CN113100734B - Living body detection method, apparatus, medium, and computer program product - Google Patents
Living body detection method, apparatus, medium, and computer program product Download PDFInfo
- Publication number
- CN113100734B CN113100734B CN202110405171.2A CN202110405171A CN113100734B CN 113100734 B CN113100734 B CN 113100734B CN 202110405171 A CN202110405171 A CN 202110405171A CN 113100734 B CN113100734 B CN 113100734B
- Authority
- CN
- China
- Prior art keywords
- signal
- echo
- frequency domain
- living body
- preset
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The application discloses a living body detection method, a device, a medium and a computer program product, wherein the living body detection method comprises the following steps: receiving an echo signal generated by a target to be detected based on a sound wave signal; extracting a vibration signal in a preset vital sign signal frequency band from the echo signal, judging whether the vibration signal is a vital sign signal or not, and obtaining a signal judgment result; and detecting whether the target to be detected is a living body or not based on the signal judgment result. The method and the device solve the technical problem of the living body detection accuracy in face recognition.
Description
Technical Field
The present application relates to the field of face recognition technology for financial technology (Fintech), and in particular, to a method, device, medium, and computer program product for detecting a living body.
Background
With the continuous development of financial science and technology, especially internet science and technology, more and more technologies (such as distributed technology, artificial intelligence and the like) are applied to the financial field, but the financial industry also puts higher requirements on the technologies, for example, higher requirements on the distribution of backlog in the financial industry are also put forward.
With the continuous development of computer software, artificial intelligence and big data cloud service application, the application of the face recognition technology is more and more extensive. Since the face data is easy to obtain, it is becoming more and more common to attack the face recognition system by means of face photos, face videos, etc. of other people, and how to recognize that the face in the photos or videos is the user himself, i.e. to verify whether the user is operated by the real living body himself, which is more and more important in the face recognition system, the comparison document (CN 110688957A) discloses a method for performing living body detection based on sound wave signals when performing face recognition, i.e. based on the principle that reflectors made of different materials reflect sound wave signals differently, whether the echo of the sound wave signals is reflected by the skin is recognized, and further whether the target of the reflected sound wave signals is a living body is recognized, but a malicious attacker only needs to forge a detection target similar to the face material to reflect the sound wave signals to attack the face recognition system, so the living body detection accuracy of the method is low.
Disclosure of Invention
The present application mainly aims to provide a method, an apparatus, a medium, and a computer program product for detecting a living body, which aim to solve the technical problem of low accuracy of living body detection in face recognition in the prior art.
To achieve the above object, the present application provides a living body detecting method applied to a living body detecting apparatus, the living body detecting method including:
receiving an echo signal generated by a target to be detected based on a sound wave signal;
extracting a vibration signal in a preset vital sign signal frequency band from the echo signal, judging whether the vibration signal is a vital sign signal or not, and obtaining a signal judgment result;
and detecting whether the target to be detected is a living body or not based on the signal discrimination result.
The present application further provides a living body detection apparatus, the living body detection apparatus is a virtual apparatus, just the living body detection apparatus is applied to the living body detection device, the living body detection apparatus includes:
the receiving module is used for receiving an echo signal generated by a target to be detected based on the sound wave signal;
the judging module is used for extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal or not and obtaining a signal judging result;
and the living body detection module is used for detecting whether the target to be detected is a living body or not based on the signal judgment result.
The application also provides a biopsy device, the biopsy device is an entity device, the biopsy device includes: a memory, a processor and a program of the living body detecting method stored on the memory and executable on the processor, the program of the living body detecting method being executable by the processor to implement the steps of the living body detecting method as described above.
The present application also provides a medium which is a readable storage medium having stored thereon a program for implementing the living body detection method, the program implementing the steps of the living body detection method as described above when executed by a processor.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method of living body detection as described above.
Compared with the technical means of carrying out in-vivo detection on human face characteristics based on a human face image sequence or human face video adopted in the prior art, the method comprises the steps of firstly receiving echo signals generated by a target to be detected based on sound wave signals, extracting vibration signals in a preset in-vivo sign signal frequency band from the echo signals, judging whether the vibration signals are in-vivo sign signals or not, and obtaining a signal judgment result, wherein the in-vivo sign signals comprise wave signals generated by heartbeat and wave signals generated by respiration, and further detecting whether the target to be detected is in-vivo or not based on the signal judgment result, so that the aim of carrying out in-vivo detection on micro vibration signals generated based on in-vivo sign signals in the echo signals is realized by judging whether the vibration signals in the preset in-vivo sign signal frequency band are signals generated by in-vivo signs or not, the in-vivo detection on the target to be detected is realized, and even if a malicious attacker forges the detection target similar to the human face materials so as to reflect the human face signals, the defect that the human face detection technology can be accurate is overcome.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
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 description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a first embodiment of a biopsy method of the present application;
fig. 2 is a schematic diagram illustrating that when a face video is shot in the living body detection method of the present application, an acoustic wave signal is transmitted to a living body face, and an echo signal generated by a face skin of the living body face based on the acoustic wave signal is received;
FIG. 3 is a schematic flow chart of a second embodiment of the in-vivo detection method of the present application;
FIG. 4 is a schematic flow chart of a third embodiment of the in-vivo detection method of the present application;
FIG. 5 is a schematic flow chart of a fourth embodiment of the in-vivo detection method according to the present application;
fig. 6 is a schematic structural diagram of a hardware operating environment related to the in-vivo detection method in the embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In a first embodiment of the biopsy method according to the present application, with reference to fig. 1, the biopsy method includes:
step S10, receiving an echo signal generated by a target to be detected based on a sound wave signal;
in this embodiment, it should be noted that the object to be detected is an object that needs to be subjected to face recognition, and when performing face recognition, a face video usually needs to be recorded, and at this time, a sound wave signal may be emitted to the object to be detected, where the sound wave signal is preferably a high-frequency signal outside a human hearing range, for example, a high-sound-wave frequency signal around 6-25 kHz.
Receiving an echo signal generated by a target to be detected based on a sound wave signal, specifically, transmitting the sound wave signal to the target to be detected through a loudspeaker of a front-end device, wherein the front-end device is a device for face recognition, such as a mobile phone, a bracelet, a watch, and the like, and then receiving a reflected wave of the target to be detected to the sound wave signal through a microphone of the front-end device to obtain the echo signal, wherein if the target to be detected is a real living body, the echo signal is obtained by reflecting the sound wave signal by skin of the target to be detected, and the skin vibrates due to vital signs of the real living body, and then the echo signal carries a vital sign signal, wherein the vital sign signal comprises heartbeat, respiration, and if the target to be detected is not the real living body, the echo signal does not carry the vital sign signal.
Wherein the target to be detected comprises a living human face,
the step of receiving an echo signal generated by a target to be detected based on the sound wave signal comprises the following steps:
step S11, receiving an echo signal generated by the facial skin of the living body face based on the sound wave signal, wherein the facial skin of the living body face vibrates along with the heartbeat and the breath of the living body corresponding to the living body face;
in this embodiment, it should be noted that the target to be detected includes a living human face when a human face video for performing human face recognition is recorded, and then an acoustic wave signal may be transmitted to the living human face through a speaker of the front-end device.
Receiving an echo signal generated by the face skin of the living body face based on the sound wave signal, wherein the face skin of the living body face vibrates along with the heartbeat and the respiration of the living body corresponding to the living body face, specifically, receiving a reflected wave of the face skin of the face to the sound wave signal through a microphone of a front-end device to obtain the echo signal, wherein the face skin of the living body face vibrates along with the heartbeat and the respiration of the living body corresponding to the living body face, so that the echo signal carries the heartbeat and the respiration signal corresponding to the heartbeat and the respiration of the living body, and as shown in fig. 2, when a face video is shot, the sound wave signal is transmitted to the living body face, and a schematic diagram of the echo signal generated by the face skin of the living body face based on the sound wave signal is received.
And S20, extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal or not, and obtaining a signal judgment result.
In this embodiment, a vibration signal in a preset vital sign signal frequency band is extracted from the echo signal, and it is determined whether the vibration signal is a vital sign signal, so as to obtain a signal determination result, specifically, the echo signal is converted from a time domain to a frequency domain, so as to obtain echo frequency domain data, and then the echo frequency domain data is filtered, and a vibration signal in the preset vital sign signal frequency band is extracted from the echo signal, where the preset vital sign signal frequency band is a signal frequency band in which a signal generated by a preset vital sign may exist, so as to determine whether the vibration signal is a vital sign signal, if so, the signal determination result is to determine that the vibration signal is a vital sign signal, and if not, the signal determination result is to determine that the vibration signal is a non-vital sign signal.
Wherein the vibration signal comprises at least one of a respiration echo frequency domain signal and a heartbeat echo frequency domain signal,
the step of judging whether the vibration signal is a vital sign signal or not and obtaining a signal judgment result comprises the following steps:
a10, classifying the respiratory echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result; judging whether the breath echo frequency domain signal is the vital sign signal or not based on the first signal classification result to obtain a signal judgment result;
in this embodiment, it should be noted that the respiration echo frequency domain signal is a frequency band signal suspected to be associated with the respiration sign, and the frequency of the respiration echo frequency domain signal is in a second preset frequency band, where the second preset frequency band is a specific frequency range where a frequency domain sound wave signal generated by the respiration sign is located, and the preset first sound wave classification model is a machine learning model for classifying the respiration echo frequency domain signal.
Classifying the respiratory echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result; and judging whether the respiration echo frequency domain signal is the living body sign signal or not based on the first signal classification result, obtaining the signal judgment result, specifically, inputting a preset first sound wave classification model by representing a second echo frequency domain feature corresponding to the respiration echo frequency domain signal, mapping the second echo frequency domain feature representation into a second signal probability value, wherein the second echo frequency domain feature representation is a coding matrix representing the respiration echo frequency domain signal, the second signal probability value is a probability value that the respiration echo frequency domain signal belongs to the living body sign signal, mapping the second signal probability value into a second sound wave classification tag value, wherein the second sound wave classification tag value is an identification value of the category of the respiration echo frequency domain signal, taking the second sound wave classification tag value as a first signal classification result, comparing the second sound wave classification tag value with a preset sound wave classification tag value, judging whether the respiration echo frequency domain signal is the living body sign signal if the second sound wave classification tag value is consistent with the preset sound wave classification tag value, and judging whether the second sound wave classification tag value is inconsistent with the preset sound wave classification tag value, and judging whether the respiration echo frequency domain signal is not in the living body sign signal, and judging whether the second sound wave classification tag value is inconsistent with the biological sign signal.
Step B10, classifying the heartbeat echo frequency domain signals based on a preset second sound wave classification model to obtain a second signal classification result; and judging whether the vibration signal is the vital sign signal or not based on the second signal classification result, and obtaining the signal judgment result.
In this embodiment, it should be noted that the heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with the heartbeat physical sign, and the frequency of the heartbeat echo frequency domain signal is in a third preset frequency band, where the third preset frequency band is a specific frequency range where a frequency domain acoustic wave signal generated by the heartbeat physical sign is located, and the preset second sound wave classification model is a machine learning model for classifying the heartbeat echo frequency domain signal.
Classifying the heartbeat echo frequency domain signals based on a preset second sound wave classification model to obtain a second signal classification result; and judging whether the vibration signal is the vital sign signal or not based on the second signal classification result, obtaining the signal judgment result, specifically, representing and inputting a preset second sound wave classification model by using a third echo frequency domain feature corresponding to the heartbeat echo frequency domain signal, mapping the third echo frequency domain feature representation into a third signal probability value, wherein the third echo frequency domain feature represents an encoding matrix representing the heartbeat echo frequency domain signal, the third signal probability value is a probability value that the heartbeat echo frequency domain signal belongs to the vital sign signal, further mapping the third signal probability value into a third sound wave classification tag value, wherein the third sound wave classification tag value is an identification value of a category of the heartbeat echo frequency domain signal, further using the third sound wave classification tag value as a second signal classification result, further comparing the third sound wave classification tag value with a preset sound wave classification tag value, if the third sound wave classification tag value is consistent with the preset sound wave classification tag value, judging whether the heartbeat echo frequency domain signal is the vital sign signal, if the third sound wave classification tag value is inconsistent with the preset sound wave classification tag value, further judging whether the heartbeat echo signal is in a target frequency domain, and whether the heartbeat echo signal is not capable of detecting the vital sign signal.
And step S30, detecting whether the target to be detected is a living body or not based on the signal judgment result.
In this embodiment, whether the target to be detected is a living body is detected based on the signal determination result, specifically, if the signal determination result is that the vibration signal is determined to be a vital sign signal, the target to be detected is determined to be a living body, and if the signal determination result is that the vibration signal is determined to be a non-vital sign signal, the target to be detected is determined not to be a living body.
After the step of extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal, and obtaining a signal judgment result, the living body detection method further comprises the following steps:
s40, acquiring face video data of the target to be detected, and performing living body detection on the target to be detected based on the face video data to obtain a video living body detection result;
in this embodiment, face video data of the target to be detected is acquired, and living body detection is performed on the target to be detected based on the face video data, so as to obtain a video living body detection result, specifically, face video data taken from the target to be detected when an acoustic signal is transmitted to the target to be detected is acquired, and then image detection is performed on each time frame image in the face video data based on a preset image detection model, so as to determine whether an action living body exists in the face video data, so as to obtain a video living body detection result, where the action living body is a living body with action change of a face, such as a blinking living body.
In another practical manner, step S30 further includes:
the method comprises the steps of obtaining face video data shot by a target to be detected when a sound wave signal is transmitted to the target to be detected, further carrying out image detection on images of each time frame in the face video data based on a preset image detection model, judging whether a digital living body exists in the face video data, and obtaining a video living body detection result, wherein the digital living body is a living body with voice information and mouth action, further judging that the living body is a real living body if the voice information is consistent with the corresponding semantics of the mouth action, and judging that the living body is not a real living body if the voice information is inconsistent with the corresponding semantics of the mouth action.
And S50, judging whether the target to be detected is a living body or not based on the video living body detection result and the signal judgment result, and obtaining a target living body detection result.
In this embodiment, whether the target to be detected is a living body is determined based on the video living body detection result and the signal discrimination result, and a target living body detection result is obtained, specifically, if the target to be detected is determined to be a real living body based on both the video living body detection result and the signal discrimination result, the target to be detected is determined to be a real living body, the obtained target living body detection result is determined to be a real living body, if the target to be detected is not determined to be a real living body based on both the video living body detection result and the signal discrimination result, the target to be detected is determined not to be a real living body, and the obtained target living body detection result is determined not to be a real living body, so that the purpose of performing living body detection by combining a vibration signal in a preset living body sign signal frequency band in an echo signal based on a living body detection performed by a face video is achieved, the accuracy of the living body detection is improved, and further, the accuracy of the face recognition and the safety of the face recognition system are improved.
The embodiment of the application provides a living body detection method, compared with a technical means for performing living body detection based on a human face image sequence or human face video adopted by the prior art, the embodiment of the application firstly receives an echo signal generated by a target to be detected based on a sound wave signal, extracts a vibration signal in a preset living body sign signal frequency band from the echo signal, and judges whether the vibration signal is a living body sign signal to obtain a signal judgment result, wherein the living body sign signal comprises a wave signal generated by heartbeat, a wave signal generated by respiration and the like, and then detects whether the target to be detected is a living body based on the signal judgment result, so that the living body detection is performed on the target to be detected by judging whether the vibration signal in the preset living body sign signal frequency band is a signal generated by living body signs, namely, the purpose of performing the living body detection based on a tiny vibration signal generated by the living body signs is realized, and even if a malicious attacker forges a detection target similar to the human face material to reflect the sound wave signal, the human face identification system can be damaged, and the defect that the human face identification technology is accurate is overcome.
Further, referring to fig. 3, in another embodiment of the present application, based on the first embodiment of the present application, the step of extracting a vibration signal in a preset vital sign signal frequency band from the echo signal includes:
step S21, carrying out Fourier transform on the echo signal to obtain echo frequency domain data corresponding to the echo signal;
in this embodiment, the echo signal is fourier-transformed to obtain echo frequency domain data corresponding to the echo signal, specifically, the echo signal is fourier-transformed to convert the echo signal from a time domain to a frequency domain, so as to obtain echo frequency domain data, where the echo frequency domain data is spectrogram data of the echo signal in a frequency domain.
And S22, filtering the echo frequency domain data, and screening the echo frequency domain data for a vibration signal in the preset vital sign signal frequency band.
In this embodiment, it should be noted that, for a real living body, the vital sign signal in the echo frequency domain data is usually in a specific frequency range, for example, the respiration signal generated by respiration of the living body is usually in 0.2Hz to 0.35Hz, the heart rate signal generated by heartbeat of the living body is usually in 0.5Hz to 3.7Hz, and the like.
Through right echo frequency domain data carries out filtering the screening is in among the echo frequency domain data predetermine the vibration signal of vital sign signal frequency channel, specifically, through right echo frequency domain data carries out filtering the echo frequency domain data filter the frequency band signal except being in the specific signal of predetermineeing vital sign signal frequency channel among the echo frequency domain data, obtain vibration signal, wherein, predetermine the vital sign signal frequency channel and do the specific frequency range that the vital sign signal that the vital sign corresponds, vibration signal is in among the echo frequency domain data predetermine the frequency band signal in the vital sign signal frequency channel.
Wherein the preset vital sign signal frequency band comprises a first preset frequency band, a second preset frequency band and a third preset frequency band, the vibration signal at least comprises one of a respiration and heartbeat echo frequency domain signal, a respiration echo frequency domain signal and a heartbeat echo frequency domain signal,
the step of screening the echo frequency domain data for vibration signals in the preset vital sign signal frequency band by filtering the echo frequency domain data comprises:
step C10, filtering the echo frequency domain data, and screening signal data in a first preset frequency band commonly associated with respiratory signs and heartbeat signs from the echo frequency domain data to obtain respiratory and heartbeat echo frequency domain signals;
in this embodiment, it should be noted that the vital signs include respiratory signs and heartbeat signs, and the first preset frequency band is a specific frequency range in which a respiratory signal corresponding to the respiratory signs and a heart rate signal corresponding to the heartbeat signs are located together, for example, if the respiratory signal generated by respiration of the living body is usually 0.2Hz to 0.35Hz, and the heart rate signal generated by heartbeat of the living body is usually 0.5Hz to 3.7Hz, the first preset frequency band is 0.2Hz to 3.7Hz.
Additionally, it should be noted that the respiration and heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with the respiration sign and the heartbeat sign together, and the frequency of the respiration and heartbeat echo frequency domain signal is in a first preset frequency band.
Through right echo frequency domain data filters the signal data that is in the first predetermined frequency channel that respiratory sign and heartbeat sign are correlated with jointly is selected among the echo frequency domain data, obtains respiratory and heartbeat echo frequency domain signal, specifically, through right echo frequency domain data filters the frequency channel signal except the specific signal that is in the first predetermined frequency channel that respiratory sign and heartbeat sign correspond jointly in the echo frequency domain data, obtains respiratory and heartbeat echo frequency domain signal.
Step D10, filtering the echo frequency domain data, and screening signal data in a second preset frequency band associated with the respiratory sign from the echo frequency domain data to obtain a respiratory echo frequency domain signal;
in this embodiment, it should be noted that the second preset frequency band is a specific frequency range where a respiratory signal corresponding to the respiratory sign is located, the respiratory echo frequency domain signal is a frequency band signal suspected to be associated with the respiratory sign, and the frequency of the respiratory echo frequency domain signal is in the second preset frequency band.
Through right echo frequency domain data filters, is in echo frequency domain data screens the signal data of the second preset frequency channel that respiratory sign is correlated with, obtains respiratory echo frequency domain signal, specifically, through right echo frequency domain data filters the frequency channel signal except being in with the specific signal of the second preset frequency channel that respiratory sign corresponds in the echo frequency domain data, obtains respiratory echo frequency domain signal.
And E10, filtering the echo frequency domain data, and screening signal data in a third preset frequency band associated with the heartbeat sign from the echo frequency domain data to obtain the heartbeat echo frequency domain signal.
In this embodiment, it should be noted that the third preset frequency band is a specific frequency range where a heart rate signal corresponding to the heartbeat physical sign is located, the heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with the heartbeat physical sign, and the frequency of the heartbeat echo frequency domain signal is in the third preset frequency band.
Through right echo frequency domain data filters, select to be in among the echo frequency domain data the signal data of the third preset frequency channel that the heartbeat sign is correlated with obtains the heartbeat echo frequency domain signal, specifically, through right echo frequency domain data filters the echo frequency domain data in the echo frequency domain data filter except being in with the frequency channel signal of the third preset frequency channel that the heartbeat sign corresponds obtains the heartbeat echo frequency domain signal.
Additionally, it should be noted that, according to actual requirements, an echo frequency domain signal may be arbitrarily selected from the respiration and heartbeat echo frequency domain signal, the respiration echo frequency domain signal, and the heartbeat echo frequency domain signal as the vibration signal, for example, the respiration echo frequency domain signal and the heartbeat echo frequency domain signal are collectively used as the vibration signal, or the respiration and heartbeat echo frequency domain signal, the respiration echo frequency domain signal, and the heartbeat echo frequency domain signal are collectively used as the echo frequency domain signal, and the like.
The embodiment of the application provides a method for obtaining vibration signal, that is, the echo signal carries out Fourier transform, obtains the echo frequency domain data that the echo signal corresponds, and then through right the echo frequency domain data carries out the filtering the echo frequency domain data in the screening is in predetermine the vibration signal of vital sign signal frequency channel, and then realized gathering the purpose of the vibration signal that is suspected the vibration that produces by the vital sign, and then for judging based on whether the vibration signal is the vital sign signal, and carry out the live body and detect and establish the basis.
Further, referring to fig. 4, based on the first and second embodiments of the present application, in another embodiment of the present application, the vibration signal includes a respiration and heartbeat echo frequency domain signal,
the step of judging whether the vibration signal is a vital sign signal or not and obtaining a signal judgment result comprises the following steps:
step F10, classifying the respiration and heartbeat echo frequency domain signals based on a preset sound wave classification model to obtain a signal classification result;
in this embodiment, it should be noted that the respiration and heartbeat echo frequency domain signals are frequency domain signals in a first preset frequency band in the echo frequency domain data.
Based on a preset sound wave classification model, classifying the respiration and heartbeat echo frequency domain signals to obtain a signal classification result, specifically, representing the input preset sound wave classification model by using a first echo frequency domain feature corresponding to the respiration and heartbeat echo frequency domain signals, mapping the first echo frequency domain feature representation to a first signal probability value, wherein the first echo frequency domain feature representation represents an encoding matrix of the respiration and heartbeat echo frequency domain signals, the first signal probability value is a probability value of the respiration and heartbeat echo frequency domain signals belonging to the vital sign signals, and further mapping the first signal probability value to a first sound wave classification label value, wherein the first sound wave classification label value is an identification value of a category of the respiration and heartbeat echo frequency domain signals, for example, if the first sound wave classification label value is 1, the respiration and heartbeat echo frequency domain signals belong to the vital sign signals, if the first sound wave classification label value is 0, the respiration and heartbeat echo frequency domain signals do not belong to the vital sign signals, the first sound wave classification label value can be mapped to a first sound wave probability function, and then the first sound wave classification label value is used as the first sound wave classification result.
And F20, judging whether the respiration and heartbeat echo frequency domain signals are the vital sign signals or not based on the signal classification result, and obtaining the signal judgment result.
In this embodiment, based on the signal classification result, it is determined whether the breath and heartbeat echo frequency domain signal is the vital sign signal, and the signal determination result is obtained, specifically, the first sound wave classification tag value is compared with a preset sound wave classification tag value, if the first sound wave classification tag value is consistent with the preset sound wave classification tag value, it is determined that the breath and heartbeat echo frequency domain signal is the vital sign signal, the signal determination result is determined as the vital sign signal, if the first sound wave classification tag value is inconsistent with the preset sound wave classification tag value, it is determined that the breath and heartbeat echo frequency domain signal is not the vital sign signal, and the signal determination result is determined as not being the vital sign signal, so that the purpose of performing the in vivo detection by determining whether the breath and heartbeat echo frequency domain signal in a first preset frequency band corresponding to the vital sign signal and breath is the vital sign signal can be realized.
The embodiment of the application provides a method for judging whether a breath and heartbeat echo frequency domain signal is a vital sign signal, namely, classifying the breath and heartbeat echo frequency domain signal based on a preset sound wave classification model to obtain a signal classification result, and then judging whether the breath and heartbeat echo frequency domain signal is the vital sign signal based on the signal classification result to obtain a signal judgment result, namely, classifying the breath and heartbeat echo frequency domain signal through the preset sound wave classification model to realize the judgment of whether the breath and heartbeat echo frequency domain signal is the vital sign signal, and then judging whether a target to be detected is a real living body based on the signal judgment result, namely, realizing the purpose of detecting the living body based on a tiny vibration signal generated by the vital sign, and further laying a foundation for overcoming the technical defect that a malicious attacker forges a detection target similar to a human face material to reflect the sound wave signal and cannot attack a human face recognition system.
Further, referring to fig. 5, based on the first, second and third embodiments of the present application, in another embodiment of the present application, the vibration signal includes at least one of a respiration echo frequency domain signal and a heartbeat echo frequency domain signal,
the step of judging whether the vibration signal is a vital sign signal or not and obtaining a signal judgment result comprises the following steps:
g10, classifying the respiratory echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result;
in this embodiment, it should be noted that the breathing echo frequency domain signal is a frequency band signal in a second preset frequency band in the echo frequency domain data, and the heartbeat echo frequency domain signal is a frequency band signal in a third preset frequency band in the echo frequency domain data.
Classifying the respiration echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result, specifically, inputting a second echo frequency domain feature representation corresponding to the respiration echo frequency domain signals into the preset first sound wave classification model, mapping the second echo frequency domain feature representation into a second signal probability value, wherein the second echo frequency domain feature representation is a coding matrix representing the respiration echo frequency domain signals, the second signal probability value is a probability value that the respiration echo frequency domain signals belong to the vital sign signals, and further mapping the second signal probability value into a second sound wave classification label value, wherein the second sound wave classification label value is an identification value of the category of the respiration echo frequency domain signals, and further takes the second sound wave classification label value as the first signal classification result.
G20, classifying the heartbeat echo frequency domain signals based on a preset second sound wave classification model to obtain a second signal classification result;
in this embodiment, the heartbeat echo frequency domain signals are classified based on a preset second sound wave classification model to obtain a second signal classification result, specifically, a third echo frequency domain feature corresponding to the heartbeat echo frequency domain signals is input into the preset second sound wave classification model, and the third echo frequency domain feature representation is mapped to a third signal probability value, where the third echo frequency domain feature is represented to represent an encoding matrix of the heartbeat echo frequency domain signals, the third signal probability value is a probability value that the heartbeat echo frequency domain signals belong to the vital sign signals, and the third signal probability value is further mapped to a third sound wave classification tag value, where the third sound wave classification tag value is an identification value of a category of the heartbeat echo frequency domain signals, and the third sound wave classification tag value is further used as the second signal classification result.
And G30, judging whether the vibration signal is the vital sign signal or not based on the first signal classification result and the second signal classification result, and obtaining the signal judgment result.
In this embodiment, whether the vibration signal is the living body sign signal is determined based on the first signal classification result and the second signal classification result, and the signal determination result is obtained, specifically, a second sound wave classification tag value and a third sound wave classification tag value are respectively compared with a preset sound wave classification tag value, if the second sound wave classification tag value and the third sound wave classification tag value are both consistent with the preset sound wave classification tag value, the vibration signal is determined to be the living body sign signal, and if the second sound wave classification tag value and the third sound wave classification tag value are not both consistent with the preset sound wave classification tag value, the vibration signal is determined not to be the living body sign signal, so that the signal determination result is obtained, thereby achieving the purpose of performing living body detection by simultaneously determining a respiration echo frequency domain signal in a second preset frequency band corresponding to living body respiration, and determining whether a heartbeat echo frequency domain signal in a third preset frequency band corresponding to living body heartbeat echo is a living body sign signal.
The embodiment of the application provides a method for judging whether a vibration signal is a living body sign signal, namely, classifying a respiration echo frequency domain signal based on a preset first sound wave classification model to obtain a first signal classification result, classifying a heartbeat echo frequency domain signal based on a preset second sound wave classification model to obtain a second signal classification result, judging whether the vibration signal is the living body sign signal based on the first signal classification result and the second signal classification result to obtain a signal judgment result, so that the purpose of carrying out living body detection based on combining the respiration echo frequency domain signal and the heartbeat echo frequency domain signal and judging whether the vibration signal is the living body sign signal is realized, the reliability and the accuracy of the signal judgment result are improved, and then living body detection is carried out based on the signal judgment result, so that the purpose of carrying out living body detection based on a tiny vibration signal generated based on the living body sign is realized, and even if a malicious attacker forges a detection target similar to a human face material to reflect the human face signal, a sound wave identification system cannot be broken, and therefore, the defect of the human face detection system can be overcome the defect that the malicious attacker can falsify the human face signal based on the malicious attacker material.
Referring to fig. 6, fig. 6 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 6, the living body detecting apparatus may include: a processor 1001, such as a CPU, memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory such as a disk memory. The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.
Optionally, the liveness detection device may further include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and the like. The rectangular user interface may comprise a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the biopsy device configuration shown in FIG. 6 does not constitute a limitation of a biopsy device, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 6, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, and a living body detection program. The operating system is a program that manages and controls the hardware and software resources of the liveness detection device, supporting the operation of the liveness detection program as well as other software and/or programs. The network communication module is used to enable communication between the various components within the memory 1005, as well as with other hardware and software in the liveness detection system.
In the living body detecting apparatus shown in fig. 6, the processor 1001 is configured to execute a living body detecting program stored in the memory 1005, and implement the steps of the living body detecting method described in any one of the above.
The specific implementation of the biopsy device of the present application is substantially the same as the embodiments of the biopsy method described above, and is not described herein again.
The embodiment of the present application further provides a living body detection apparatus, the living body detection apparatus is applied to the living body detection device, the living body detection apparatus includes:
the receiving module is used for receiving an echo signal generated by a target to be detected based on the sound wave signal;
the signal discrimination module is used for extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, discriminating whether the vibration signal is a living body sign signal or not and obtaining a signal discrimination result;
and the living body detection module is used for detecting whether the target to be detected is a living body or not based on the signal judgment result.
Optionally, the signal discrimination module is further configured to:
performing Fourier transform on the echo signal to obtain echo frequency domain data corresponding to the echo signal;
and filtering the echo frequency domain data to screen the vibration signals in the preset vital sign signal frequency band from the echo frequency domain data.
Optionally, the signal discrimination module is further configured to:
filtering the echo frequency domain data, and screening signal data in a first preset frequency band which is commonly associated with respiratory signs and heartbeat signs from the echo frequency domain data to obtain respiratory and heartbeat echo frequency domain signals; and/or
Filtering the echo frequency domain data, and screening signal data in a second preset frequency band associated with the respiratory sign from the echo frequency domain data to obtain a respiratory echo frequency domain signal; and/or
And filtering the echo frequency domain data, and screening signal data in a third preset frequency band associated with the heartbeat sign from the echo frequency domain data to obtain the heartbeat echo frequency domain signal.
Optionally, the signal discrimination module is further configured to:
classifying the respiration and heartbeat echo frequency domain signals based on a preset sound wave classification model to obtain a signal classification result;
and judging whether the respiration and heartbeat echo frequency domain signals are the vital sign signals or not based on the signal classification result to obtain the signal judgment result.
Optionally, the signal discrimination module is further configured to:
classifying the respiratory echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result;
classifying the heartbeat echo frequency domain signals based on a preset second sound wave classification model to obtain a second signal classification result;
and judging whether the vibration signal is the living body sign signal or not based on the first signal classification result and the second signal classification result to obtain the signal judgment result.
Optionally, the signal discrimination module is further configured to:
classifying the respiratory echo frequency domain signals based on a preset first sound wave classification model to obtain a first signal classification result; judging whether the respiratory echo frequency domain signal is the living body sign signal or not based on the first signal classification result to obtain a signal judgment result; and/or
Classifying the heartbeat echo frequency domain signals based on a preset second sound wave classification model to obtain a second signal classification result; and judging whether the vibration signal is the vital sign signal or not based on the second signal classification result, and obtaining the signal judgment result.
Optionally, the in-vivo detection device is further configured to:
acquiring face video data of the target to be detected, and performing living body detection on the target to be detected based on the face video data to obtain a video living body detection result;
and judging whether the target to be detected is a living body or not based on the video living body detection result and the signal judgment result to obtain a target living body detection result.
Optionally, the receiving module is further configured to:
and receiving an echo signal generated by the face skin of the living body face based on the sound wave signal, wherein the face skin of the living body face vibrates along with the heartbeat and the respiration of the living body corresponding to the living body face.
The specific implementation of the biopsy device of the present application is substantially the same as the embodiments of the biopsy method described above, and is not described herein again.
The present application provides a medium, which is a readable storage medium, and the readable storage medium stores one or more programs, and the one or more programs are further executable by one or more processors for implementing the steps of the living body detection method described in any one of the above.
The specific implementation of the readable storage medium of the present application is substantially the same as that of each embodiment of the above-mentioned biopsy method, and is not described herein again.
The present application provides a computer program product, and the computer program product includes one or more computer programs, which can also be executed by one or more processors for implementing the steps of the living body detection method described in any one of the above.
The specific implementation of the computer program product of the present application is substantially the same as the embodiments of the above-mentioned biopsy method, and will not be described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent processes, which are directly or indirectly applied to other related technical fields, and which are not limited by the present application, are also included in the scope of the present application.
Claims (15)
1. A living body detection method is applied to a face recognition device, and comprises the following steps:
receiving an echo signal generated by a target to be detected based on a sound wave signal;
extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal or not, and obtaining a signal judgment result, wherein the preset living body sign signal frequency band is a signal frequency band in which a preset signal generated by the vibration of human face skin along with the living body sign exists, the vibration signal comprises a respiration and heartbeat echo frequency domain signal, and the respiration and heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with respiration signs and heartbeat signs;
detecting whether the target to be detected is a living body or not based on the signal discrimination result so as to carry out face recognition;
the target to be detected comprises a living human face, and the step of receiving an echo signal generated by the target to be detected based on the sound wave signal comprises the following steps of:
receiving an echo signal generated by the face skin of the living body face based on the sound wave signal, wherein the face skin of the living body face vibrates along with heartbeat and respiration of a living body corresponding to the living body face;
wherein, the step of judging whether the vibration signal is a vital sign signal or not and obtaining a signal judgment result comprises the following steps:
inputting a first echo frequency domain characteristic representation corresponding to the respiration and heartbeat echo frequency domain signals into a preset sound wave classification model, and mapping the first echo frequency domain characteristic representation into a first signal probability value;
mapping the first signal probability value into a first sound wave classification label value as a signal classification result;
and judging whether the respiration and heartbeat echo frequency domain signals are the vital sign signals or not based on the signal classification result to obtain the signal judgment result.
2. The in-vivo detection method as set forth in claim 1, wherein the step of extracting the vibration signal in the echo signal at the preset vital sign signal frequency band comprises:
performing Fourier transform on the echo signal to obtain echo frequency domain data corresponding to the echo signal;
and filtering the echo frequency domain data to screen the vibration signals in the preset vital sign signal frequency band from the echo frequency domain data.
3. The in-vivo detection method as claimed in claim 2, wherein the preset vital sign signal frequency band comprises a first preset frequency band, and the step of filtering the echo frequency domain data to screen the echo frequency domain data for a vibration signal in the preset vital sign signal frequency band comprises:
and filtering the echo frequency domain data, and screening signal data in a first preset frequency band associated with the respiratory sign and the heartbeat sign in the echo frequency domain data to obtain the respiratory and heartbeat echo frequency domain signals.
4. The in-vivo detection method as claimed in claim 1, wherein after the steps of extracting a vibration signal in a preset frequency band of the in-vivo sign signal from the echo signal, determining whether the vibration signal is the in-vivo sign signal, and obtaining a signal determination result, the in-vivo detection method further comprises:
acquiring face video data of the target to be detected, and performing living body detection on the target to be detected based on the face video data to obtain a video living body detection result;
and judging whether the target to be detected is a living body or not based on the video living body detection result and the signal judgment result, and obtaining a target living body detection result.
5. A living body detection method is applied to a face recognition device, and comprises the following steps:
receiving an echo signal generated by a target to be detected based on a sound wave signal;
extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal or not, and obtaining a signal judgment result, wherein the preset living body sign signal frequency band is a signal frequency band in which a preset signal generated by the vibration of human face skin along with the living body sign exists, the vibration signal comprises a respiration echo frequency domain signal and a heartbeat echo frequency domain signal, the respiration echo frequency domain signal is a frequency band signal suspected to be associated with the respiration sign, and the heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with the heartbeat sign;
detecting whether the target to be detected is a living body or not based on the signal discrimination result so as to carry out face recognition;
the target to be detected comprises a living human face, and the step of receiving an echo signal generated by the target to be detected based on the sound wave signal comprises the following steps of:
receiving an echo signal generated by the facial skin of the living body face based on the sound wave signal, wherein the facial skin of the living body face vibrates along with the heartbeat and the respiration of the living body corresponding to the living body face;
the step of judging whether the vibration signal is a living body sign signal or not and obtaining a signal judgment result comprises the following steps:
inputting a second echo frequency domain feature representation corresponding to the respiration echo frequency domain signal into a preset first sound wave classification model, and mapping the second echo frequency domain feature representation into a second signal probability value;
mapping the second signal probability value to a second sound wave classification label value as a first signal classification result;
inputting a third echo frequency domain feature representation corresponding to the heartbeat echo frequency domain signal into a preset second sound wave classification model, and mapping the third echo frequency domain feature representation into a third signal probability value;
mapping the third signal probability value to a third sound wave classification label value as a second signal classification result;
and judging whether the vibration signal is the vital sign signal or not based on the first signal classification result and the second signal classification result to obtain the signal judgment result.
6. The in-vivo detection method as set forth in claim 5, wherein the step of extracting the vibration signal in the echo signal at the preset frequency band of the vital sign signal comprises:
performing Fourier transform on the echo signal to obtain echo frequency domain data corresponding to the echo signal;
and filtering the echo frequency domain data to screen the vibration signals in the preset vital sign signal frequency band from the echo frequency domain data.
7. The in-vivo detection method of claim 6, wherein the preset vital sign signal frequency bands comprise a second preset frequency band and a third preset frequency band,
the step of screening the echo frequency domain data for vibration signals in the preset vital sign signal frequency band by filtering the echo frequency domain data comprises:
filtering the echo frequency domain data, and screening signal data in a second preset frequency band associated with the respiratory sign from the echo frequency domain data to obtain a respiratory echo frequency domain signal;
and filtering the echo frequency domain data, and screening signal data in a third preset frequency band associated with the heartbeat sign from the echo frequency domain data to obtain the heartbeat echo frequency domain signal.
8. The in-vivo detection method as claimed in claim 5, wherein after the step of extracting a vibration signal in a preset frequency band of the vital sign signal from the echo signal, determining whether the vibration signal is the vital sign signal, and obtaining a signal determination result, the in-vivo detection method further comprises:
acquiring face video data of the target to be detected, and performing living body detection on the target to be detected based on the face video data to obtain a video living body detection result;
and judging whether the target to be detected is a living body or not based on the video living body detection result and the signal judgment result to obtain a target living body detection result.
9. A living body detection method is applied to a face recognition device, and comprises the following steps:
receiving an echo signal generated by a target to be detected based on a sound wave signal;
extracting a vibration signal in a preset living body sign signal frequency band from the echo signal, judging whether the vibration signal is a living body sign signal or not, and obtaining a signal judgment result, wherein the preset living body sign signal frequency band is a signal frequency band in which a preset signal generated by the vibration of the human face skin along with the living body sign exists, the vibration signal at least comprises one of a respiration echo frequency domain signal and a heartbeat echo frequency domain signal, the respiration echo frequency domain signal is a frequency band signal suspected to be associated with the respiration sign, and the heartbeat echo frequency domain signal is a frequency band signal suspected to be associated with the heartbeat sign;
detecting whether the target to be detected is a living body or not based on the signal discrimination result so as to carry out face recognition;
the target to be detected comprises a living human face, and the step of receiving an echo signal generated by the target to be detected based on the sound wave signal comprises the following steps of:
receiving an echo signal generated by the face skin of the living body face based on the sound wave signal, wherein the face skin of the living body face vibrates along with heartbeat and respiration of a living body corresponding to the living body face;
wherein, the step of judging whether the vibration signal is a vital sign signal or not and obtaining a signal judgment result comprises the following steps:
inputting a second echo frequency domain feature representation corresponding to the respiration echo frequency domain signal into a preset first sound wave classification model, and mapping the second echo frequency domain feature representation into a second signal probability value; mapping the second signal probability value to a second sound wave classification label value as a first signal classification result; judging whether the breath echo frequency domain signal is the vital sign signal or not based on the first signal classification result to obtain a signal judgment result; or
Inputting a third echo frequency domain feature representation corresponding to the heartbeat echo frequency domain signal into a preset second sound wave classification model, and mapping the third echo frequency domain feature representation into a third signal probability value; mapping the third signal probability value to a third sound wave classification label value as a second signal classification result; and judging whether the vibration signal is the vital sign signal or not based on the second signal classification result, and obtaining the signal judgment result.
10. The in-vivo detection method as set forth in claim 9, wherein the step of extracting the vibration signal in the echo signal at the preset vital sign signal frequency band comprises:
performing Fourier transform on the echo signal to obtain echo frequency domain data corresponding to the echo signal;
and filtering the echo frequency domain data, and screening the vibration signals in the preset vital sign signal frequency band from the echo frequency domain data.
11. The in-vivo detection method of claim 10, wherein the predetermined in-vivo sign signal frequency band comprises a second predetermined frequency band and a third predetermined frequency band,
the step of screening the echo frequency domain data for vibration signals in the preset vital sign signal frequency band by filtering the echo frequency domain data comprises:
filtering the echo frequency domain data, and screening signal data in a second preset frequency band associated with the respiratory sign from the echo frequency domain data to obtain a respiratory echo frequency domain signal;
or filtering the echo frequency domain data, and screening signal data in a third preset frequency band associated with the heartbeat sign from the echo frequency domain data to obtain the heartbeat echo frequency domain signal.
12. The in-vivo detection method as set forth in claim 9, wherein after the steps of extracting a vibration signal in a preset frequency band of the vital sign signal from the echo signal, determining whether the vibration signal is the vital sign signal, and obtaining a signal determination result, the in-vivo detection method further comprises:
acquiring face video data of the target to be detected, and performing living body detection on the target to be detected based on the face video data to obtain a video living body detection result;
and judging whether the target to be detected is a living body or not based on the video living body detection result and the signal judgment result to obtain a target living body detection result.
13. A biopsy device, the biopsy device comprising: a memory, a processor, and a program stored on the memory for implementing the liveness detection method,
the memory is used for storing a program for realizing the living body detection method;
the processor is configured to execute a program implementing the living body detecting method to implement the steps of the living body detecting method according to any one of claims 1 to 12.
14. A medium which is a readable storage medium, characterized in that the readable storage medium has stored thereon a program for implementing a living body detection method, the program being executed by a processor to implement the steps of the living body detection method according to any one of claims 1 to 12.
15. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the liveness detection method according to any one of claims 1 to 12 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405171.2A CN113100734B (en) | 2021-04-15 | 2021-04-15 | Living body detection method, apparatus, medium, and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405171.2A CN113100734B (en) | 2021-04-15 | 2021-04-15 | Living body detection method, apparatus, medium, and computer program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113100734A CN113100734A (en) | 2021-07-13 |
| CN113100734B true CN113100734B (en) | 2022-11-25 |
Family
ID=76717156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110405171.2A Active CN113100734B (en) | 2021-04-15 | 2021-04-15 | Living body detection method, apparatus, medium, and computer program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113100734B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230334911A1 (en) * | 2022-04-13 | 2023-10-19 | Nec Corporation | Face liveness detection |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MX2017016718A (en) * | 2015-06-16 | 2018-11-09 | Eyeverify Inc | Systems and methods for spoof detection and liveness analysis. |
| US11707197B2 (en) * | 2017-12-22 | 2023-07-25 | Resmed Sensor Technologies Limited | Apparatus, system, and method for physiological sensing in vehicles |
| CN110688957B (en) * | 2019-09-27 | 2023-06-30 | 腾讯科技（深圳）有限公司 | Living body detection method, device and storage medium applied to face recognition |
| US20210093203A1 (en) * | 2019-09-30 | 2021-04-01 | DawnLight Technologies | Systems and methods of determining heart-rate and respiratory rate from a radar signal using machine learning methods |
| CN111812629A (en) * | 2020-07-21 | 2020-10-23 | 成都阶跃时进科技有限公司 | Living body existence detection method, living body existence detection device, living body existence detection equipment and readable storage medium |
-
2021
- 2021-04-15 CN CN202110405171.2A patent/CN113100734B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113100734A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215802B (en) | Skin detection method and electronic equipment | |
| RU2715521C2 (en) | Systems and methods for detecting fraudulent objects and analysing vitality | |
| CN105160318B (en) | Lie detecting method based on facial expression and system | |
| CN107895369B (en) | Image classification method, device, storage medium and equipment | |
| CN110688957B (en) | Living body detection method, device and storage medium applied to face recognition | |
| WO2019020014A1 (en) | Unlocking control method and related product | |
| CN111368811B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| WO2022033556A1 (en) | Electronic device and speech recognition method therefor, and medium | |
| WO2019015418A1 (en) | Unlocking control method and related product | |
| CN113100734B (en) | Living body detection method, apparatus, medium, and computer program product | |
| WO2008054162A1 (en) | Method, apparatus, and system for diagnosing health status of mobile terminal users | |
| CN208351494U (en) | Face identification system | |
| EP2503545A1 (en) | Arrangement and method relating to audio recognition | |
| WO2021052436A1 (en) | Skin roughness measurement method and electronic device | |
| CN112382306B (en) | Method and device for separating speaker audio | |
| CN113095272A (en) | Living body detection method, living body detection apparatus, living body detection medium, and computer program product | |
| JP5907487B2 (en) | Information transmission system, transmission device, reception device, information transmission method, and program | |
| CN111177086A (en) | File clustering method and device, storage medium and electronic equipment | |
| CN111756705B (en) | Attack testing method, device, equipment and storage medium of in-vivo detection algorithm | |
| CN116884078B (en) | Image pickup apparatus control method, monitoring device, and computer-readable medium | |
| WO2023138660A1 (en) | Audio detection method, and electronic device | |
| CN114882577B (en) | Health state identification method and device, electronic equipment and computer readable medium | |
| CN116048681B (en) | Icon display method, electronic device, and computer-readable storage medium | |
| TW202326709A (en) | Method and system for detecting a target lies | |
| CN116757284A (en) | Model reasoning method, device, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |