequence to a client;

and receiving a colorful video stream, and carrying out colorful living body detection on the object to be detected based on the colorful video stream.

2. The method of claim 1, wherein prior to the sending of the dazzle video stream capture signal to the client, the method further comprises:

sending a first video stream acquisition signal to the client;

receiving a first video stream, and carrying out gesture detection on the object to be detected based on the first video stream to obtain a gesture detection result;

correspondingly, sending the colorful video stream collecting signal to the client comprises:

and when the gesture detection result meets the gesture requirement, sending the colorful video stream acquisition signal to the client.

3. The method of claim 2, further comprising:

and when the gesture detection result is determined not to meet the gesture requirement, sending the gesture detection result and/or gesture adjustment prompt information to the client.

4. The method according to claim 2 or 3,

the receiving a first video stream, comprising:

receiving the first video stream in real time based on a point-to-point connection channel established between the client and the client;

and/or the presence of a gas in the gas,

the receiving of the dazzle color video stream comprises:

and receiving the colorful video stream in real time based on a point-to-point connection channel established between the colorful video stream and the client.

5. The method of claim 2, wherein prior to the dazzle live detection of the object to be detected based on the dazzle video stream, the method further comprises:

and carrying out posture detection on the object to be detected based on the colorful video stream, and determining that the object to be detected meets the posture requirement represented by a posture detection result obtained based on the colorful video stream.

6. The method according to any one of claims 1 to 5, wherein the receiving a dazzle color video stream and performing dazzle color live detection on an object to be detected based on the dazzle color video stream comprises:

and after the colorful video stream is received for a fixed time, colorful living body detection is carried out on the object to be detected based on the colorful video stream.

7. A living body detection method based on a webpage is applied to a client side, and the method comprises the following steps:

receiving configuration information comprising a colorful color sequence and a colorful video stream acquisition signal;

responding to the colorful video stream acquisition signal, and when determining that the colorful video stream acquisition signal has a camera calling right, calling the camera to acquire a colorful video stream comprising the colorful color sequence;

and sending the colorful video stream to a back-end server.

8. The method of claim 7, further comprising:

when the colorful video stream starts to be collected, sending a collection starting signal to the back-end server; and/or the presence of a gas in the gas,

and when the colorful video stream is collected, sending a collection finishing signal to the rear-end server.

9. The method according to claim 7 or 8, comprising, prior to the receiving configuration information comprising a sequence of dazzle colors:

establishing long connection with a signaling server;

and exchanging media information and network information with the back-end server through the signaling server, and establishing a point-to-point connection channel between the back-end server and the signaling server based on the media information and the network information.

10. The method of claim 9, wherein receiving configuration information comprising a sequence of colors comprises:

receiving, by the signaling server, configuration information including the sequence of dazzle colors; and/or the presence of a gas in the gas,

the will dazzle various video streaming and send back-end server, include:

and sending the colorful video stream to the back-end server through the point-to-point connecting channel.

11. A web-based liveness detection system, comprising: the system comprises a client, a back-end server and a signaling server;

12. The web-based liveness detection system of claim 11,

13. A web-based liveness detection device, the device comprising:

14. A web-based liveness detection device, the device comprising:

15. An electronic device, comprising: a memory and a processor, the memory and the processor connected;

the memory is used for storing programs;

the processor calls a program stored in the memory to perform the method of any of claims 1-10.

16. A readable storage medium, having stored thereon a computer program which, when executed by a computer, performs the method of any one of claims 1-10.