Liveness detection method, device, equipment and system

Abstract

This specification provides a method, device, equipment and system for liveness detection, which collects biometric images of the target detection object, predicts the brain wave signals of the target detection object based on the collected biometric images, calculates the emotional characteristics of the target detection object based on the brain wave signals, and identifies whether the target detection object is a live object based on the brain wave signals and emotional characteristics. This method utilizes the essential difference between real users and attacks, namely their brain wave signals and emotional states, and can essentially improve the security capabilities of the liveness anti-attack method. Even attacks that have never been seen before will be intercepted because of abnormal brain wave and emotional state signals, which improves the accuracy of liveness detection and thus improves the security of biometrics.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and more particularly to a method, device, equipment and system for detecting a living body. Background Art

[0002] With the development of computer Internet technology, face recognition technology is being used more and more, such as face payment, face login, face attendance, face identity authentication for travel, etc. The application of other biometric technologies is also increasing. Biometric technology requires the collection of biological images, and then uses the biological images to achieve the purpose of identity authentication.

[0003] As facial recognition technology becomes more widely used, its potential social impact will become more serious. One of the main risks threatening facial recognition security is liveness attacks, which bypass facial recognition through photos, screens, masks and other media to steal victims' accounts.

[0004] Therefore, how to propose a liveness detection solution that can prevent liveness attacks during biometrics and improve the security of biometrics is a technical problem that needs to be urgently solved in this field. Summary of the invention

[0005] The purpose of the embodiments of this specification is to provide a liveness detection method, device, equipment and system to improve the accuracy of liveness detection and thereby improve the security of biometrics.

[0006] On the one hand, an embodiment of this specification provides a living body detection method, the method comprising:

[0007] Collecting biometric images of the target detection object during biometric identification;

[0008] Predicting a brain wave signal of the target detection object based on the biometric image;

[0009] Determining the emotional characteristics of the target detection object according to the brain wave signal;

[0010] According to the emotion feature, it is determined whether the target detection object is a living object.

[0011] On the other hand, this specification provides a living body detection device, including:

[0012] An image acquisition module, used to acquire a biometric image of a target detection object during biometric identification;

[0013] A brain wave information prediction module, used to predict the brain wave signal of the target detection object based on the biometric image;

[0014] An emotion feature recognition module, used to determine the emotion feature of the target detection object according to the brain wave signal;

[0015] A liveness detection module is used to determine whether the target detection object is a live object based on the emotion characteristics.

[0016] In another aspect, an embodiment of the present specification provides a living body detection device, including at least one processor and a memory for storing processor executable instructions, wherein the processor implements the above-mentioned living body detection method when executing the instructions.

[0017] On the other hand, an embodiment of the present specification provides a liveness detection system, comprising: an image acquisition device and an image processing device, wherein the image acquisition device is used to acquire a biometric image of a target detection object for biometric identification, and the image processing device includes at least one processor and a memory for storing processor executable instructions, and the processor implements the above-mentioned liveness detection method when executing the instructions.

[0018] The liveness detection method, device, equipment and system provided in this specification collects the biometric image of the target detection object, predicts the brain wave signal of the target detection object based on the collected biometric image, calculates the emotional characteristics of the target detection object based on the brain wave signal, and identifies whether the target detection object is a live object based on the brain wave signal and emotional characteristics. This method utilizes the essential difference between real users and attacks, namely their brain wave signals and emotional states, and can essentially improve the security capabilities of the liveness anti-attack method. Even attacks that have never been seen before will be intercepted because of abnormal brain wave and emotional state signals, thereby improving the accuracy of liveness detection and thus improving the security of biometric identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a flowchart of an embodiment of a liveness detection method provided in an embodiment of this specification;

[0021] Figure 2 This is a schematic diagram of the principle flow of liveness detection in a scenario example of this manual;

[0022] Figure 3 It is a schematic diagram of the module structure of an embodiment of a living body detection device provided in this specification;

[0023] Figure 4 It is a hardware structure block diagram of a liveness detection server in one embodiment of this specification. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0025] With the increasing popularity of biometric technology, the security of biometric technology has been paid more and more attention. Generally, the main threat to biometric security is liveness attack, such as: using photos, screens, masks, etc. to disguise in the face recognition process, stealing information of face recognition users, etc. Generally, biometric systems such as face recognition systems will integrate liveness anti-attack algorithms for liveness detection. Generally, liveness anti-attack algorithms may only use simple liveness detection models to classify face recognition users. This method generally has weak security capabilities and weak interception capabilities for attack types that do not appear in the training data. Alternatively, some algorithms require users to cooperate in a series of actions to achieve liveness detection, such as blinking, nodding, etc., and the difficulty of attack is increased by the completion of the action. However, this type of method is mostly used in more private and secure scenarios (such as banks, etc.), and has a poor experience in commercial scenarios with a large number of people (such as vending machines), and is difficult to be applied.

[0026] In some embodiments of this specification, a liveness detection method can be provided, which is mainly used for liveness detection in the process of face recognition to avoid liveness attacks and theft of user information. In the embodiments of this specification, the biometric image of the target detection object is collected, the brain wave signal of the target detection object is predicted based on the collected biometric image, the emotional characteristics of the target detection object are calculated based on the brain wave signal, and the target detection object is identified as a live object based on the brain wave signal and the emotional characteristics. This method utilizes the essential difference between real users and attacks (static photos, etc.) (i.e., their brain wave signals, emotions, and states), which can essentially improve the security capabilities of the liveness anti-attack method. Even attacks that have never been seen will be intercepted because of abnormal brain wave and emotional state signals, thereby improving the security of biometric recognition.

[0027] In addition, it should be noted that the acquisition, storage, use, and processing of data involved in the embodiments of this specification, such as face recognition and liveness detection, all comply with the relevant provisions of national laws and regulations.

[0028] Figure 1 It is a flow chart of an embodiment of a liveness detection method provided in an embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure described is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, a parallel processor or multi-threaded processing environment, or even a distributed processing, server cluster implementation environment).

[0029] A specific implementation example is Figure 1 As shown, in one embodiment of the liveness detection method provided in this specification, the method can be applied to a server, a computer, a tablet computer, a server, a smart phone, a smart wearable device, a vehicle-mounted device, a smart home device, and other devices capable of image processing, and the method may include the following steps:

[0030] Step 102: Collect a biometric image of the target detection object during biometric identification.

[0031] In the specific implementation process, when performing biometric identification such as face recognition, the camera in the biometric identification device can be used to collect the biometric image of the target detection object being identified. The target detection object can be understood as the object of biometric identification. The embodiments of this specification are mainly used to detect whether the target detection object is a living object, to ensure that the user performing biometric identification is a real person, and then to ensure that the user performing biometric identification is the user himself. The biometric image can be determined according to the type of biometric identification, and can refer to image information with a face, or pupil information or fingerprint information, etc. In the embodiments of this specification, face images can be mainly used. The biometric image can be a picture or a video, which can be determined according to actual needs, and the embodiments of this specification do not make specific limitations.

[0032] In some embodiments of this specification, the biometric feature image of the target detection object during biometric identification includes:

[0033] The image information of the target detection object within a specified time after the start of biometric identification is collected, and a specified number of images are selected from the image information as the biometric feature images of the target detection object.

[0034] In the specific implementation process, when collecting the biometric image of the target detection object, the image information of the target detection object within a specified time after the start of biometric identification can be collected, such as: when the user collects and performs face recognition through the IoT device, the face data of about 5S from the start of the user's face recognition can be collected, which can be 5S of video data, or 5S of continuously shot photo data. A specified number of images such as 10 images are selected as the biometric image of the target detection object. The biometric image in the embodiment of this specification can collect high-definition biometric images, such as: a face image with a face area resolution greater than 400*400. The face area of ​​a general face recognition algorithm is generally 100*100, and the amount of information is relatively small. By collecting high-definition biometric images, the accuracy of liveness detection and biometric identification can be improved.

[0035] By collecting image information for a certain period of time and then selecting a specified number of images as biometric images, we can ensure the uniformity and comprehensiveness of biological sampling, provide a more accurate data basis for liveness detection and biometric identification, and improve the accuracy of liveness detection and biometric identification.

[0036] Step 104: predicting the brain wave signal of the target detection object based on the biometric image.

[0037] In the specific implementation process, after the biometric image of the target detection object is collected, the brain wave signal of the biometric image can be predicted to predict the brain wave signal of the target detection object for biometric identification. Brain waves are also called "brain waves". Brain waves are bioelectric signals generated when information is transmitted between neurons. They are electric wave signals generated by ion exchange during the synaptic activity of pyramidal cells in the cerebral cortex. Brain wave signals can be understood as signals that can characterize the brain activity of the detection object, which can be signal curves or fluctuation signals represented by numbers. Predicting the brain wave signal of the target detection object can be a basis for judging whether the subsequent target detection object belongs to a living object. Regarding the prediction method of brain wave signals, an intelligent learning algorithm can be used, such as: pre-collecting biometric images and corresponding brain wave signals of different users, etc., to perform model training, and using the trained brain wave prediction model to predict the brain wave signal of the biometric image of the target detection object. Alternatively, expert experience can be used, such as: inviting some experts to analyze and classify the brain wave signals of the biometric images corresponding to different users, obtain the relationship between the biometric image and the brain wave signal, and then predict the brain wave signal of the biometric image of the target detection object. The embodiments of this specification do not specifically limit the method for predicting brain wave signals.

[0038] Step 106: Determine the emotional characteristics of the target detection object according to the brain wave signal.

[0039] In the specific implementation process, different brain wave signals can reflect the user's emotions, such as: when happy, angry, nervous, the brain wave signal may fluctuate more, and when calm, the brain wave signal fluctuates less. Emotional features can be understood as feature data that can characterize the emotions of the detection object, and may include emotion categories or other feature data, which are not specifically limited in the embodiments of this specification. The emotional features of the target detection object can be determined through brain wave signals, and the emotional perception model can also be trained using an intelligent learning algorithm or using expert experience, etc., to perceive the brain wave signals obtained in the previous step and determine the emotional features of the target detection object. For example: pre-acquire brain wave signals corresponding to several emotion categories, compare the brain wave signals of the target detection object obtained in the previous step with brain wave signals of different types of emotion categories, and use the one with the highest similarity as the emotion category of the target detection object. The embodiments of this specification can use an affective computing algorithm (affective computing) to perform emotional computing on the detection object. Affective computing can generally refer to the perception and influence of a person's emotions and state by a computer using an algorithm. In the embodiments of this specification, it can specifically refer to the use of facial images to perceive the user's emotions and state.

[0040] In some embodiments of the present specification, before determining the emotional characteristics of the target detection object according to the brain wave signal, the method further includes:

[0041] If the brain wave signal of the target detection object is predicted to be 0 based on the biometric image, it is determined that the target detection object is not a living object.

[0042] In the specific implementation process, after predicting the brain wave signal of the target detection object, if the predicted brain wave signal is 0, it means that the target detection object has no brain wave signal. At this time, it can be said that the target detection object may be a photo, mask, screen or other object without brain activity. In this case, it is directly determined that the target detection object is not a living object, and no subsequent liveness detection processing is required. Through the prediction of brain wave signals, when the predicted brain wave signal is 0, the detection object is directly determined to be a non-living object and an attack target, and a warning can be issued, which improves the efficiency of liveness detection and the security of biometrics.

[0043] Step 108: Determine whether the target detection object is a living object based on the emotion characteristics.

[0044] In the specific implementation process, after the emotional characteristics of the target detection object are perceived based on the brain wave signal, it can be determined whether the target detection object is a living object based on the emotional characteristics of the target detection object, such as: if the emotional fluctuation of the target detection object is relatively large, the target detection object is determined to be a living object, and if the emotional fluctuation of the target detection object is relatively small, the target detection object is determined to be a non-living object. Alternatively, the brain wave signal and emotional characteristics of the target detection object can be combined to comprehensively evaluate whether the target detection object is a living object. An intelligent learning algorithm can also be used to train a liveness detection model, and then the trained liveness detection model can be used to perform liveness detection on the target detection object based on emotional characteristics, brain wave signals, etc., to predict the probability of the target detection object belonging to a live attack, and to determine whether the target detection object is a live object based on the size of the live attack probability. The embodiments of this specification do not limit the specific method of liveness detection.

[0045] The liveness detection method provided in the embodiments of this specification collects the biometric image of the target detection object, predicts the brain wave signal of the target detection object based on the collected biometric image, calculates the emotional characteristics of the target detection object based on the brain wave signal, and identifies whether the target detection object is a live object based on the brain wave signal and emotional characteristics. This method utilizes the essential difference between real users and attacks, namely their brain wave signals and emotional states, and can essentially improve the security capabilities of the liveness anti-attack method. Even attacks that have never been seen before will be intercepted because of abnormal brain wave and emotional state signals, thereby improving the accuracy of liveness detection and thus improving the security of biometric identification.

[0046] In some embodiments of this specification, the method further includes:

[0047] Pre-training to build brainwave prediction models and emotion perception models;

[0048] Using the output of the brain wave prediction model and the output of the emotion perception model as training input data of a liveness detection model, and training and constructing the liveness detection model;

[0049] Predicting the brain wave signal of the target detection object based on the biometric image using the trained brain wave prediction model;

[0050] Determine the emotional characteristics of the target detection object according to the brain wave signal using the trained emotion perception model;

[0051] The trained liveness detection model is used to determine whether the target detection object is a live object according to the brain wave signal and the emotional characteristics.

[0052] In the specific implementation process, the embodiment of this specification can be pre-trained to construct a brain wave prediction model and an emotion perception model, such as: collecting a certain number of historical users' biometric images and corresponding brain wave signals, emotional states, etc. when performing biometric identification as sample data, and performing model training of the brain wave prediction model and the emotion perception model. Then use the trained brain wave prediction model and the emotion perception model to train the liveness detection model, and the model output of the trained brain wave prediction model and the emotion perception model can be used as the input of the training sample of the liveness detection model to train and construct the liveness detection model. After each model is trained, when performing liveness detection on the target detection object, the collected biometric image of the target detection object can be input into the trained brain wave prediction model to predict the brain wave signal of the target detection object. Then input the brain wave signal into the trained emotion perception model to obtain the emotional characteristics of the target detection object. Finally, the emotional characteristics, or the emotional characteristics and the brain wave signal can be input into the trained liveness detection model, and the liveness detection model is used to obtain the probability that the target detection object belongs to a live object, and then determine whether the target detection object belongs to a live object, and complete the liveness detection of the target detection object. The model training process can be completed offline or on the server. The pre-trained intelligent learning model can quickly detect the object's brain wave signals, emotional characteristics and the probability of belonging to a living object, thereby improving data processing efficiency.

[0053] In some embodiments of this specification, the method for constructing the brain wave prediction model includes:

[0054] Setting model parameters of the brain wave prediction model, wherein the model parameters include a network structure and a loss function of the brain wave prediction model;

[0055] Collecting living biological characteristic sample images and corresponding living brain wave sample signals of living objects;

[0056] Collect attack biometric sample images and corresponding attack brain wave sample signals of different categories of attack objects, where the attack brain wave sample signal is 0;

[0057] The living body biometric sample image and the attacking biometric sample image are used as inputs of the brain wave prediction model, and the living body brain wave sample signal and the attacking brain wave sample signal are used as outputs corresponding to the brain wave prediction model. Model training is performed until the loss function of the brain wave prediction model converges, thereby completing the training of the brain wave prediction model.

[0058] In the specific implementation process, the model parameters of the brain wave prediction model can be set first, such as: model structure, type of loss function, etc., which can be set according to actual needs, and the embodiments of this specification do not make specific limitations. Then collect a certain number of living objects such as real users' living biometric sample images and corresponding living brain wave sample signals. By wearing a brain wave collector for the real user, the biometric image of the real user wearing the brain wave collector for face recognition and other biometric identification and the brain wave signal collected by the worn brain wave collector are collected as living biometric sample images and living brain wave sample signals. Then collect different categories of attack objects such as photos, screens, masks, etc. for biometric identification and corresponding brain wave signals, respectively as attack biometric sample images and attack brain wave sample signals, wherein the attack sample has no brain wave signal, so the attack brain wave sample signal is 0. The samples of real users can be used as white samples and the samples of attack objects can be used as black samples to train the brain wave prediction model.

[0059] In some embodiments of the present specification, the collecting of living biological characteristic sample images and corresponding living brain wave sample signals of living objects includes:

[0060] Select living subjects of different age groups as sample subjects, each sample subject wears a brain wave collector;

[0061] The living biological sample images and the living brain wave sample signals collected by the brain wave collector are collected when each sample object is subjected to biometric identification under different lighting conditions.

[0062] In the specific implementation process, when collecting the sample images of living biological characteristics of living objects and the corresponding sample signals of living brain waves, living objects of different age groups can be selected as sample objects, and then each sample object is given a brain wave collector for biometric identification, and the sample images of living biological characteristics and the sample signals of living brain waves collected by the brain wave collector are collected for each sample object under different lighting conditions for biometric identification. The sample objects cover different age groups and different lighting conditions, which better meet the needs of real users, thereby improving the accuracy of model training.

[0063] By collecting biometric images and brain wave signals of real users and attack targets during biometric identification as sample data, the brain wave prediction model is trained, and the trained brain wave prediction model is used to predict the brain wave signals of the detection object, laying a data foundation for liveness detection.

[0064] In some embodiments of this specification, the training method of the emotion perception model includes:

[0065] Setting model parameters of the emotion perception model, wherein the model parameters include a network structure and a loss function of the emotion perception model;

[0066] Collecting a living brain wave sample signal of a living object, and determining an emotion category corresponding to the living object;

[0067] The living brain wave sample signal is used as the input of the emotion perception model, and the emotion category and the corresponding emotion feature are used as the corresponding output of the emotion perception model. Model training is performed until the loss function of the emotion perception model converges, thereby completing the training of the emotion perception model.

[0068] In the specific implementation process, similar to the training process of the brain wave prediction model, the training of the emotion perception model can be carried out. First, the model parameters of the emotion perception model are set, the living brain wave sample signals of the living object are collected, and the emotion category corresponding to the living object is determined, such as: happy, nervous, angry, calm. The living object can be pre-identified under the specified emotion category, and then the corresponding brain wave sample signal is collected. The collected living brain wave sample signal is used as the input of the emotion perception model, and the corresponding emotion category and emotion feature are used as the output of the model. The model is trained until the loss function of the emotion perception model converges and the training of the emotion perception model is completed. Among them, the emotion feature can be understood as a feature vector of the emotion perception model before the output of the emotion category. After processing the input data, the emotion perception model obtains a vector of emotion features, and identifies the corresponding emotion category based on the vector, such as: the emotion feature can be a 512-dimensional vector. The trained emotion perception model can be used to quickly perceive the emotions of the target detection object, laying a data foundation for subsequent live detection.

[0069] In some other embodiments of this specification, the training method of the emotion perception model may also include:

[0070] Setting model parameters of the emotion perception model, wherein the model parameters include a network structure and a loss function of the emotion perception model;

[0071] Inputting the collected biometric sample image into the trained brain wave prediction model, and using the brain wave prediction model to predict the corresponding predicted brain wave signal;

[0072] Clustering the predicted brain wave signals to determine the emotion category corresponding to each predicted brain wave signal;

[0073] The predicted brain wave signal is used as the input of the emotion perception model, and the emotion category and the corresponding emotion feature are used as the corresponding output of the emotion perception model. Model training is performed until the loss function of the emotion perception model converges, thereby completing the training of the emotion perception model.

[0074] In the specific implementation process, in some embodiments of the present specification, the trained brainwave prediction model can also be used to generate input sample data for training the emotion perception model, and the collected biometric sample images such as: face area images can be input into the trained brainwave prediction model, and the corresponding predicted brainwave signals can be predicted using the brainwave prediction model. It is possible to collect some biometric images of objects without brainwave signals, such as: collecting face images of real users when performing face recognition, but there is no need to use a brainwave collector to collect the corresponding brainwave signals, and use the trained brainwave prediction model to predict the brainwave signals corresponding to each face image. It is also possible to directly use the biometric images collected during the training of the brainwave prediction model as training samples for training the emotion perception model, and after using the brainwave prediction model to predict the corresponding brainwave signals, perform cluster analysis on the predicted brainwave signals output by the brainwave prediction model to obtain a variety of different emotion categories, and use the emotion categories corresponding to each predicted brainwave signal as labels for subsequent emotion perception model training. The predicted brain wave signal can be used as the input of the emotion perception model, and the corresponding emotion category and emotion feature can be used as the corresponding output of the emotion perception model to perform model training until the loss function of the emotion perception model converges, thus completing the training of the emotion perception model. The meaning of the emotion feature is the same as the meaning of the emotion feature output during the emotion perception model training in the above embodiment, and will not be repeated here.

[0075] In the embodiments of this specification, a trained brainwave prediction model is used to train an emotion perception model. When performing liveness detection subsequently, the brainwave prediction model is also used to predict the brainwave signals of the target detection object, and then the emotion perception model performs emotion recognition on the brainwave signals predicted by the brainwave prediction model. The model training process is more in line with the application requirements and application process of liveness detection, thereby improving the overall performance of the liveness detection algorithm, improving the accuracy of liveness detection, and thereby improving the security of biometrics.

[0076] In some embodiments of this specification, the output of the brain wave prediction model and the output of the emotion perception model are used as training input data of a liveness detection model, and training and constructing the liveness detection model includes:

[0077] Setting model parameters of the liveness detection model, wherein the model parameters include a network structure and a loss function of the liveness detection model;

[0078] Collecting sample images of living biometric features of living objects and sample images of attack biometric features of different categories of attack objects, and marking the attack probability labels corresponding to each sample image;

[0079] Using the trained brain wave prediction model, respectively predict the predicted brain wave signals corresponding to the living biological characteristic sample image and the attacking biological characteristic sample image;

[0080] Determine the emotion characteristics corresponding to the living body biometric sample image and the attacking biometric sample image using the trained emotion perception model based on the predicted brain wave signal predicted by the brain wave prediction model;

[0081] The predicted brain wave signal output by the brain wave prediction model and the corresponding emotional features output by the emotion perception model are used as the input of the liveness detection model, and the attack probability label corresponding to each sample image is used as the output of the liveness detection model. Model training is performed until the loss function of the liveness detection model converges, thereby completing the training of the liveness detection model.

[0082] In the specific implementation process, after the brain wave prediction model and the emotion perception model are trained, the output of the above-trained brain wave prediction model and the emotion perception model can be used to train the liveness detection model. After setting the model parameters of the liveness detection model, the liveness biometric sample images of the live object and the attack biometric sample images of different categories of attack objects can be collected, and at the same time, the attack probability labels corresponding to each sample image are marked, such as: the attack probability label corresponding to the liveness biometric sample image is 0, and the attack probability label corresponding to the attack biometric sample image is 1. It is also possible to directly use the biometric images collected during the training of the brain wave prediction model as training samples for training the liveness detection model, input the collected liveness biometric sample images and the attack biometric sample images into the brain wave prediction model, use the brain wave prediction model to predict the corresponding predicted brain wave signal, and then use the emotion perception model to perform emotion recognition on the predicted brain wave signal to determine the emotional characteristics corresponding to each liveness biometric sample image and the attack biometric sample image. After obtaining the predicted brain wave signals and emotional features, the predicted brain wave signals and emotional features can be used as the input of the liveness detection model, and the attack probability label corresponding to each sample image can be used as the output of the liveness detection model. The model is trained until the loss function of the liveness detection model converges, thus completing the training of the liveness detection model.

[0083] The embodiments of this specification use the trained brain wave prediction model and emotion perception model to train the liveness detection model, which is consistent with the liveness detection process, better meets the liveness detection scenario requirements, has higher accuracy in model training, and improves the accuracy of liveness detection.

[0084] In some embodiments of the present specification, the model structure of the brain wave prediction model adopts a lightweight network structure, and the model structures of the emotion perception model and the living body detection model adopt a multi-layer perceptron structure.

[0085] In the specific implementation process, the model structure of the brainwave prediction model can adopt a lightweight network structure such as: MobileNetV2. The MobileNetV2 structure is based on an inverted residual structure. The main branch of the original residual structure has three convolutions, and the two point-by-point convolution channels are large. The inverted residual structure is just the opposite. The number of convolution channels in the middle (still using a depth-separable convolution structure) is large, and the number of channels at both ends is small. The model structure of the emotion perception model and the liveness detection model can adopt a multi-layer perceptron structure such as: MLP, Multilayer Perceptron. The multi-layer perceptron is a feedforward artificial neural network model that maps multiple input data sets to a single output data set. The brainwave prediction model chooses a lightweight type with a simple structure to reduce the computational cost. The emotion perception model and the liveness detection model use a model structure that is slightly more complex than the lightweight structure, which can improve the accuracy of emotion perception and liveness detection.

[0086] Figure 2 This is a schematic diagram of the principle flow of liveness detection in a scenario example of this manual, such as Figure 2 As shown, in some scenario examples of this manual, the process of liveness detection mainly includes 5 steps, and the specific process can be referred to as follows:

[0087] 1. Training data collection: Use brain wave data collection instruments and IoT devices equipped with high-definition cameras to simulate brain wave and face area changes during face recognition;

[0088] 2. Brainwave prediction model training: using the user's face image as input, the user's brainwave data is fitted and predicted;

[0089] 3. Emotion perception model training: training an emotion classification model based on brain waves as the basis for liveness detection;

[0090] 4. Liveness model training: Based on the results of the emotion perception model in the previous step, the liveness detection model is trained;

[0091] 5. Liveness detection: Use the above-trained models to perform liveness detection on the biometric object.

[0092] Among them, the training process of the brain wave prediction model can be referred to as follows:

[0093] Brainwave acquisition equipment and IoT devices equipped with high-definition cameras are used to collect the user's facial data and corresponding brainwave data when the user performs facial recognition verification.

[0094] Data collection process: In some scenario examples in this manual, 500 users (dispersed in various age groups to ensure coverage of various types of users) can be selected; each user wears a brain wave collector under different lighting conditions and uses the IoT device for 5 face recognitions; each face recognition data collection lasts about 5 seconds. Each time, the IoT device's built-in high-precision camera is used to collect about 5 seconds of face data and corresponding brain wave data; after completing the data collection of real users, 500 types of attack materials are used for data collection, and the collection process is the same as that of real users; since the attack cannot collect brain wave data, the brain wave data is replaced with a sequence of all 0s.

[0095] Brainwave prediction model training:

[0096] Data preprocessing: First, perform face detection on the collected real person / attack data and crop the face area for backup; then, perform a mean filter with a length of 25 on the brain wave data to filter out noise;

[0097] Model structure: Use MobileNetV2 (lightweight network structure) as the backbone to regress brain wave signals;

[0098] Model input and output: The model input is 10 images randomly and uniformly sampled from 5s face images, and the output is the corresponding brain wave signal; note that the attacking brain wave signal is a sequence of all 0s;

[0099] Loss function: The loss function is the L2 distance between the model output and the real brain wave sequence;

[0100] Training method: Use the above network structure and loss function to train the model based on SGD (stochastic gradient descent) until the loss function converges to complete the training of the brain wave prediction model.

[0101] The training process of the emotion perception model can be referred to as follows:

[0102] The emotion perception model is mainly based on the brain wave prediction model obtained in the previous step for further unsupervised emotion perception model training.

[0103] Brainwave sequence extraction: For facial image sequences without corresponding brainwave signals, the above-trained brainwave prediction model is used to perform brainwave prediction; approximately 50,000-100,000 brainwave data of living body data is generated for the training of the emotion perception model;

[0104] Brainwave-emotion clustering: Hierarchical clustering is performed on 50,000-100,000 brainwave records to obtain N categories of different emotions; the emotion category corresponding to each record will be used as a label for subsequent emotion recognition;

[0105] Model structure: The model can choose a 5-layer MLP (Multilayer Perceptron) model;

[0106] Input and output: The input is the brain wave sequence, and the output is the emotion category and the corresponding emotion characteristics;

[0107] Loss function: The loss function is a classification loss function;

[0108] Model training: Use the above network structure and loss function to perform model training based on SGD until the loss function converges to complete the training of the emotion perception model.

[0109] The training of the liveness detection model can refer to the following process:

[0110] Using the outputs of the above-trained brain wave prediction model and emotion perception model, a living body classification model is trained;

[0111] Model structure: The model is a 5-layer MLP;

[0112] Input and output: The input is emotional characteristics and brain wave signals, and the output is the probability of attack;

[0113] Loss function: live / attack classification function;

[0114] Model training method: Use the above network structure and loss function to train the model based on SGD until the loss function converges.

[0115] The process of liveness detection can be referred to as follows:

[0116] The target detection object starts face recognition by interacting with the IoT device;

[0117] Collect face data for about 5 seconds and perform face detection to obtain the face area;

[0118] Uniformly sample the 5s face images, take 10 images and input them into the brain wave prediction model to obtain the predicted brain wave signal; if the brain wave is all 0 signals, it is directly judged as non-living and the face recognition fails; otherwise, proceed to the next step;

[0119] Input brain wave signals into the emotion perception model to obtain emotion categories and emotion characteristics;

[0120] The emotional features and brain wave signals are input into the liveness detection model to obtain the liveness attack probability P. If P is greater than the pre-set threshold T, it is judged as an attack, otherwise it is judged as a live object.

[0121] The embodiments of this specification use multiple frames of high-definition face images to predict the user's brain wave signals, and then calculate the user's state and emotions, and determine whether it is a live user based on the state and emotions. This method takes advantage of the essential difference between real users and attacks (static photos, etc.) (i.e. their emotions and states), which can essentially improve the security capabilities of the method. Even attacks that have never been seen will be intercepted because of abnormal emotional and state signals. Both security and experience have been greatly improved.

[0122] In this specification, each embodiment of the above method is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0123] Based on the liveness detection method described above, one or more embodiments of this specification also provide a system for liveness detection. The system may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this specification and a device in combination with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0124] Specifically, Figure 3 This is a schematic diagram of the module structure of an embodiment of a liveness detection device provided in this specification. The device can be used in biometric devices, such as face recognition devices, face recognition payment devices, etc. Figure 3 As shown, the living body detection device provided in this specification may include:

[0125] An image acquisition module 31 is used to acquire a biometric image of a target detection object during biometric identification;

[0126] A brain wave information prediction module 32, used to predict the brain wave signal of the target detection object based on the biometric image;

[0127] An emotion feature recognition module 33, used to determine the emotion feature of the target detection object according to the brain wave signal;

[0128] The living body detection module 34 is used to determine whether the target detection object is a living body object according to the emotion characteristics.

[0129] The liveness detection device provided in the embodiments of this specification predicts the user's brain wave signals by using multiple frames of high-definition face images, and then calculates the user's state and emotions, and determines whether it is a live user based on the state and emotions. This type of method utilizes the essential difference between real users and attacks (static photos, etc.) (i.e. their emotions and states), which can essentially improve the security capabilities of the method. Even attacks that have never been seen will be intercepted because of abnormal emotional and state signals. Both security and experience have been greatly improved.

[0130] It should be noted that the above-mentioned device may also include other implementations according to the description of the corresponding method embodiment. The specific implementation methods can refer to the description of the corresponding method embodiment above, and will not be described one by one here.

[0131] The embodiment of this specification also provides a living body detection device, including: at least one processor and a memory for storing processor executable instructions, and the processor implements the living body detection method of the above embodiment when executing the instructions, such as:

[0132] Collecting biometric images of target detection objects;

[0133] Predicting a brain wave signal of the target detection object based on the biometric image;

[0134] Determining the emotional characteristics of the target detection object according to the brain wave signal;

[0135] According to the emotion feature, it is determined whether the target detection object is a living object.

[0136] The embodiment of this specification also provides a liveness detection system, including: an image acquisition device and an image processing device, wherein the image acquisition device is used to acquire a biometric image of a target detection object for biometric identification, and the image processing device includes at least one processor and a memory for storing processor executable instructions. When the processor executes the instructions, the liveness detection method performs liveness detection on the biometric image acquired by the image acquisition device, such as:

[0137] Collecting biometric images of target detection objects;

[0138] Predicting a brain wave signal of the target detection object based on the biometric image;

[0139] Determining the emotional characteristics of the target detection object according to the brain wave signal;

[0140] According to the emotion feature, it is determined whether the target detection object is a living object.

[0141] It should be noted that the above-mentioned device and system may also include other implementation modes according to the description of the method embodiment. The specific implementation modes may refer to the description of the relevant method embodiment, which will not be described one by one here.

[0142] The liveness detection device provided in this specification can also be used in a variety of data analysis and processing systems. The system or server or terminal or device can be a separate server, or it can include a server cluster, system (including distributed system), software (application), actual operation device, logic gate circuit device, quantum computer, etc. that uses one or more of the methods or one or more embodiments of the system or server or terminal or device of this specification and a terminal device combined with necessary implementation hardware. The detection system for checking the difference data may include at least one processor and a memory storing computer executable instructions, and the processor implements the steps of the method described in any one or more of the above embodiments when executing the instructions.

[0143] The method embodiments provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 4 1 is a hardware structure block diagram of a liveness detection server in one embodiment of this specification. The computer terminal may be a liveness detection server or a liveness detection device in the above embodiment. Figure 4 The server 10 shown may include one or more (only one is shown in the figure) processors 100 (the processor 100 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a non-volatile memory 200 for storing data, and a transmission module 300 for communication functions. Those skilled in the art will understand that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components shown in the figure may also include other processing hardware, such as a database or multi-level cache, GPU, or other hardware with Figure 4 Different configurations are shown.

[0144] The non-volatile memory 200 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the liveness detection method in the embodiment of this specification. The processor 100 executes various functional applications and resource data updates by running the software programs and modules stored in the non-volatile memory 200. The non-volatile memory 200 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the non-volatile memory 200 may further include a memory remotely arranged relative to the processor 100, and these remote memories may be connected to a computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0145] The transmission module 300 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission module 300 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 300 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0146] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media, and the storage media can be read and executed by computers to achieve the effects of the solutions described in the embodiments of this specification, such as:

[0148] Collecting biometric images of target detection objects;

[0149] Predicting a brain wave signal of the target detection object based on the biometric image;

[0150] Determining the emotional characteristics of the target detection object according to the brain wave signal;

[0151] According to the emotion feature, it is determined whether the target detection object is a living object.

[0152] The above-mentioned liveness detection method or device provided in the embodiments of this specification can be implemented by a processor in a computer executing corresponding program instructions, such as using the C++ language of the Windows operating system to implement it on a PC, on a Linux system, or other systems such as Android and iOS system programming languages ​​to implement it on a smart terminal, as well as based on the processing logic of a quantum computer.

[0153] It should be noted that the device, computer storage medium, and system described in the specification may also include other implementation methods according to the description of the relevant method embodiments. The specific implementation methods can refer to the description of the corresponding method embodiments, which will not be described one by one here.

[0154] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0155] The embodiments of this specification are not limited to complying with industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom method or embodiment can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of the embodiments of this specification.

[0156] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0157] Although one or more embodiments of the present specification provide method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps, and does not represent a unique execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, an environment of a parallel processor or multi-threaded processing, or even a distributed resource data update environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or equipment including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or equipment. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or equipment including the elements. The first, second, etc. words are used to represent the name, and do not represent any particular order.

[0158] For the convenience of description, the above devices are described in various modules according to their functions. Of course, when implementing one or more of the present specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple 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, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable resource data update device to produce a machine, so that instructions executed by the processor of the computer or other programmable resource data update device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0160] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable resource data update device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0161] These computer program instructions may also be loaded onto a computer or other programmable resource data updating device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0162] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0163] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0164] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage, graphene storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0165] It should be understood by those skilled in the art that one or more embodiments of the present specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of the present specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, one or more embodiments of the present specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0167] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0168] The above description is only an example of one or more embodiments of the present specification and is not intended to limit one or more embodiments of the present specification. For those skilled in the art, one or more embodiments of the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims.

Claims

1. A method for detecting a living body, the method comprising: Collecting biometric images of the target detection object during biometric identification; Predicting a brain wave signal of the target detection object based on the biometric image; Determining the emotional characteristics of the target detection object according to the brain wave signal; Determining whether the target detection object is a living object according to the emotion characteristics; The method further comprises: Pre-training to build brainwave prediction models and emotion perception models; Using the output of the brain wave prediction model and the output of the emotion perception model as training input data of a liveness detection model, and training and constructing the liveness detection model; Predicting the brain wave signal of the target detection object based on the biometric image using the trained brain wave prediction model; Determine the emotional characteristics of the target detection object according to the brain wave signal using the trained emotion perception model; The trained liveness detection model is used to determine whether the target detection object is a live object according to the brain wave signal and the emotional characteristics.

2. The method according to claim 1, before determining the emotional characteristics of the target detection object according to the brain wave signal, the method further comprises: If the brain wave signal of the target detection object is predicted to be 0 based on the biometric image, it is determined that the target detection object is not a living object.

3. The method according to claim 1, wherein the method for constructing the brain wave prediction model comprises: Setting model parameters of the brain wave prediction model, wherein the model parameters include a network structure and a loss function of the brain wave prediction model; Collecting living biological characteristic sample images and corresponding living brain wave sample signals of living objects; Collect attack biometric sample images and corresponding attack brain wave sample signals of different categories of attack objects, where the attack brain wave sample signal is 0; The living body biometric sample image and the attacking biometric sample image are used as inputs of the brain wave prediction model, and the living body brain wave sample signal and the attacking brain wave sample signal are used as outputs corresponding to the brain wave prediction model. Model training is performed until the loss function of the brain wave prediction model converges, thereby completing the training of the brain wave prediction model.

4. The method according to claim 1, wherein the training method of the emotion perception model comprises: Setting model parameters of the emotion perception model, wherein the model parameters include a network structure and a loss function of the emotion perception model; Collecting a living brain wave sample signal of a living object, and determining an emotion category corresponding to the living object; The living brain wave sample signal is used as the input of the emotion perception model, and the emotion category and the corresponding emotion feature are used as the corresponding output of the emotion perception model. Model training is performed until the loss function of the emotion perception model converges, thereby completing the training of the emotion perception model.

5. The method according to claim 1, wherein the training method of the emotion perception model comprises: Setting model parameters of the emotion perception model, wherein the model parameters include a network structure and a loss function of the emotion perception model; Inputting the collected biometric sample image into the trained brain wave prediction model, and using the brain wave prediction model to predict the corresponding predicted brain wave signal; Clustering the predicted brain wave signals to determine the emotion category corresponding to each predicted brain wave signal; The predicted brain wave signal is used as the input of the emotion perception model, and the emotion category and the corresponding emotion feature are used as the corresponding output of the emotion perception model. Model training is performed until the loss function of the emotion perception model converges, thereby completing the training of the emotion perception model.

6. The method according to claim 1, wherein the output of the brain wave prediction model and the output of the emotion perception model are used as training input data of a liveness detection model, and the training and construction of the liveness detection model comprises: Setting model parameters of the liveness detection model, wherein the model parameters include a network structure and a loss function of the liveness detection model; Collecting sample images of living biometric features of living objects and sample images of attack biometric features of different categories of attack objects, and marking the attack probability labels corresponding to each sample image; Using the trained brain wave prediction model, respectively predict the predicted brain wave signals corresponding to the living biological characteristic sample image and the attacking biological characteristic sample image; Determine the emotion characteristics corresponding to the living body biometric sample image and the attacking biometric sample image using the trained emotion perception model based on the predicted brain wave signal predicted by the brain wave prediction model; The predicted brain wave signal output by the brain wave prediction model and the corresponding emotional features output by the emotion perception model are used as the input of the liveness detection model, and the attack probability label corresponding to each sample image is used as the output of the liveness detection model. Model training is performed until the loss function of the liveness detection model converges, thereby completing the training of the liveness detection model.

7. According to the method as claimed in claim 1, the model structure of the brain wave prediction model adopts a lightweight network structure, and the model structure of the emotion perception model and the living body detection model adopts a multi-layer perceptron structure.

8. The method according to claim 1, wherein collecting a biometric image of the target detection object during biometric identification comprises: The image information of the target detection object within a specified time after the start of biometric identification is collected, and a specified number of images are selected from the image information as the biometric feature images of the target detection object.

9. The method according to claim 3, wherein collecting a living biological characteristic sample image and a corresponding living brain wave sample signal of a living object comprises: Select living subjects of different age groups as sample subjects, each sample subject wears a brain wave collector; The living biological sample images and the living brain wave sample signals collected by the brain wave collector are collected when each sample object is subjected to biometric identification under different lighting conditions.

10. A living body detection device, comprising: An image acquisition module, used to acquire a biometric image of a target detection object during biometric identification; A brain wave information prediction module, used to predict the brain wave signal of the target detection object based on the biometric image; An emotion feature recognition module, used to determine the emotion feature of the target detection object according to the brain wave signal; A liveness detection module, used to determine whether the target detection object is a live object according to the emotion characteristics; The device is also used for: Pre-training to build brainwave prediction models and emotion perception models; Using the output of the brain wave prediction model and the output of the emotion perception model as training input data of a liveness detection model, and training and constructing the liveness detection model; Predicting the brain wave signal of the target detection object based on the biometric image using the trained brain wave prediction model; Determine the emotional characteristics of the target detection object according to the brain wave signal using the trained emotion perception model; The trained liveness detection model is used to determine whether the target detection object is a live object according to the brain wave signal and the emotional characteristics.

11. A living body detection device, comprising: At least one processor and a memory for storing processor-executable instructions, wherein when the processor executes the instructions, the method according to any one of claims 1 to 9 is implemented.

12. A liveness detection system, comprising: An image acquisition device and an image processing device, wherein the image acquisition device is used to acquire biometric images of a target detection object for biometric identification, and the image processing device includes at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the method described in any one of claims 1 to 9 is implemented, which is used to perform liveness detection on the biometric images acquired by the image acquisition device.

Images