WO2024077971A1 - 活体检测方法及装置 - Google Patents

活体检测方法及装置 Download PDF

Info

Publication number
WO2024077971A1
WO2024077971A1 PCT/CN2023/097428 CN2023097428W WO2024077971A1 WO 2024077971 A1 WO2024077971 A1 WO 2024077971A1 CN 2023097428 W CN2023097428 W CN 2023097428W WO 2024077971 A1 WO2024077971 A1 WO 2024077971A1
Authority
WO
WIPO (PCT)
Prior art keywords
sequence
detection result
detected
sub
information
Prior art date
Application number
PCT/CN2023/097428
Other languages
English (en)
French (fr)
Inventor
何果财
周秋生
刘宇光
裴积全
Original Assignee
京东科技控股股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东科技控股股份有限公司 filed Critical 京东科技控股股份有限公司
Publication of WO2024077971A1 publication Critical patent/WO2024077971A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
    • G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal recognition

Definitions

  • the embodiments of the present application relate to the field of computer technology, specifically to face recognition technology, and more particularly to a living body detection method and device.
  • face recognition technology is being used more and more widely.
  • face recognition technology is used in scenarios such as face attendance, face payment, and face query, which can effectively improve the efficiency of user operations.
  • face recognition technology is widely used, it is also vulnerable to presentation attacks and non-presentation attacks.
  • the existing liveness detection methods for attacks are less secure.
  • the embodiments of the present application provide a living body detection method, device, computer-readable medium, electronic device and computer program product.
  • One or more embodiments of the present application provide a liveness detection method, comprising: in response to receiving a liveness detection request, generating a position sequence for indicating position information of an identification area of an object to be detected, a light sequence for indicating light information of a luminous area, and an action sequence for indicating action information referenced by the object to be detected; obtaining state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, to obtain a state information sequence; and determining a detection result characterizing whether the object to be detected is a live object based on the state information sequence.
  • a living body detection device including: a generating unit, The invention is configured to generate, in response to receiving a liveness detection request, a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referred to by the object to be detected; the acquisition unit is configured to acquire the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence and the action information in the action sequence, and obtain a state information sequence; the determination unit is configured to determine the detection result characterizing whether the object to be detected is a live object based on the state information sequence.
  • One or more embodiments of the present application provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.
  • One or more embodiments of the present application provide an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above implementation methods.
  • One or more embodiments of the present application provide a computer program product, which includes a computer program.
  • the computer program When the computer program is executed by a processor, the computer program implements the method described in any of the above implementations.
  • FIG1 is an exemplary system architecture diagram in which an embodiment of the present application may be applied
  • FIG2 is a flow chart of an embodiment of a liveness detection method according to the present application.
  • FIG3 is a schematic diagram of an application scenario of the liveness detection method according to this embodiment.
  • FIG4 is a flow chart of another embodiment of a liveness detection method according to the present application.
  • FIG5 is a structural diagram of an embodiment of a living body detection device according to the present application.
  • FIG. 6 is a schematic diagram of the structure of a computer system suitable for implementing an embodiment of the present application.
  • FIG. 1 shows an exemplary architecture 100 to which the living body detection method and apparatus of the present application can be applied.
  • the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105.
  • the communication connection between the terminal devices 101, 102, 103 constitutes a topological network
  • the network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.
  • Terminal devices 101, 102, 103 can be hardware devices or software that support network connection for data interaction and data processing.
  • terminal devices 101, 102, 103 can be various electronic devices that support network connection, information acquisition, interaction, display, processing and other functions, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers and desktop computers, etc.
  • terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
  • the server 105 may be a server that provides various services, for example, a background processing server that performs liveness detection on an object to be detected to determine whether the object to be detected is a live object in response to receiving a liveness detection request sent by the terminal devices 101, 102, 103.
  • the server 105 may be a cloud server.
  • the server can be hardware or software.
  • the server can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server.
  • the server is software, it can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.
  • the liveness detection method provided in the embodiments of the present application can be executed by a server, or by a terminal device, or by a server and a terminal device in cooperation with each other. Accordingly, the various parts (such as various units) included in the liveness detection device can be all set in the server, or all set in the terminal device, or can be set in the server and the terminal device respectively.
  • the number of terminal devices, networks, and servers in FIG1 is merely illustrative. Depending on the implementation requirements, there may be any number of terminal devices, networks, and servers.
  • the system architecture may only include the electronic device (e.g., server or terminal device) on which the liveness detection method is running.
  • a process 200 of an embodiment of a liveness detection method comprising the following steps:
  • Step 201 in response to receiving a liveness detection request, generates a position sequence for indicating position information of an identification area of an object to be detected, a light sequence for indicating light information of a luminous area, and an action sequence for indicating action information referenced by the object to be detected.
  • the executor of the liveness detection method (for example, the terminal device or server in Figure 1) can generate a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referenced by the object to be detected in response to receiving a liveness detection request.
  • Liveness detection is used to detect whether the object to be detected is a live object.
  • the position sequence includes multiple position information, and the recognition area in the display screen of the above-mentioned execution subject can change in sequence according to the position information in the position sequence.
  • the recognition area is specifically manifested as a part of the display screen, which can be specifically presented in a circular, square or other shape, which is not limited here.
  • the position sequence includes three position information of the upper left corner position, the center position, and the lower right corner position of the screen. When this position sequence is adopted, the recognition area in the display screen changes from the upper left corner position of the display screen, through the center position, to the lower right corner position.
  • the execution subject can perform a position movement operation of the identification area according to the position information in the position sequence at a preset time interval.
  • the preset time can be set according to the actual situation.
  • the position sequence is intended to guide the object to be detected to move with the movement of the identification area by changing the position of the identification area.
  • the preset time can be determined based on the reaction time of the whole process of humans reacting to the movement of the identification area and moving with the movement of the identification area.
  • the light sequence includes multiple light information, and the light emitting area corresponding to the display screen of the execution subject
  • the domain can change in sequence according to the light information in the light sequence.
  • the luminous area can be the display screen itself or a luminous light source outside the display screen.
  • the light information includes information such as the color and intensity of the light.
  • the light sequence includes three types of light information: red, green, and blue.
  • the display screen can display red light, green light, and blue light in sequence.
  • the above-mentioned execution subject can perform a light change operation on the luminous area according to the light information in the light sequence based on a preset duration.
  • the light sequence is intended to change the light environment information around the object to be detected.
  • the action sequence includes multiple action information, and the above-mentioned execution subject can display the multiple action information in the action sequence in the form of voice, text, etc. in sequence to guide the user to perform corresponding actions according to the action information.
  • the action sequence includes three action information: blinking, opening the mouth, and reading a preset number.
  • the display screen can display blinking, opening the mouth, and reading a preset number in sequence through text.
  • the above-mentioned execution subject can display the action information in the action sequence in sequence based on a preset duration.
  • the number of position information in the position sequence, the number of light information in the light information, and the number of action information in the action sequence can be the same or different, and the timing of changes in the three types of information can be the same or different, which is not limited here.
  • the above-mentioned execution subject can generate position sequences, light sequences and action sequences in a random manner.
  • the position sequence multiple position information can be randomly selected from the position set to form a position sequence, wherein the position set includes all possible positions of the identification area on the display screen.
  • the light sequence multiple light information can be randomly selected from the light set to form a light sequence.
  • the light sequence includes all light information that can be controlled by the luminous area;
  • the action sequence multiple action information can be randomly selected from the action set to form an action sequence.
  • the action sequence includes various action information that can be easily performed by the object to be detected and has recognition.
  • the execution subject may determine the complexity of generating the position sequence, light sequence, and action sequence according to the scene information corresponding to the liveness detection, and then generate the position sequence, light sequence, and action sequence according to the complexity.
  • the complexity may include information such as the amount of information and the way the information changes.
  • the security level and complexity required by the scenario information are positively correlated.
  • the security requirement is relatively high, so a higher complexity can be set.
  • the location sequence The amount of information in the three sequences of light sequence and action sequence is large, and the information in each sequence can change in many ways.
  • the security requirement is relatively low, so a lower complexity can be set.
  • Step 202 obtaining state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, to obtain a state information sequence.
  • the execution subject can obtain the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence and the action information in the action sequence, and obtain the state information sequence.
  • the execution subject can refer to the three sequences to change the corresponding information on the display screen of the execution subject.
  • the corresponding information includes changing the position of the recognition area, the light of the luminous area and the displayed action information.
  • the purpose is to guide the object to be detected to actively change the position state and action state of the face with reference to the information in the sequence; for the light sequence, the purpose is to actively change the light environment information around the object to be detected.
  • the state information of the object to be detected will be changed multiple times based on the position sequence, light sequence and action sequence.
  • the above execution subject can obtain the state information of the object to be detected multiple times to obtain the state information sequence.
  • the execution subject acquires an image or video including the object to be detected at a preset time interval, and then performs data processing on the image or video to obtain state information of the object to be detected, thereby combining multiple state information in sequence to obtain a state information sequence.
  • the data processing process includes determining a detection frame (position) of the object to be detected on the screen, determining the light environment information of the object to be detected, and identifying the action information of the object to be detected.
  • data processing can be performed through a corresponding neural network model.
  • location information as an example, the above-mentioned execution subject can determine whether an image or video includes an object to be detected and the location information of the object to be detected through a target detection model.
  • timing of information change and image or video acquisition in the three sequences may be the same or different, and is not limited here.
  • the execution subject may perform step 202 in the following manner:
  • the recognition area is displayed based on the position sequence, and the position information representing the object to be detected is determined A sequence of position status information.
  • the timing of changing the position information of the recognition area based on the position sequence matches the timing of collecting the position data of the object to be detected. For example, in the interval between two changes in position information, the image or video data of the object to be detected is collected to determine the position information of the face of the object to be detected on the display screen, and finally obtain a position state information sequence representing the actual position state information of the object to be detected.
  • the light environment information of the object to be detected is changed based on the light sequence, and a light state information sequence representing the light environment information of the object to be detected is determined.
  • the timing of changing the light environment information of the object to be detected based on the light sequence is matched with the timing of collecting the light environment data of the object to be detected. For example, in the interval between two changes in light information, image or video data representing the light environment of the object to be detected is collected to determine the light environment information of the object to be detected, and finally a light state information sequence representing the actual light state information of the object to be detected is obtained.
  • the action information in the action sequence is displayed, and an action state information sequence representing the action information displayed by the object to be detected is determined.
  • the timing of changing the action information displayed on the display screen based on the action sequence matches the timing of collecting the action data of the object to be detected. For example, in the interval between two changes in action information, image or video data representing the action of the object to be detected is collected to determine the action state information of the object to be detected, and finally obtain an action state information sequence representing the actual action state information of the object to be detected.
  • the image data or video data collected by the camera device of the above-mentioned execution subject can be used as target data to determine the position status information, light environment status information and action status information of the object to be detected.
  • the position state information, light environment state information and action state information are determined respectively to obtain the position state information sequence, light state information sequence and action state information sequence, thereby improving the pertinence and accuracy of information acquisition.
  • Step 203 Determine a detection result indicating whether the object to be detected is a living object based on the state information sequence.
  • the execution subject can determine the characterization of the pair to be detected based on the state information sequence. The detection result of whether the object is a living object.
  • the timing of the change of information in the three sequences including the timing of collecting images or videos of the object to be detected, is the same, it can be determined whether the state information obtained based on the image or video corresponds to the information in the sequence of the corresponding timing.
  • the three sequences simultaneously undergo a change operation, wherein the recognition area changes to the center position of the display screen, the light information changes to green, and the action information is opening the mouth.
  • the above-mentioned execution entity collects a video of the object to be detected at the current moment, and determines a state information in the state information sequence based on the video. It is necessary to determine whether the position of the object to be detected in the state information is consistent with the center position, whether the light environment information is consistent with the green light, and whether the object to be detected makes a mouth-opening action.
  • the object to be detected under the state information in the state information sequence is a living object, otherwise, it is considered to be a non-living object.
  • a voting operation is performed to obtain the final detection result.
  • the information being presented in the three sequences at the current time can be determined based on the time information. Furthermore, it can be determined whether the collected state information of the object to be detected corresponds to the information that should be presented in the three sequences corresponding to the data collection moment, so as to determine the final detection result.
  • the execution subject may perform step 203 in the following manner:
  • a first sub-detection result indicating whether the object to be detected is a living object is determined.
  • the above-mentioned execution entity can determine whether the object to be detected moves based on the guidance of the identification area according to multiple position state information in the position state information sequence, and in response to determining that the object to be detected moves, determine the first sub-detection result characterizing that the object to be detected is a living object; otherwise, determine the first sub-detection result characterizing that the object to be detected is not a living object.
  • a second sub-detection result indicating whether the object to be detected is a living object is determined.
  • the execution subject can determine whether the light environment information of the object to be detected changes based on the light changes according to the multiple light state information in the light state information sequence, and determine the characterization in response to determining that the light environment state information of the object to be detected changes.
  • the second sub-detection result indicating that the object to be detected is a living object; otherwise, determining the second sub-detection result indicating that the object to be detected is not a living object.
  • a third sub-detection result indicating whether the object to be detected is a living object is determined.
  • the above-mentioned execution subject can determine whether the object to be detected makes corresponding actions according to the action sequence based on multiple action state information in the action state information sequence, and in response to determining that the object to be detected makes corresponding actions according to the action sequence, determine the third sub-detection result characterizing that the object to be detected is a living object; otherwise, determine the third sub-detection result characterizing that the object to be detected is not a living object.
  • a detection result is determined according to the first sub-detection result, the second sub-detection result, and the third sub-detection result.
  • the execution subject may determine the detection result according to the first sub-detection result, the second sub-detection result and the third sub-detection result in various ways. For example, by adopting OR logic, as long as the first sub-detection result, the second sub-detection result and the third sub-detection result include the result that characterizes the object to be detected as a non-living object, the final detection result indicates that the object to be detected is a non-living object; by adopting a voting method, the result with the largest number of identical results among the first sub-detection result, the second sub-detection result and the third sub-detection result is determined as the final detection result; the comprehensive judgment method includes but is not limited to logical reasoning, model prediction, machine learning and other methods.
  • the method of obtaining the final detection result according to the first sub-detection result, the second sub-detection result, and the third sub-detection result can be determined according to the scene corresponding to the liveness detection.
  • the safety requirement of the application scene when the safety requirement of the application scene is high, it can be processed based on OR logic; when the safety requirement of the application scene is low, it can be processed according to the chip casting method.
  • corresponding sub-detection results are obtained for each of the various detection methods related to position, light, and motion, and then the final detection result is determined based on the multiple sub-detection results, thereby improving the independence of the multiple detection methods.
  • the various detection methods do not affect each other, and the accuracy of the final detection result is further improved.
  • the execution subject may perform the first step as follows: compare the position state information sequence and the position sequence to determine the first sub-detection result. Specifically, when multiple position state information in the position state information sequence and multiple position information in the position sequence correspond to each other, and the corresponding information is consistent, it is determined that the object to be detected is The first sub-detection result of the detected object is a living object; otherwise, the first sub-detection result indicating that the detected object is a non-living object is determined.
  • the execution subject may perform the second step in the following manner: compare the light state information sequence and the light sequence to determine the second sub-detection result. Specifically, when multiple light state information in the light state information sequence and multiple light information in the light sequence correspond one to one, and the corresponding information is consistent, then the second sub-detection result indicating that the object to be detected is a living object is determined; otherwise, the second sub-detection result indicating that the object to be detected is a non-living object is determined.
  • the execution subject may perform the third step in the following manner: compare the action state information sequence and the action sequence to determine the third sub-detection result. Specifically, when multiple action state information in the action state information sequence and multiple action information in the action sequence correspond one to one, and the corresponding information is consistent, then the third sub-detection result indicating that the object to be detected is a living object is determined; otherwise, the third sub-detection result indicating that the object to be detected is a non-living object is determined.
  • the above-mentioned execution subject may also determine feature data of the object to be detected; and determine, based on the feature data, a fourth sub-detection result indicating whether the object to be detected is a living object.
  • the above-mentioned execution entity can input the acquired image or video data of the object to be detected into the liveness detection model, and the feature extraction network in the liveness detection model extracts the feature data of the object to be detected (for example, facial feature data); the classification network determines the fourth sub-detection result characterizing whether the object to be detected is a live object based on the feature data.
  • the feature extraction network in the liveness detection model extracts the feature data of the object to be detected (for example, facial feature data); the classification network determines the fourth sub-detection result characterizing whether the object to be detected is a live object based on the feature data.
  • a detection result is determined based on the first sub-detection result, the second sub-detection result, the third sub-detection result, and the fourth sub-detection result.
  • the above-mentioned execution entity can adopt a variety of methods such as logic, voting, and comprehensive analysis to determine the detection results, and the specific processing method can be determined according to the security level required by the application scenario.
  • a detection method based on the characteristic data of the object to be detected is further combined to further improve the accuracy of the living body detection process.
  • FIG. 3 is a schematic diagram 300 of an application scenario of the liveness detection method according to the present embodiment.
  • a user 301 performs an electronic transfer based on face recognition through a terminal device 302, and the electronic device 302 sends a liveness detection request to a server 303 in response to receiving a liveness detection request.
  • the server generates a position sequence 304 for indicating the position information of the identification area of the object to be detected, a light sequence 305 for indicating the light information of the luminous area, and an action sequence 306 for indicating the action information referenced by the object to be detected; obtains the state information of the object to be detected after the change based on the position information in the position sequence 304, the light information in the light sequence 305, and the action information in the action sequence 306, and obtains a state information sequence 307; based on the state information sequence 307, determines a detection result 308 representing whether the object to be detected is a live object.
  • the method provided by the above-mentioned embodiment of the present application generates, in response to receiving a liveness detection request, a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referenced by the object to be detected; obtains the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, to obtain a state information sequence; based on the state information sequence, determines the detection result characterizing whether the object to be detected is a live object, thereby combining multiple liveness detection methods regarding position, light, and action, and improving the accuracy of the liveness detection process.
  • FIG. 4 a schematic process 400 of an embodiment of a remote plug-in development and publishing method according to the present application is shown, including the following steps:
  • Step 401 in response to receiving a liveness detection request, generates a position sequence for indicating position information of an identification area of an object to be detected, a light sequence for indicating light information of a luminous area, and an action sequence for indicating action information referenced by the object to be detected.
  • Step 402 display the identification area based on the position sequence, and determine a position state information sequence representing the position information of the object to be detected.
  • Step 403 compare the position state information sequence and the position sequence to determine a first sub-detection result indicating whether the object to be detected is a living object.
  • Step 404 Change the light environment information of the object to be detected based on the light sequence, and determine a light state information sequence representing the light environment information of the object to be detected.
  • Step 405 Compare the light state information sequence and the light sequence to determine a second sub-detection result indicating whether the object to be detected is a living object.
  • Step 406 display the action information in the action sequence, and determine an action state information sequence representing the action information displayed by the object to be detected.
  • Step 407 Compare the action state information sequence and the action sequence to determine a third sub-detection result indicating whether the object to be detected is a living object.
  • Step 408 Determine the feature data of the object to be detected.
  • Step 409 Determine, based on the feature data, a fourth sub-detection result indicating whether the object to be detected is a living object.
  • Step 410 determining a detection result according to the first sub-detection result, the second sub-detection result, the third sub-detection result and the fourth sub-detection result.
  • the process 400 of the liveness detection method in this embodiment specifically illustrates the process of determining the first sub-detection result, the second sub-detection result, the third sub-detection result and the fourth sub-detection result, further improving the accuracy of the final detection result.
  • the present application provides an embodiment of a liveness detection device, which corresponds to the method embodiment shown in FIG. 2 , and can be specifically applied to various electronic devices.
  • the liveness detection device includes: a generating unit 501, which is configured to generate, in response to receiving a liveness detection request, a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referenced by the object to be detected; an acquiring unit 502, which is configured to acquire the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, to obtain a state information sequence; a determining unit 503, which is configured to determine, based on the state information sequence, a detection result characterizing whether the object to be detected is a live object.
  • the acquisition unit 502 is further configured to: display the identification area based on the position sequence, and determine a position state information sequence representing the position information of the object to be detected; change the light environment information of the object to be detected based on the light sequence, and determine a light state information sequence representing the light environment information of the object to be detected; display the action information in the action sequence, and determine an action state information sequence representing the action information displayed by the object to be detected.
  • the above-mentioned determination unit 503 is further configured The method comprises the following steps: determining, according to a position state information sequence, a first sub-detection result indicating whether the object to be detected is a living object; determining, according to a light state information sequence, a second sub-detection result indicating whether the object to be detected is a living object; determining, according to a motion state information sequence, a third sub-detection result indicating whether the object to be detected is a living object; and determining a detection result according to the first sub-detection result, the second sub-detection result, and the third sub-detection result.
  • the above-mentioned determination unit 503 is further configured to: compare the position state information sequence and the position sequence to determine the first sub-detection result.
  • the above-mentioned determination unit 503 is further configured to: compare the light state information sequence and the light sequence to determine the second sub-detection result.
  • the above-mentioned determination unit 503 is further configured to: compare the action state information sequence and the action sequence to determine the third sub-detection result.
  • the above-mentioned determination unit 503 is further configured to: determine the characteristic data of the object to be detected; determine, based on the characteristic data, a fourth sub-detection result characterizing whether the object to be detected is a living object; and determine the detection result based on the first sub-detection result, the second sub-detection result, the third sub-detection result and the fourth sub-detection result.
  • the generating unit in the liveness detection device generates, in response to receiving a liveness detection request, a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referenced by the object to be detected;
  • the acquiring unit acquires the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, and obtains a state information sequence;
  • the determining unit determines the detection result characterizing whether the object to be detected is a live object based on the state information sequence, and combines a variety of liveness detection methods regarding position, light, and action to improve the accuracy of the liveness detection process.
  • FIG6 a schematic diagram of the structure of a computer system 600 suitable for implementing the device of the present application (e.g., the devices 101, 102, 103, 105 shown in FIG1) is shown below.
  • the device shown in FIG6 is only an example and should not limit the functions and scope of use of the present application.
  • a computer system 600 includes a processor (eg, a CPU, a central processing unit) 601, which can execute commands according to a program stored in a read-only memory (ROM) 602 or loaded from a storage part 608.
  • the processor 601, ROM 602 and RAM 603 are connected to each other via a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604.
  • the following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc.
  • the communication section 609 performs communication processing via a network such as the Internet.
  • a drive 610 is also connected to the I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.
  • an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart.
  • the computer program can be downloaded and installed from a network through a communication part 609, and/or installed from a removable medium 611.
  • the processor 601 executes the above-mentioned functions defined in the method of the present application.
  • the computer-readable medium of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above.
  • Computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code.
  • This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • the computer-readable signal medium also Any computer-readable medium other than a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device.
  • the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
  • Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages.
  • the program code may be executed entirely on the client computer, partially on the client computer, as a separate software package, partially on the client computer and partially on a remote computer, or entirely on a remote computer or server.
  • the remote computer may be connected to the client computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • Internet service provider e.g., AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.
  • each box in the block diagram and/or flow chart, and the combination of the boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present application may be implemented by software or by hardware.
  • the units described may also be provided in a processor, for example, may be described as: a processor comprising a generating unit, an acquiring unit and a determining unit.
  • the names of these units do not, in certain cases, constitute limitations on the units themselves.
  • the generating unit may also be described as “in response to receiving a liveness detection request, generating a position sequence for indicating position information of an identification area of an object to be detected, a light sequence for indicating light information of a luminous area, and a unit for indicating an action sequence of action information referenced by the object to be detected”.
  • the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device.
  • the above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the computer device: in response to receiving a liveness detection request, generates a position sequence for indicating the position information of the identification area of the object to be detected, a light sequence for indicating the light information of the luminous area, and an action sequence for indicating the action information referenced by the object to be detected; obtains the state information of the object to be detected after the change based on the position information in the position sequence, the light information in the light sequence, and the action information in the action sequence, and obtains a state information sequence; based on the state information sequence, determines the detection result characterizing whether the object to be detected is a live object.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

本申请公开了一种活体检测方法及装置。方法的一具体实施方式包括：响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。

Description

活体检测方法及装置
本专利申请要求于2022年10月10日提交的、申请号为202211242072.8、发明名称为“活体检测方法及装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请实施例涉及计算机技术领域，具体涉及人脸识别技术，尤其涉及一种活体检测方法及装置。
背景技术
随着计算机技术的深入发展，人脸识别技术的应用越来越广泛。例如，在人脸考勤、人脸支付、人脸查询等场景下，都会应用人脸识别技术，可有效提升用户操作时的效率。但是，人脸识别技术被广泛应用的同时，也容易遭到呈现式攻击、非呈现式攻击。现有的针对于攻击的活体检测方法的安全性较低。
发明内容
本申请实施例提出了一种活体检测方法、装置、计算机可读介质，电子设备以及计算机程序产品。
本申请的一种或多种实施例提供了一种活体检测方法，包括：响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。
本申请的一种或多种实施例提供了一种活体检测装置，包括：生成单元， 被配置成响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取单元，被配置成获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；确定单元，被配置成基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。
本申请的一种或多种实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如第一方面任一实现方式描述的方法。
本申请的一种或多种实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如上述任一实现方式描述的方法。
本申请的一种或多种实施例提供了一种计算机程序产品，其包括计算机程序，该计算机程序在被处理器执行时实现如上述任一实现方式描述的方法。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请的一个实施例可以应用于其中的示例性系统架构图；
图2是根据本申请的活体检测方法的一个实施例的流程图；
图3是根据本实施例的活体检测方法的应用场景的示意图；
图4是根据本申请的活体检测方法的又一个实施例的流程图；
图5是根据本申请的活体检测装置的一个实施例的结构图；
图6是适于用来实现本申请实施例的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的活体检测方法及装置的示例性架构100。
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。终端设备101、102、103之间通信连接构成拓扑网络，网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103可以是支持网络连接从而进行数据交互和数据处理的硬件设备或软件。当终端设备101、102、103为硬件时，其可以是支持网络连接，信息获取、交互、显示、处理等功能的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以是提供各种服务的服务器，例如，响应于接收到终端设备101、102、103发出的活体检测请求，对待检测对象进行活体检测，以确定待检测对象是否为活体对象的后台处理服务器。作为示例，服务器105可以是云端服务器。
需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务的软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
还需要说明的是，本申请的实施例所提供的活体检测方法可以由服务器执行，也可以由终端设备执行，还可以由服务器和终端设备彼此配合执行。相应地，活体检测装置包括的各个部分(例如各个单元)可以全部设置于服务器中，也可以全部设置于终端设备中，还可以分别设置于服务器和终端设备中。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。当活体检测方法运行于其上的电子设备不需要与其他电子设备进行数据传输时，该系统架构可以仅包括活体检测方法运行于其上的电子设备(例如服务器或终端设备)。
继续参考图2，示出了活体检测方法的一个实施例的流程200，包括以下步骤：
步骤201，响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列。
本实施例中，活体检测方法的执行主体(例如图1中的终端设备或服务器)可以响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列。
在人脸识别场景中，上述执行主体接收到用户的人脸识别请求时，可以默认用户同时发出了活体检测请求。活体检测用于检测待检测对象是否为活体对象。
位置序列包括多个位置信息，上述执行主体的显示屏幕中的识别区域可以依次按照位置序列中的位置信息变化。识别区域具体表现为显示屏幕中的一部分区域，可以具体呈现为圆形、方形等形状，在此不做限定。作为示例，位置序列中包括屏幕的左上角位置、中心位置、右下角位置三个位置信息。当采用该位置序列时，显示屏幕中的识别区域依次从显示屏幕的左上角位置，经过中心位置，变化至右下角位置。
具体的，上述执行主体可以间隔预设时长按照位置序列中的位置信息进行识别区域的一次位置移动操作。其中，预设时长可以根据实际情况具体设置。比如，位置序列旨在通过改变识别区域的位置，引导待检测对象随着识别区域的移动而移动，则预设时长可以根据人类观察到识别区域的移动后做出反应，而随着识别区域的移动而移动这整个过程的反应时长而确定。
光线序列中包括多个光线信息，上述执行主体的显示屏幕对应的发光区 域可以依次按照光线序列中的光线信息而变化。发光区域可以是显示屏幕本身，也可以是显示屏幕之外的发光光源。光线信息包括发光的颜色、强度等信息。作为示例，光线序列中包括红色、绿色、蓝色三种光线信息。当采用该光线序列时，显示屏幕可以依次显示红色光线、绿色光线、蓝色光线。具体的，上述执行主体可以基于预设时长按照光线序列中的光线信息进行发光区域的一次光线变化操作。光线序列旨在改在待检测对象周围的光线环境信息。
动作序列包括多个动作信息，上述执行主体可以通过语音、文本等形式依次显示动作序列中的多个动作信息，以引导用户按照动作信息做出相应的动作。作为示例，动作序列中包括眨眼、张嘴、读预设数字三个动作信息。当采用该动作序列时，显示屏幕可以通过文本依次显示眨眼、张嘴、读预设数字。具体的，上述执行主体可以基于预设时长依次显示动作序列中的动作信息。
需要说明的是，位置序列中的位置信息的数量、光线信息中的光线信息的数量、动作序列中的动作信息的数量可以相同也可以不同，三种信息的变化时机可以相同也可以不同，在此不做限定。
本实施例中，上述执行主体可以采用随机方式生成位置序列、光线序列和动作序列。作为示例，对于位置序列，可以随机从位置集合中选取多个位置信息，构成位置序列，其中，位置集合中包括识别区域在显示屏幕中的所有可能位置。同理，对于光线序列，可以从光线集合中随机选取多种光线信息，构成光线序列。其中，光线序列中包括发光区域所能控制的所有光线信息；对于动作序列，可以从动作集合中随机选取多种动作信息，构成动作序列。其中，动作序列中包括待检测对象能够便捷地做出而又具有识别度的各种动作信息。
在一些可选的实现方式中，上述执行主体可以根据活体检测对应的场景信息，确定生成位置序列、光线序列、动作序列的复杂度，进而根据复杂度，生成位置序列、光线序列、动作序列。其中，复杂度可以包括信息的数量、信息的变化方式等信息。
场景信息所要求的安全度与复杂度呈正相关。作为示例，在电子支付场景中，对于安全度要求比较高，可以设置较高的复杂度。比如，位置序列、 光线序列、动作序列这三种序列中的信息的数量较多，每个序列中的信息之间的变化方式较多。在人脸考勤场景中，对于安全度要求比较低，可以设置较低的复杂度。
步骤202，获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列。
本实施例中，上述执行主体可以获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列。
作为示例，上述执行主体在生成位置序列、光线序列和动作序列后，可以参照三种序列改变上述执行主体的显示屏幕中的对应信息。具体的，对应信息包括改变识别区域的位置、发光区域的光线和显示的动作信息。
对于位置序列和动作序列，旨在引导待检测对象参照序列中的信息主动改变面部的位置状态和动作状态；对于光线序列，旨在主动改变待检测对象周围的光线环境信息。
由于位置序列、光线序列和动作序列中均包括多种信息，因此，待检测对象的状态信息会基于位置序列、光线序列和动作序列得到多次改变。上述执行主体可以多次获取待检测对象的状态信息，得到状态信息序列。
作为示例，上述执行主体每间隔预设时长，获取包括待检测对象的图像或视频，进而对图像或视频进行数据处理，得到待检测对象的状态信息，从而按顺序组合多个状态信息得到状态信息序列。其中，数据处理过程包括确定待检测对象在屏幕中的检测框(位置)、确定待检测对象的光线环境信息以及识别待检测对象的动作信息。
具体的，可以通过对应的神经网络模型进行数据处理。以位置信息为例，上述执行主体可以通过目标检测模型确定图像或视频中是否包括待检测对象以及待检测对象的位置信息。
需要说明的是，三种序列中的信息的变化时机、图像或视频的采集时机可以相同也可以不同，在此不做限定。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下方式执行上述步骤202：
第一，基于位置序列展示识别区域，并确定表征待检测对象的位置信息 的位置状态信息序列。
本实现方式中，基于位置序列而改变识别区域的位置信息的时机，与待检测对象的位置数据的采集时机相匹配。例如，在两次位置信息的变化间隙，采集待检测对象的图像或视频数据，确定待检测对象的面部在显示屏幕中的位置信息，最终得到表征待检测对象的实际位置状态信息的位置状态信息序列。
第二，基于光线序列改变待检测对象的光线环境信息，并确定表征待检测对象的光线环境信息的光线状态信息序列。
本实现方式中，基于光线序列改变待检测对象的光线环境信息的时机，与待检测对象的光线环境数据的采集时机相匹配。例如，在两次光线信息的变化间隙，采集表征待检测对象的光线环境的图像或视频数据，确定待检测对象的光线环境信息，最终得到表征待检测对象的实际光线状态信息的光线状态信息序列。
第三，展示动作序列中的动作信息，并确定表征待检测对象所展示的动作信息的动作状态信息序列。
本实现方式中，基于动作序列改变显示屏幕所展示的动作信息的时机，与待检测对象的动作数据的采集时机相匹配。例如，在两次动作信息的变化间隙，采集表征待检测对象的动作的图像或视频数据，从而确定待检测对象的动作状态信息，最终得到表征待检测对象的实际动作状态信息的动作状态信息序列。
当位置序列、光线序列和动作序列中的信息的变化时机相同时，可以将上述执行主体的摄像装置采集的图像数据或视频数据作为目标数据，从中确定出待检测对象的位置状态信息、光线环境状态信息和动作状态信息。
本实现方式中，对于基于位置序列、光线序列和动作序列改变后的待检测对象的状态信息，分别确定位置状态信息、光线环境状态信息和动作状态信息，得到位置状态信息序列、光线状态信息序列和动作状态信息序列，提高了信息获取的针对性和准确度。
步骤203，基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。
本实施例中，上述执行主体可以基于状态信息序列，确定表征待检测对 象是否为活体对象的检测结果。
作为示例，当三种序列中的信息的变化时机、包括待检测对象的图像或视频的采集时机相同时，可以确定根据图像或视频得到的状态信息是否与对应时机的序列中的信息相对应。例如，在开始活体检测后，三种序列同时进行了一次变化操作，其中，识别区域变化至显示屏幕的中心位置，光线信息变为绿色，动作信息为张嘴。并且，上述执行主体采集了当前时刻待检测对象的视频，并根据视频确定了状态信息序列中的一次状态信息。则需要确定该状态信息中待检测对象的位置是否与中心位置一致，光线环境信息是否与绿色光线一致，待检测对象是否做出张嘴动作。
当一致时，可以确定状态信息序列中该状态信息下的待检测对象为活体对象，否则，认为是非活体对象。对于状态信息序列中的每个状态信息对应的子检测结果，进行投票操作等方式得到最终的检测结果。
作为又一示例，当三种序列中的信息的变化时机、包括待检测对象的图像或视频的采集时机不同时，虽然变化时机不同，但是可以根据时间信息确定当前时间下三种序列中正在呈现的信息。进而，可以确定所采集的待检测对象的状态信息，与数据采集时刻所对应的三种序列中应该呈现的信息是否对应，以确定最终的检测结果。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下方式执行上述步骤203：
第一，根据位置状态信息序列，确定表征待检测对象是否为活体对象的第一子检测结果。
本实现方式中，上述执行主体可以根据位置状态信息序列中的多个位置状态信息，确定待检测对象是否基于识别区域的引导而发生移动，响应于确定待检测对象发生移动，确定表征待检测对象是活体对象的第一子检测结果；否则，确定表征待检测对象不是活体对象的第一子检测结果。
第二，根据光线状态信息序列，确定表征待检测对象是否为活体对象的第二子检测结果。
本实现方式中，上述执行主体可以根据光线状态信息序列中的多个光线状态信息，确定待检测对象是否基于光线的改变而使得周围的光线环境信息发生改变，响应于确定待检测对象的光线环境状态信息发生变化，确定表征 待检测对象是活体对象的第二子检测结果；否则，确定表征待检测对象不是活体对象的第二子检测结果。
第三，根据动作状态信息序列，确定表征待检测对象是否为活体对象的第三子检测结果。
本实现方式中，上述执行主体可以根据动作状态信息序列中的多个动作状态信息，确定待检测对象是否按照动作序列做出相应的动作，响应于确定待检测对象的按照动作序列做出相应的动作，确定表征待检测对象是活体对象的第三子检测结果；否则，确定表征待检测对象不是活体对象的第三子检测结果。
第四，根据第一子检测结果、第二子检测结果和第三子检测结果，确定检测结果。
本实现方式中，上述执行主体可以采用各种方式根据第一子检测结果、第二子检测结果和第三子检测结果，确定检测结果。例如，采用或逻辑，只要第一子检测结果、第二子检测结果和第三子检测结果中包括表征待检测对象为非活体对象的结果，则最终的检测结果指示待检测对象为非活体对象；采用投票方式，将第一子检测结果、第二子检测结果和第三子检测结果中相同结果的数量最多的结果确定为最终的检测结果；综合判断的方法，包括但不限于逻辑推理、模型预测、机器学习等方法。
在一些实现方式中，可以根据活体检测对应的场景，确定根据第一子检测结果、第二子检测结果和第三子检测结果得到最终的检测结果的方式。作为示例，当应用场景的安全度要求较高时，可以基于或逻辑进行处理；当当应用场景的安全度要求较低时，可以根据投片方式进行处理。
本实现方式中，对于位置、光线、动作相关的多种检测方式，分别得到对应的子检测结果，进而根据多个子检测结果确定最终的检测结果，提高了多种检测方式的独立性，各种检测方式互不影响，进一步提高了最终得到的检测结果的准确度。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下方式执行上述第一步骤：比对位置状态信息序列和位置序列，确定第一子检测结果。具体的，当位置状态信息序列中多个位置状态信息和位置序列中的多个位置信息一一对应，相对应的信息之间是一致的，则确定表征待检测对象为 活体对象的第一子检测结果，否则，确定表征待检测对象为非活体对象的第一子检测结果。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下方式执行上述第二步骤：比对光线状态信息序列和光线序列，确定第二子检测结果。具体的，当光线状态信息序列中多个光线状态信息和光线序列中的多个光线信息一一对应，相对应的信息之间是一致的，则确定表征待检测对象为活体对象的第二子检测结果，否则，确定表征待检测对象为非活体对象的第二子检测结果。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下方式执行上述第三步骤：比对动作状态信息序列和动作序列，确定第三子检测结果。具体的，当动作状态信息序列中多个动作状态信息和动作序列中的多个动作信息一一对应，相对应的信息之间是一致的，则确定表征待检测对象为活体对象的第三子检测结果，否则，确定表征待检测对象为非活体对象的第三子检测结果。
在本实施例的一些可选的实现方式中，上述执行主体还可以确定待检测对象的特征数据；根据特征数据，确定表征待检测对象是否为活体对象的第四子检测结果。
作为示例，上述执行主体可以将获取的待检测对象的图像或视频数据输入活体检测模型，活体检测模型中的特征提取网络提取待检测对象的特征数据(例如，面部的特征数据)；分类网络根据特征数据确定表征待检测对象是否为活体对象的第四子检测结果。
本实现方式中，根据第一子检测结果、第二子检测结果、第三子检测结果和第四子检测结果，确定检测结果。
具体的，上述执行主体可以采用或逻辑方式、投票方式、综合分析方式等多种方式确定检测结果，具体的处理方式可以根据应用场景所需的安全程度确定。
本实现方式中，在基于位置、光线和动作相关的检测方式的基础上，进一步结合基于待检测对象的特征数据的检测方式，进一步提高了活体检测过程的准确度。
继续参见图3，图3是根据本实施例的活体检测方法的应用场景的一个示意图300。在图3的应用场景中，用户301通过终端设备302基于人脸识别方式进行电子转账，电子设备302响应于接收到活体检测请求，将活体检测请求发送至服务器303。服务器生成用于指示待检测对象的识别区域的位置信息的位置序列304，用于指示发光区域的光线信息的光线序列305，以及用于指示待检测对象所参照的动作信息的动作序列306；获取待检测对象基于位置序列304中的位置信息、光线序列305中的光线信息和动作序列306中的动作信息而改变后的状态信息，得到状态信息序列307；基于状态信息序列307，确定表征待检测对象是否为活体对象的检测结果308。
本申请的上述实施例提供的方法，通过响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果，从而结合关于位置、光线、动作的多种活体检测方式，提高了活体检测过程的准确度。
继续参考图4，示出了根据本申请的远程插件的开发、发布方法的一个实施例的示意性流程400，包括如下步骤：
步骤401，响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列。
步骤402，基于位置序列展示识别区域，并确定表征待检测对象的位置信息的位置状态信息序列。
步骤403，比对位置状态信息序列和位置序列，确定表征待检测对象是否为活体对象的第一子检测结果。
步骤404，基于光线序列改变待检测对象的光线环境信息，并确定表征待检测对象的光线环境信息的光线状态信息序列。
步骤405，比对光线状态信息序列和光线序列，确定表征待检测对象是否为活体对象的第二子检测结果。
步骤406，展示动作序列中的动作信息，并确定表征待检测对象所展示的动作信息的动作状态信息序列。
步骤407，比对动作状态信息序列和动作序列，确定表征待检测对象是否为活体对象的第三子检测结果。
步骤408，确定待检测对象的特征数据。
步骤409，根据特征数据，确定表征待检测对象是否为活体对象的第四子检测结果。
步骤410，根据第一子检测结果、第二子检测结果、第三子检测结果和第四子检测结果，确定检测结果。
从本实施例中可以看出，与图2对应的实施例相比，本实施例中的活体检测方法的流程400具体说明了第一子检测结果、第二子检测结果、第三子检测结果和第四子检测结果的确定过程，进一步提高了最终的检测结果的准确度。
继续参考图5，作为对上述各图所示方法的实现，本申请提供了一种活体检测装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，活体检测装置包括：生成单元501，被配置成响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取单元502，被配置成获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；确定单元503，被配置成基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。
在本实施例的一些可选的实现方式中，上述获取单元502，进一步被配置成：基于位置序列展示识别区域，并确定表征待检测对象的位置信息的位置状态信息序列；基于光线序列改变待检测对象的光线环境信息，并确定表征待检测对象的光线环境信息的光线状态信息序列；展示动作序列中的动作信息，并确定表征待检测对象所展示的动作信息的动作状态信息序列。
在本实施例的一些可选的实现方式中，上述确定单元503，进一步被配置 成：根据位置状态信息序列，确定表征待检测对象是否为活体对象的第一子检测结果；根据光线状态信息序列，确定表征待检测对象是否为活体对象的第二子检测结果；根据动作状态信息序列，确定表征待检测对象是否为活体对象的第三子检测结果；根据第一子检测结果、第二子检测结果和第三子检测结果，确定检测结果。
在本实施例的一些可选的实现方式中，上述确定单元503，进一步被配置成：比对位置状态信息序列和位置序列，确定第一子检测结果。
在本实施例的一些可选的实现方式中，上述确定单元503，进一步被配置成：比对光线状态信息序列和光线序列，确定第二子检测结果。
在本实施例的一些可选的实现方式中，上述确定单元503，进一步被配置成：比对动作状态信息序列和动作序列，确定第三子检测结果。
在本实施例的一些可选的实现方式中，上述确定单元503，进一步被配置成：确定待检测对象的特征数据；根据特征数据，确定表征待检测对象是否为活体对象的第四子检测结果；根据第一子检测结果、第二子检测结果、第三子检测结果和第四子检测结果，确定检测结果。
本实施例中，活体检测装置中的生成单元响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取单元获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；确定单元基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果，结合关于位置、光线、动作的多种活体检测方式，提高了活体检测过程的准确度。
下面参考图6，其示出了适于用来实现本申请实施例的设备(例如图1所示的设备101、102、103、105)的计算机系统600的结构示意图。图6示出的设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统600包括处理器(例如CPU，中央处理器)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加 载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM603中，还存储有系统600操作所需的各种程序和数据。处理器601、ROM602以及RAM603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本申请的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本申请的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被处理器601执行时，执行本申请的方法中限定的上述功能。
需要说明的是，本申请的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还 可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码，程序设计语言包括面向目标的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如”C”语言或类似的程序设计语言。程序代码可以完全地在客户计算机上执行、部分地在客户计算机上执行、作为一个独立的软件包执行、部分在客户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到客户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本申请各种实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器，包括生成单元、获取单元和确定单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，生成单元还可以被描述为“响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列， 以及用于指示待检测对象所参照的动作信息的动作序列的单元”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的设备中所包含的；也可以是单独存在，而未装配入该设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该计算机设备：响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示待检测对象所参照的动作信息的动作序列；获取待检测对象基于位置序列中的位置信息、光线序列中的光线信息和动作序列中的动作信息而改变后的状态信息，得到状态信息序列；基于状态信息序列，确定表征待检测对象是否为活体对象的检测结果。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (17)

  1. 一种活体检测方法，包括：
    响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示所述待检测对象所参照的动作信息的动作序列；
    获取所述待检测对象基于所述位置序列中的位置信息、所述光线序列中的光线信息和所述动作序列中的动作信息而改变后的状态信息，得到状态信息序列；
    基于所述状态信息序列，确定表征所述待检测对象是否为活体对象的检测结果。
  2. 根据权利要求1所述的方法，其中，所述获取所述待检测对象基于所述位置序列中的位置信息、所述光线序列中的光线信息和所述动作序列中的动作信息而改变后的状态信息，得到状态信息序列，包括：
    基于所述位置序列展示所述识别区域，并确定表征所述待检测对象的位置信息的位置状态信息序列；
    基于所述光线序列改变所述待检测对象的光线环境信息，并确定表征所述待检测对象的光线环境信息的光线状态信息序列；
    展示所述动作序列中的动作信息，并确定表征所述待检测对象所展示的动作信息的动作状态信息序列。
  3. 根据权利要求2所述的方法，其中，所述基于所述状态信息序列，确定表征所述待检测对象是否为活体对象的检测结果，包括：
    根据所述位置状态信息序列，确定表征所述待检测对象是否为活体对象的第一子检测结果；
    根据所述光线状态信息序列，确定表征所述待检测对象是否为活体对象的第二子检测结果；
    根据所述动作状态信息序列，确定表征所述待检测对象是否为活体对象的第三子检测结果；
    根据所述第一子检测结果、所述第二子检测结果和所述第三子检测结果，确定所述检测结果。
  4. 根据权利要求3所述的方法，其中，所述根据所述位置状态信息序列，确定表征所述待检测对象是否为活体对象的第一子检测结果，包括：
    比对所述位置状态信息序列和所述位置序列，确定所述第一子检测结果。
  5. 根据权利要求3-4任一项所述的方法，其中，所述根据所述光线状态信息序列，确定表征所述待检测对象是否为活体对象的第二子检测结果，包括：
    比对所述光线状态信息序列和所述光线序列，确定所述第二子检测结果。
  6. 根据权利要求3-5任一项所述的方法，其中，所述根据所述动作状态信息序列，确定表征所述待检测对象是否为活体对象的第三子检测结果，包括：
    比对所述动作状态信息序列和所述动作序列，确定所述第三子检测结果。
  7. 根据权利要求3-6任一项所述的方法，其中，还包括：
    确定所述待检测对象的特征数据；
    根据所述特征数据，确定表征所述待检测对象是否为活体对象的第四子检测结果；以及
    所述根据所述第一子检测结果、所述第二子检测结果和所述第三子检测结果，确定所述检测结果，包括：
    根据所述第一子检测结果、所述第二子检测结果、所述第三子检测结果和所述第四子检测结果，确定所述检测结果。
  8. 一种活体检测装置，包括：
    生成单元，被配置成响应于接收到活体检测请求，生成用于指示待检测对象的识别区域的位置信息的位置序列，用于指示发光区域的光线信息的光线序列，以及用于指示所述待检测对象所参照的动作信息的动作序列；
    获取单元，被配置成获取所述待检测对象基于所述位置序列中的位置信息、所述光线序列中的光线信息和所述动作序列中的动作信息而改变后的状态信息，得到状态信息序列；
    确定单元，被配置成基于所述状态信息序列，确定表征所述待检测对象是否为活体对象的检测结果。
  9. 根据权利要求8所述的活体检测装置，所述获取单元，进一步被配置成：
    基于所述位置序列展示所述识别区域，并确定表征所述待检测对象的位置信息的位置状态信息序列；
    基于所述光线序列改变所述待检测对象的光线环境信息，并确定表征所述待检测对象的光线环境信息的光线状态信息序列；
    展示所述动作序列中的动作信息，并确定表征所述待检测对象所展示的动作信息的动作状态信息序列。
  10. 根据权利要求9所述的活体检测装置，所述确定单元，进一步被配置成：
    根据所述位置状态信息序列，确定表征所述待检测对象是否为活体对象的第一子检测结果；
    根据所述光线状态信息序列，确定表征所述待检测对象是否为活体对象的第二子检测结果；
    根据所述动作状态信息序列，确定表征所述待检测对象是否为活体对象的第三子检测结果；
    根据所述第一子检测结果、所述第二子检测结果和所述第三子检测结果，确定所述检测结果。
  11. 根据权利要求10所述的活体检测装置，所述确定单元，进一步被配置成：
    比对所述位置状态信息序列和所述位置序列，确定所述第一子检测结果。
  12. 根据权利要求10-11任一项所述的活体检测装置，所述确定单元，进一步被配置成：
    比对所述光线状态信息序列和所述光线序列，确定所述第二子检测结果。
  13. 根据权利要求10-12任一项所述的活体检测装置，所述确定单元，进一步被配置成：
    比对所述动作状态信息序列和所述动作序列，确定所述第三子检测结果。
  14. 根据权利要求10-13任一项所述的活体检测装置，所述确定单元，进一步被配置成：
    确定所述待检测对象的特征数据；
    根据所述特征数据，确定表征所述待检测对象是否为活体对象的第四子检测结果；
    根据所述第一子检测结果、所述第二子检测结果、所述第三子检测结果和所述第四子检测结果，确定所述检测结果。
  15. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-7中任一所述的方法。
  16. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的方法。
  17. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现如权利要求1-7中任一项所述的方法。
PCT/CN2023/097428 2022-10-10 2023-05-31 活体检测方法及装置 WO2024077971A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211242072.8 2022-10-10
CN202211242072.8A CN115512447A (zh) 2022-10-10 2022-10-10 活体检测方法及装置

Publications (1)

Publication Number Publication Date
WO2024077971A1 true WO2024077971A1 (zh) 2024-04-18

Family

ID=84511126

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/097428 WO2024077971A1 (zh) 2022-10-10 2023-05-31 活体检测方法及装置

Country Status (2)

Country Link
CN (1) CN115512447A (zh)
WO (1) WO2024077971A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115512447A (zh) * 2022-10-10 2022-12-23 京东科技控股股份有限公司 活体检测方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190019024A1 (en) * 2017-07-17 2019-01-17 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Method for Iris Recognition and Related Products
CN109886080A (zh) * 2018-12-29 2019-06-14 深圳云天励飞技术有限公司 人脸活体检测方法、装置、电子设备及可读存储介质
CN111274928A (zh) * 2020-01-17 2020-06-12 腾讯科技（深圳）有限公司 一种活体检测方法、装置、电子设备和存储介质
CN114596638A (zh) * 2020-11-30 2022-06-07 华为技术有限公司 人脸活体检测方法、装置及存储介质
CN114724071A (zh) * 2022-04-18 2022-07-08 北京市商汤科技开发有限公司 信息检测方法、装置、电子设备及存储介质
CN115512447A (zh) * 2022-10-10 2022-12-23 京东科技控股股份有限公司 活体检测方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190019024A1 (en) * 2017-07-17 2019-01-17 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Method for Iris Recognition and Related Products
CN109886080A (zh) * 2018-12-29 2019-06-14 深圳云天励飞技术有限公司 人脸活体检测方法、装置、电子设备及可读存储介质
CN111274928A (zh) * 2020-01-17 2020-06-12 腾讯科技（深圳）有限公司 一种活体检测方法、装置、电子设备和存储介质
CN114596638A (zh) * 2020-11-30 2022-06-07 华为技术有限公司 人脸活体检测方法、装置及存储介质
CN114724071A (zh) * 2022-04-18 2022-07-08 北京市商汤科技开发有限公司 信息检测方法、装置、电子设备及存储介质
CN115512447A (zh) * 2022-10-10 2022-12-23 京东科技控股股份有限公司 活体检测方法及装置

Also Published As

Publication number Publication date
CN115512447A (zh) 2022-12-23

Similar Documents

Publication Publication Date Title
WO2020000879A1 (zh) 图像识别方法和装置
WO2019242222A1 (zh) 用于生成信息的方法和装置
WO2020006963A1 (zh) 生成图像检测模型的方法和装置
US10691928B2 (en) Method and apparatus for facial recognition
WO2020024484A1 (zh) 用于输出数据的方法和装置
JP6030240B2 (ja) 顔認識のための方法および装置
KR102488530B1 (ko) 동영상을 생성하기 위한 방법 및 장치
CN109993150B (zh) 用于识别年龄的方法和装置
WO2020062493A1 (zh) 图像处理方法和装置
WO2020006964A1 (zh) 图像检测方法和装置
WO2020019591A1 (zh) 用于生成信息的方法和装置
WO2020029466A1 (zh) 图像处理方法和装置
US11087140B2 (en) Information generating method and apparatus applied to terminal device
WO2020000876A1 (zh) 用于生成模型的方法和装置
WO2021083069A1 (zh) 用于训练换脸模型的方法和设备
TW202011260A (zh) 活體檢測方法、裝置和電腦可讀取儲存媒介
WO2020056902A1 (zh) 用于处理嘴部图像的方法和装置
WO2020211573A1 (zh) 用于处理图像的方法和装置
WO2024077971A1 (zh) 活体检测方法及装置
US11210563B2 (en) Method and apparatus for processing image
CN112149615A (zh) 人脸活体检测方法、装置、介质及电子设备
CN109766496A (zh) 一种内容风险识别方法、系统、设备及介质
WO2020034981A1 (zh) 编码信息的生成方法和识别方法
WO2020052062A1 (zh) 检测方法和装置
CN110059624A (zh) 用于检测活体的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23876182

Country of ref document: EP

Kind code of ref document: A1