A living organism verification method, terminal device and storage medium

Abstract

The present application is applicable to the field of live biometric authentication technology, and provides a live biometric authentication method, terminal device and storage medium. By obtaining corresponding multiple heart rate data based on multiple biometric data of the object to be authenticated, since the counterfeiting method of each type of biometric data is different, it is more difficult for counterfeiters to counterfeit multiple biometric data at the same time; since heart rate data can only be collected from living bodies, by matching and verifying multiple heart rate data, when the multiple heart rate data do not match, it is determined that the object to be authenticated is a counterfeit living body, which can effectively improve the security of live biometric authentication.

Description

Technical Field

[0001] The present application belongs to the field of live biological authentication technology, and in particular relates to a live biological authentication method, terminal device and storage medium. Background Art

[0002] Live biometric authentication technology is widely used in our daily lives, for example, in payment, time clocking, and access control, bringing significant convenience to our daily lives. However, while this technology offers convenience, it also presents inherent security concerns. Impersonators often use facial and fingerprint biometrics to spoof users, leading to privacy breaches, financial losses, and other adverse events. Improving the security of live biometric authentication technology is a critical issue that requires attention and resolution. Summary of the Invention

[0003] In view of this, embodiments of the present application provide a live biometric authentication method, apparatus, terminal device, and storage medium, which can effectively improve the security of live biometric authentication technology.

[0004] A first aspect of the embodiments of the present application provides a living organism verification method, comprising:

[0005] Acquire corresponding multiple heart rate data according to multiple biological data of the subject to be verified;

[0006] If the plurality of heart rate data do not match, it is determined that the object to be authenticated is a counterfeit living body.

[0007] A second aspect of the embodiments of the present application provides a living biological authentication device, comprising:

[0008] A data acquisition unit, configured to acquire corresponding multiple heart rate data based on multiple biological data of the subject to be verified;

[0009] The data verification unit is configured to determine that the object to be verified is a counterfeit living body if the plurality of heart rate data do not match.

[0010] A third aspect of an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the live biological verification method described in the first aspect of the embodiment of the present application are implemented.

[0011] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the live biological verification method described in the first aspect of the embodiments of the present application are implemented.

[0012] The first aspect of the embodiments of the present application provides a live biometric verification method, which obtains corresponding multiple heart rate data based on multiple biometric data of the object to be verified. Since the counterfeiting method of each type of biometric data is different, it is more difficult for an counterfeiter to counterfeit multiple biometric data at the same time; since heart rate data can only be collected from living bodies, by matching and verifying multiple heart rate data, when the multiple heart rate data do not match, it is determined that the object to be verified is a counterfeit living body, which can effectively improve the security of live biometric verification.

[0013] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0015] Figure 1 This is a schematic diagram of the first flow chart of the living organism verification method provided in the embodiment of the present application;

[0016] Figure 2 is a comparison table of biological data and biological data collection devices provided in the embodiments of the present application;

[0017] Figure 3 This is a second flow chart of the living organism verification method provided in the embodiment of the present application;

[0018] Figure 4 is a structural diagram of a mobile terminal provided in an embodiment of the present application;

[0019] Figure 5 This is a first structural diagram of a mobile terminal and a smart bracelet provided in an embodiment of the present application;

[0020] Figure 6 This is a second structural diagram of a mobile terminal and a smart bracelet provided in an embodiment of the present application;

[0021] Figure 7 This is a third flow chart of the living organism verification method provided in the embodiments of the present application;

[0022] Figure 8 This is a fourth flow chart of the living organism verification method provided in the embodiments of the present application;

[0023] Figure 9 This is a schematic diagram of the first structure of the living organism authentication device provided in an embodiment of the present application;

[0024] Figure 10 This is a schematic diagram of the second structure of the living biological authentication device provided in the embodiment of the present application;

[0025] Figure 11 This is a schematic diagram of the third structure of the living organism authentication device provided in the embodiment of the present application;

[0026] Figure 12 This is a schematic diagram of the fourth structure of the living organism authentication device provided in the embodiment of the present application;

[0027] Figure 13 It is a structural diagram of the terminal device provided in an embodiment of the present application. Specific implementation methods

[0028] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0029] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0030] It will also be understood that the term "and / or" used in the present description and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0032] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0033] References to "one embodiment" or "some embodiments" in the present specification mean that one or more embodiments of the present invention include a particular feature, structure, or characteristic described in conjunction with that embodiment. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "comprises," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized. The term "plurality" and variations thereof all mean "at least two."

[0034] The embodiments of the present application provide a live biometric verification method that can be executed by a processor of a terminal device when running a computer program with corresponding functions. By obtaining corresponding multiple heart rate data based on multiple biometric data of the object to be verified, it is more difficult for an imposter to simultaneously collect and counterfeit multiple biometric data and obtain heart rate data from multiple biometric data. By matching and verifying the features of multiple heart rate data, when the multiple heart rate data do not match, it is determined that the object to be verified is a counterfeit live person, which can effectively improve the security of live biometric verification. The live biometric verification method can be applied to various security verification scenarios that require verification of whether the user is alive, such as liveness verification, payment verification, access control verification, and identity verification.

[0035] In applications, the terminal device can be a computing device such as a mobile terminal, desktop computer, access control system, self-service terminal, server, etc. with live biometric verification capabilities. The mobile terminal can be a mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc. Specifically, in the payment verification scenario, the terminal device can be a mobile terminal or a server; in the access control verification scenario, the terminal device can be a desktop computer, access control system, or server; in the identity verification scenario, the terminal device can be a mobile terminal, self-service terminal, or server. The embodiments of this application do not impose any restrictions on the specific type of terminal device.

[0036] like Figure 1 As shown, the living organism verification method provided in the embodiment of the present application includes the following steps S101 and S102:

[0037] Step S101 , obtaining corresponding multiple heart rate data according to multiple biological data of the object to be verified, and then proceeding to step S102 .

[0038] In applications, the object to be authenticated can be a target living entity previously authenticated by a terminal device, or at least one counterfeit living entity. The target living entity is not limited to humans and can also be other animals. The counterfeit living entity can be a non-living entity or a living entity other than the target living entity. When the object to be authenticated is a target living entity, the biometric data is the living biometric data of the object to be authenticated; when the object to be authenticated is at least one counterfeit living entity, the biometric data is the living biometric data of the object to be authenticated or non-living biometric data carried by the object to be authenticated.

[0039] In applications, biometric data may include, but is not limited to, heart rate data or biometric image data that can be converted to heart rate data through data processing. Biometric image data includes images of blood vessels on the skin surface of the subject to be authenticated. Biometric image data may include, but is not limited to, facial image data, iris image data, fingerprint image data, and vein image data. Biometric image data may include multiple discontinuous frames or multiple continuous frames of images. Multiple continuous frames of images constitute video data.

[0040] In the application, each type of biometric data is collected through a biometric data collection device. For example, facial image data is collected through a facial camera module, iris image data is collected through an iris camera module, fingerprint image data is collected through a fingerprint image sensor, vein image data is collected through a vein image sensor, and heart rate data is collected through a photoplethysmograph (PPG) sensor. The light-emitting devices (e.g., light-emitting diodes (LEDs)) in the facial camera module, iris camera module, fingerprint image sensor, vein image sensor, and PPG sensor are capable of emitting light signals (e.g., infrared light signals or green light signals) that can penetrate the surface skin and reach veins or arteries to the object to be verified, receive light signals reflected by the surface skin and veins or arteries of the object to be verified, convert the received light signals into electrical signals, and process them into corresponding biometric data.

[0041] In application, the facial camera module can be implemented by any ordinary camera with a photo function, or by a camera with a facial recognition function. The iris camera module needs to be implemented by a camera with an iris recognition function, for example, a camera composed of a complementary metal oxide semiconductor (CMOS) image sensor, an infrared bandpass filter, and an optical lens. The iris camera module can also be implemented by a camera that has both iris recognition and photo functions, for example, a camera composed of a complementary metal oxide semiconductor (CMOS) image sensor, a filter that can pass visible light signals and infrared light signals, and an optical lens. A camera that has both iris recognition and photo functions can be used to replace a camera that only has a facial recognition function and a camera that only has an iris recognition function.

[0042] like Figure 2 As shown, a comparison table of biological data and biological data collection devices is exemplarily shown.

[0043] In application, the facial camera module can be set in mobile terminals, smart bracelets, desktop computers, access control systems, self-service terminals and other computing devices; the iris camera module can be set in mobile terminals, smart bracelets, smart glasses, desktop computers, access control systems, self-service terminals and other computing devices; the fingerprint image sensor can be set in mobile terminals, smart bracelets, desktop computers, access control systems, self-service terminals and other computing devices; the vein image sensor can be set in smart rings, smart neck rings, smart anklets, access control systems, self-service terminals and other computing devices; the PPG sensor can be set in mobile terminals, smart bracelets, smart rings, smart neck rings, smart anklets, desktop computers, access control systems, self-service terminals and other computing devices.

[0044] In applications, the biometric data collection device can be installed on a terminal device or other computing device that communicates with the terminal device, depending on actual needs. For example, if the terminal device is a server, the biometric data collection device can be installed on the other computing device. The operations of collecting biometric data, obtaining heart rate data, and verifying heart rate data can be performed using the same or different devices. By using different devices, the cost of counterfeiting a target living being can be increased because counterfeiters need to use multiple devices to counterfeit the target living being. This can reduce the cost of counterfeiting living beings by increasing the cost.

[0045] In practice, existing terminal devices typically collect and verify the same biometric data (for example, if facial image data is collected, it is directly verified). Based on this characteristic, when counterfeiters impersonate a target living person, they typically counterfeit the biometric data collected by the terminal device. Since counterfeiters often find it difficult to imagine that the biometric data collected and verified by the terminal device is different, using other types of biometric data to obtain heart rate data can mislead them. In addition, because heart rate data is obtained based on the principle that the blood flow in arteries or veins causes the blood's absorption rate of light signals to continuously change, heart rate data can only be collected from living people, making it impossible for counterfeiters to use non-living biometric data to counterfeit living biometric data. Furthermore, because the counterfeiting method for each type of biometric data is different, it is difficult for counterfeiters to counterfeit multiple types of biometric data simultaneously.

[0046] Step S102: If the plurality of heart rate data do not match, it is determined that the object to be authenticated is a counterfeit living body.

[0047] In applications, multiple heart rate data sets can be compared to determine whether they match by comparing their numerical values, waveforms, and other features. If the numerical values, waveforms, and other features of the multiple heart rate data sets are the same or similar, then the multiple heart rate data sets can be determined to match and originate from the same living individual. If the numerical values, waveforms, and other features of the multiple heart rate data sets are different or dissimilar, then the multiple heart rate data sets can be determined to be mismatched and not originate from the same living individual or from a non-living individual. In this case, the subject to be authenticated can be determined to be a counterfeit living individual. Determining whether the subject to be authenticated is a counterfeit living individual based on multiple heart rate data sets can effectively improve the security of live biometric authentication by increasing the difficulty for counterfeiters to simultaneously counterfeit multiple types of biometric data.

[0048] In one embodiment, step S101 includes:

[0049] The corresponding multiple heart rate data are indirectly obtained based on the multiple biological image data of the object to be verified.

[0050] In applications, all of the various biometric data can be biometric image data. Since biometric image data includes vascular images of the subject's skin surface, heart rate data is obtained based on the principle that blood flow in arteries or veins causes the blood's absorption rate of light signals to continuously change. Since blood flow in arteries or veins causes changes in the captured vascular images, heart rate data can be obtained based on biometric image data.

[0051] In applications, the multiple biometric image data may include multiple types of facial image data, iris image data, fingerprint image data, vein image data, and the like. Depending on the type of biometric data, the type and number of devices used to collect, obtain and verify biometric data are also different. For example, when multiple biometric image data include at least two of facial image data, iris image data, fingerprint image data, vein image data, etc., the collection, acquisition and verification of biometric data can be achieved through a mobile terminal; when multiple biometric image data include facial image data and iris image data, facial image data and iris image data can be collected respectively through a mobile terminal and smart glasses, and heart rate data can be obtained and verified through the mobile terminal; when multiple biometric image data include iris image data and fingerprint image data, iris image data and fingerprint image data can be collected respectively through smart glasses and a smart ring, and heart rate data can be obtained and verified through the mobile terminal; when multiple biometric image data include fingerprint image data and vein image data, fingerprint image data and vein image data can be collected through a smart ring, and heart rate data can be obtained and verified through the mobile terminal; when multiple biometric image data include facial image data and vein image data, facial image data and vein image data can be collected respectively through a mobile terminal and a smart bracelet, and heart rate data can be obtained and verified through the mobile terminal.

[0052] like Figure 3 As shown, in one embodiment, step S101 includes the following steps S301 and S302:

[0053] Step S301: directly obtain the heart rate data of the subject to be verified;

[0054] Step S302: indirectly obtain corresponding at least one heart rate data based on at least one biological image data of the object to be verified.

[0055] In an application, the plurality of biometric data may include heart rate data and at least one biometric image data. The at least one biometric image data may include at least one of facial image data, iris image data, fingerprint image data, vein image data, and the like. Depending on the type of biometric data, the type and quantity of devices used to collect, obtain and verify biometric data are also different. For example, when multiple biometric data include heart rate data, facial image data and iris image data, heart rate data, facial image data and iris image data can be collected respectively through a smart bracelet, a mobile terminal and smart glasses, and the heart rate data can be obtained and verified through the mobile terminal; when multiple biometric data include heart rate data, iris image data and fingerprint image data, heart rate data, iris image data and fingerprint image data can be collected respectively through a smart bracelet, smart glasses and a smart ring, and the heart rate data can be obtained and verified through a mobile terminal; when multiple image data include heart rate data, fingerprint image data and vein image data, heart rate data, fingerprint image data and vein image data can be collected through a smart ring, and the heart rate data can be obtained and verified through a mobile terminal; when multiple biometric data include heart rate data, facial image data and vein image data, heart rate data and vein image data can be collected through a smart bracelet, facial image data can be collected through a mobile terminal, and heart rate data can be obtained and verified through a mobile terminal.

[0056] like Figure 4 , which exemplarily shows a structural diagram of a mobile terminal; wherein, the mobile terminal 1 includes a camera 11, a fingerprint image sensor 12, a vein image sensor 13 and a PPG sensor 14.

[0057] like Figure 5 As shown, a first structural diagram of a mobile terminal and a smart bracelet is exemplarily shown; wherein, the mobile terminal 1 includes a camera 11, and the smart bracelet 2 includes a PPG sensor 21.

[0058] like Figure 6 As shown, a schematic diagram of a second connection structure between a mobile terminal and a smart bracelet is exemplified; wherein, the mobile terminal 1 includes a camera 11 and a fingerprint image sensor 12, and the smart bracelet 2 includes a PPG sensor 21 and a vein image sensor 22.

[0059] It should be understood that Figure 4-Figure 6 It is only an example of the device structure and does not constitute a limitation of the device structure. It can include more or fewer components than shown in the figure, or combine certain components, or different components, and can be reasonably configured according to actual data acquisition requirements.

[0060] In one embodiment, after step S101, the method further includes:

[0061] If the multiple heart rate data match, it is determined that the object to be verified is alive.

[0062] In the application, when multiple heart rate data match, it can be determined that the object to be verified is alive. In order to improve accuracy, other methods can be further combined for auxiliary verification, for example, through infrared detection, instructing the object to be verified to perform specific body movements and other living body detection and verification methods for auxiliary verification.

[0063] like Figure 7 As shown, in one embodiment, the method for indirectly obtaining corresponding heart rate data based on biological image data includes the following steps S701 to S704:

[0064] Step S701: Perform region detection on the biological image data to obtain image data of multiple regions, and then proceed to step S702 and step S703.

[0065] In the application, at least one region of interest (ROI) data (i.e., image region data) is extracted frame by frame from the biological image data. The ROI is an area in the biological image data where optical signals reflecting blood vessels with high contrast can be obtained. For example, for facial images, the at least one ROI may include, but is not limited to, the forehead and cheek regions. Extracting the forehead and cheek regions as ROIs reduces computational complexity and improves accuracy. Convolutional Neural Networks (CNNs) can be used to extract the at least one ROI data from the biological image data frame by frame.

[0066] Step S702: perform regional mean and low-pass filtering on the image data of the multiple regions in sequence to obtain first average heart rate data, and then proceed to step S704.

[0067] In the application, first, the image data of multiple regions acquired are regionally averaged frame by frame in a time series. The regional average is the average of the three RGB color channels of the image data of each region to obtain three sets of feature values of the image data of each region. For example, for facial images, the region of interest data extracted from each frame of the biological image data includes data of the forehead and the two sides of the cheek area. When there are three regions of data in total, 3×3 sets of feature values can be obtained after regional averaging of the three regions of interest data. Then, 3×n1 (n1 is the number of regions of interest data extracted from each frame of the biological image data) sets of feature values of different frames are arranged in time to obtain 3×n1 sets of time series signals. The 3×n1 sets of time series signals are low-pass filtered to obtain 3×n1 waveform curves of heart rate data. Then, the n1 waveform curves of heart rate data with the largest variance among the 3×n1 waveform curves of heart rate data are screened out as the waveform curve of the first average heart rate data. The frequency of the low-pass filter can be set according to actual needs, for example, any frequency between 5Hz and 10Hz.

[0068] Step S703: predict the image data of the multiple regions using a preset neural network model to obtain second average heart rate data, and then proceed to step S704.

[0069] In the application, a deep learning algorithm is used to pre-train a neural network model capable of extracting heart rate waveform curves from image data of multiple regions. Image data for each region is input into the neural network model, which then predicts n1 heart rate waveform curves, each of which serves as the second average heart rate waveform curve. The neural network model utilizes a neural network architecture that includes, but is not limited to, convolutional neural networks and recurrent neural networks (RNNs), comprising convolutional layers, pooling layers, and downsampling layers.

[0070] Step S704: averaging the first average heart rate data and the second average heart rate data to obtain heart rate data corresponding to the biological image data.

[0071] In the application, the n1 heart rate data waveform curves obtained by the two methods in steps S702 and S703 are averaged to obtain the average waveform curve of the heart rate data, which is used as the waveform curve of the target heart rate data. The average waveform curve can also be subjected to a Fast Fourier Transform (FFT) to obtain a frequency domain waveform, and the highest frequency domain peak of the frequency domain waveform is taken as the value of the target heart rate data. By combining the two methods in steps S702 and S703, the robustness of the ultimately obtained heart rate data can be effectively improved.

[0072] like Figure 8 As shown, in one embodiment, the living organism verification method provided by the embodiment of the present application further includes the following steps S801 and S802:

[0073] Step S801: Acquire corresponding at least one biometric image feature data according to at least one biometric image data of the object to be verified, and proceed to step S802;

[0074] Step S802: If the plurality of heart rate data match and the at least one biological image feature data matches the corresponding preset biological image feature data, it is determined that the object to be verified is a target living body.

[0075] In an application, the biometric image data in step S801 may be facial image data, iris image data, fingerprint image data, vein image data, etc., and correspondingly, the biometric image feature data may be facial feature data, iris feature data, fingerprint feature data, vein feature data, etc. The preset biometric image feature data is pre-acquired and stored biometric image feature data of a target living being.

[0076] In the application, step S801 is executed before or after step S102, and step S802 is executed after step S102. Figure 8 exemplarily shown in FIG. , step S801 is performed after step S102. The biometric image data in step S801 may be the biometric image data in the aforementioned embodiment, so that the biometric image data obtained in a single data acquisition operation can be reused without the need for additional data acquisition, thereby improving overall data acquisition efficiency. For example, when the biometric image data in the aforementioned embodiment and step S801 both include facial image data, the facial image data is used in the aforementioned embodiment to obtain heart rate data and in step S801 to obtain facial feature data; when the biometric image data in the aforementioned embodiment and step S801 both include iris image data, the iris image data is used in the aforementioned embodiment to obtain heart rate data and in step S801 to obtain iris feature data; when the biometric image data in the aforementioned embodiment and step S801 both include fingerprint image data, the fingerprint image data is used in the aforementioned embodiment to obtain heart rate data and in step S801 to obtain fingerprint feature data; when the biometric image data in the aforementioned embodiment and step S801 both include vein image data, the vein image data is used in the aforementioned embodiment to obtain heart rate data and in step S801 to obtain vein feature data. The biological image data in step S801 may also be additionally collected data of a different type from the biological image data in the aforementioned embodiment. By additionally acquiring a new type of biological image data, it is more difficult for an imposter to impersonate the target living body, thereby improving the accuracy of live biological verification.

[0077] In applications, since the multiple heart rate data acquired in step S101 is primarily used to determine whether the subject to be authenticated is a living being, and cannot determine the subject's identity, that is, whether the subject to be authenticated is the target living being, further acquiring at least one biometric image feature data can further determine whether the subject to be authenticated is the target living being, based on the determination that the subject to be authenticated is a living being. Since an imposter can only counterfeit the identity of the target living being by counterfeiting non-living biological data, if the subject to be authenticated is determined to be a living being, it can be determined that the biometric image data in step S801 is authentic living biological image data, thereby confirming that the identity of the target living being has not been counterfeited. Furthermore, with the dual assurance that the subject to be authenticated is a living being and that their identity is authentic, the subject to be authenticated can be determined to be the target living being.

[0078] In one embodiment, after step S801, the following steps are included:

[0079] If any of the biological image feature data does not match the corresponding preset biological image feature data, it is determined that the object to be verified is not a target living body.

[0080] In the application, if any biological image feature data does not match the corresponding preset feature data, it can be considered that the identity authentication of the object to be verified has failed and the identity of the target living body has been counterfeited. At this time, regardless of whether the object to be verified is a living body, it cannot be the target living body.

[0081] In the application, corresponding multiple bio-image feature data can be obtained based on the multiple bio-image data of the object to be verified, so that the object to be verified is determined to be the target living body only when the multiple bio-image feature data match the corresponding preset bio-image feature data. This can improve the accuracy of the verification results when verifying whether the object to be verified is the target living body.

[0082] In one embodiment, before step S102, the following steps are included:

[0083] Matching the plurality of heart rate data using a plurality of matching methods;

[0084] Step S102 includes:

[0085] If the plurality of heart rate data do not match under any matching method, it is determined that the object to be authenticated is a counterfeit living body.

[0086] In practice, due to the varying accuracy of different data matching methods, a single method may occasionally produce significant errors, leading to inaccurate verification results. Therefore, using multiple matching methods to perform multiple matching verifications on the features of multiple heart rate data sets can effectively improve the accuracy and robustness of the verification results. To improve matching efficiency, a single matching method can also be used to match the values of multiple heart rate data sets. When the features of multiple heart rate data sets match using this matching method, the subject to be verified is determined to be alive.

[0087] In one embodiment, the matching of the plurality of heart rate data using a plurality of matching methods includes:

[0088] Matching the values of the plurality of heart rate data using at least one value matching method, and matching the waveform curves of the plurality of heart rate data using at least one signal matching method;

[0089] Alternatively, matching the values of the plurality of heart rate data by using a plurality of value matching methods;

[0090] Alternatively, the waveform curves of the plurality of heart rate data are matched using a variety of signal matching methods.

[0091] In the application, the characteristics of each heart rate data can be obtained separately. The characteristics of the heart rate data include at least one of a numerical value and a waveform curve. Then, the characteristics of multiple heart rate data are matched using one or more corresponding matching methods. Only when the characteristics of multiple heart rate data are matched under one or more corresponding matching methods, it is determined that the object to be verified is a living body.

[0092] In one embodiment, the numerical matching method is an error comparison method or a threshold comparison method, and the signal matching method is a machine learning method or a curve similarity comparison method.

[0093] In the application, the error comparison method calculates the error between the values of multiple heart rate data and determines whether all errors are within a preset error range. If so, the features of the multiple heart rate data are determined to match; otherwise, the features of the multiple heart rate data are determined to mismatch. The threshold comparison method determines whether the values of multiple heart rate data are within a preset threshold range. If so, the features of the multiple heart rate data are determined to match; otherwise, the features of the multiple heart rate data are determined to mismatch. The machine learning method inputs the waveform curves of the multiple heart rate data into a matching model pre-trained using a machine learning method, and the matching model directly outputs the feature matching results of the multiple heart rate data. The curve similarity comparison method compares each waveform curve of the multiple heart rate data with a pre-generated standard waveform curve of the same target living person's heart rate data to obtain a similarity. If the similarity between the waveform curves of the multiple heart rate data and the pre-generated standard waveform curve of the same target living person's heart rate data is within the preset similarity range, the features of the multiple heart rate data are determined to match; otherwise, the features of the multiple heart rate data are determined to mismatch.

[0094] The improved live biometric verification method of the embodiment of the present application can accurately verify whether the object to be verified is a counterfeit live body. When it is determined that the object to be verified is a real live body, the identity of the object to be verified can be further determined to determine whether the object to be verified is a target live body with a specific identity. It can effectively reduce the risk of adverse events such as privacy leakage and property loss caused by counterfeiters counterfeiting the user's live biometric characteristics, improve the accuracy and security of live biometric verification, and can be widely used in various security verification scenarios such as liveness verification, payment verification, access control verification, and identity verification that require verification of whether the user is alive. It also has the advantages of low cost, high feasibility, and easy implementation.

[0095] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0096] The present application also provides a live biometric verification device for executing the steps in the live biometric verification method embodiment. The live biometric verification device can be a virtual appliance in a terminal device, run by a processor of the terminal device, or can be the terminal device itself.

[0097] like Figure 9 As shown, the living biological authentication device provided in the embodiment of the present application includes:

[0098] The data acquisition unit 101 is used to acquire corresponding multiple heart rate data according to multiple biological data of the subject to be verified;

[0099] The data verification unit 102 is configured to determine that the object to be verified is a counterfeit living body if the plurality of heart rate data do not match.

[0100] In one embodiment, the data verification unit is further configured to determine that the object to be verified is a living body if multiple heart rate data match.

[0101] like Figure 10 As shown, in one embodiment, the data acquisition unit 101 includes:

[0102] A region detection unit 201 is configured to perform region detection on the biological image data to obtain image data of multiple regions;

[0103] a regional mean and low-pass filtering unit 202, configured to sequentially perform regional mean and low-pass filtering on the image data of the plurality of regions to obtain first average heart rate data;

[0104] A neural network prediction unit 203 is configured to predict the image data of the plurality of regions using a preset neural network model to obtain second average heart rate data;

[0105] The feature data calculation unit 204 is configured to average the first average heart rate data and the second average heart rate data to obtain heart rate data corresponding to the biological image data.

[0106] In one embodiment, the data acquisition unit is further configured to acquire corresponding at least one biometric image feature data based on at least one biometric image data of the object to be verified;

[0107] The data verification unit is further configured to determine that the object to be verified is a target living body if the multiple heart rate data match and the at least one biological image feature data matches the corresponding preset biological image feature data.

[0108] In one embodiment, the feature verification unit is further configured to determine that the object to be verified is not a target living body if any of the biological image feature data does not match the corresponding preset biological image feature data.

[0109] like Figure 11 As shown, in one embodiment, the data verification unit 102 includes:

[0110] A matching unit 301 is configured to match the plurality of heart rate data using a plurality of matching methods;

[0111] The verification unit 302 is configured to determine that the object to be verified is a counterfeit living body if the plurality of heart rate data do not match under any matching method.

[0112] like Figure 12 As shown, in one embodiment, the matching unit 301 includes:

[0113] A value matching unit 401 is configured to match the values of the plurality of heart rate data using at least one value matching method, or to match the values of the plurality of heart rate data using multiple value matching methods;

[0114] The signal matching unit 402 is configured to match the waveform curves of the plurality of heart rate data using at least one signal matching method, or to match the waveform curves of the plurality of heart rate data using multiple signal matching methods.

[0115] In application, each unit in the living biological authentication device may be a software program unit, or may be implemented by different logic circuits integrated in a processor, or may be implemented by two or more distributed processors.

[0116] like Figure 13 As shown, the embodiment of the present application further provides a terminal device 200, including: at least one processor 201 ( Figure 13 Only one processor is shown in the figure), a memory 202 and a computer program 203 stored in the memory 202 and capable of running on at least one processor 201. When the processor 201 executes the computer program 203, the steps in the above-mentioned embodiments of the living biological authentication method are implemented.

[0117] In applications, the terminal device may include, but is not limited to, a memory and a processor. Those skilled in the art will understand that Figure 13 This is only an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, Figure 2 The various biological data collection devices shown, etc. Input and output devices may include cameras, audio acquisition / playback devices, display screens, buttons, etc. Network access devices may include communication modules for communicating with other devices.

[0118] In applications, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0119] In applications, in some embodiments, the memory can be an internal storage unit of a terminal device, such as a hard disk or memory of the terminal device. In other embodiments, the memory can also be an external storage device of the terminal device, such as a plug-in hard disk equipped with the terminal device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory can also include both the internal storage unit of the terminal device and an external storage device. The memory is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. The memory can also be used to temporarily store data that has been output or is about to be output.

[0120] In application, the display screen can be a thin film transistor liquid crystal display (TFT-LCD), a liquid crystal display (LCD), an organic light-emitting diode (OLED), a quantum dot light-emitting diode (QLED) display screen, a seven-segment or eight-segment digital tube, etc.

[0121] In application, the communication module can be set as any device that can directly or indirectly communicate with other devices through wired or wireless communication according to actual needs. For example, the communication module can provide communication solutions applied to network devices, including communication interfaces (for example, Universal Serial Bus (USB), wired local area networks (LAN), wireless local area networks (WLAN) (for example, Wi-Fi networks), Bluetooth, Zigbee, mobile communication networks, global navigation satellite systems (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. The communication module may include an antenna, which may have only one element or an antenna array including multiple elements. The communication module receives electromagnetic waves through the antenna, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor. The communication module can also receive signals to be sent from the processor, frequency modulate and amplify them, and convert them into electromagnetic waves for radiation through the antenna.

[0122] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The functional units in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0124] An embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the live biological authentication method of any of the above embodiments is implemented.

[0125] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the live biometric authentication method of any of the above embodiments.

[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include at least: any entity or device that can carry the computer program code to the terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0127] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0128] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0129] In the embodiments provided in this application, it should be understood that the disclosed devices, terminal devices and methods can be implemented by other methods. For example, the device and terminal device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as two or more units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0130] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A living organism verification method, characterized in that: include: Acquire corresponding multiple heart rate data according to multiple biological data of the subject to be verified; If the plurality of heart rate data do not match, determining that the object to be authenticated is a counterfeit living body; The step of obtaining a plurality of heart rate data based on a plurality of biological data of the subject to be verified includes: Indirectly obtaining corresponding multiple heart rate data based on multiple biometric image data of the subject to be verified; wherein the light-emitting component of the sensor that collects the multiple biometric image data is capable of emitting light signals that can penetrate the surface skin and reach the veins or arteries of the subject to be verified, receiving light signals reflected by the surface skin and veins or arteries of the subject to be verified, converting the received light signals into electrical signals, and processing them into corresponding biometric image data; The method of indirectly obtaining the corresponding heart rate data based on the biological image data is: Performing region detection on the biological image data to obtain image data of multiple regions; Performing regional averaging and low-pass filtering on the image data of the multiple regions in sequence to obtain first average heart rate data, including: performing regional averaging on the acquired image data of the multiple regions frame by frame in time series, wherein the regional averaging is to average the three RGB color channels of the image data of each region to obtain three groups of feature values of the image data of each region; when the biological image data is facial image data, the region of interest data extracted from each frame of the biological image data includes data of the forehead and both sides of the cheeks, and after performing regional averaging on the three regions of interest data, 3×3 groups of feature values can be obtained; then, 3×n1 groups of feature values of different frames are arranged in time to obtain 3×n1 groups of time series signals, and the 3×n1 groups of time series signals are low-pass filtered to obtain 3×n1 waveform curves of heart rate data, and then n1 waveform curves of heart rate data with the largest variance among the 3×n1 waveform curves of heart rate data are screened out as the waveform curves of the first average heart rate data; Predicting the image data of the plurality of regions using a preset neural network model to obtain second average heart rate data includes: pre-training a neural network model capable of extracting waveform curves of heart rate data from the image data of the plurality of regions; inputting the image data of each region into the neural network model, and causing the neural network model to predict n1 waveform curves of heart rate data as the waveform curves of the second average heart rate data; The first average heart rate data and the second average heart rate data are averaged to obtain heart rate data corresponding to the biological image data.

2. The living organism verification method according to claim 1, wherein: The step of obtaining a plurality of heart rate data based on a plurality of biological data of the subject to be verified further includes: The heart rate data of the object to be verified is directly acquired, and at least one corresponding heart rate data is indirectly acquired according to at least one biological image data of the object to be verified.

3. The living organism authentication method according to claim 1 or 2, wherein: The biological image data is facial image data, iris image data, fingerprint image data or vein image data.

4. The living organism authentication method according to claim 2, wherein: The directly obtaining the heart rate data of the subject to be verified includes: The heart rate data of the subject to be verified is directly obtained through a photoelectric recording sensor.

5. The living organism authentication method according to claim 1 or 2, wherein: Also includes: Acquiring corresponding at least one biometric image feature data according to at least one biometric image data of the object to be verified; If the plurality of heart rate data match and the at least one biological image feature data matches the corresponding preset biological image feature data, it is determined that the object to be authenticated is a target living body.

6. The living organism authentication method according to any one of claims 1 to 2, characterized in that: If the plurality of heart rate data do not match, before determining that the object to be authenticated is a counterfeit living body, the method includes: The plurality of heart rate data are matched using a plurality of matching methods.

7. The living organism authentication method according to claim 6, wherein: The matching of the plurality of heart rate data by using a plurality of matching methods includes: Matching the values of the plurality of heart rate data using at least one value matching method, and matching the waveform curves of the plurality of heart rate data using at least one signal matching method; Alternatively, matching the values of the plurality of heart rate data by using a plurality of value matching methods; Alternatively, the waveform curves of the plurality of heart rate data are matched using a variety of signal matching methods.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the living organism authentication method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the living organism authentication method according to any one of claims 1 to 7 are implemented.

Images