Palm data processing method and device, equipment, storage medium and program product

Abstract

The invention relates to a palm data processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring current echo information received by transmitting ultrasonic waves to a target palm through a brushing device, and acquiring a current palm image obtained by shooting the target palm through the brushing device; generating a current echo feature set based on the current echo information and the ultrasonic emission information corresponding to the current echo information; performing living body detection on the target palm based on the current echo feature set to obtain a living body detection result corresponding to the target palm; and when the living body detection result is that the target palm belongs to the living body, determining target identity information corresponding to the target palm based on the current palm image. By adopting the method, the identity recognition accuracy can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a palm data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of computer technology, biometric technology has emerged. Biometric technology uses inherent physiological characteristics (such as fingerprints, finger veins, faces, irises, etc.) and behavioral features (such as handwriting, voice, gait, etc.) to identify an individual. Many devices use biometric technology, and palm-swiping devices are one of them. A palm-swiping device is a device that uses biometric technology related to the palm.

[0003] Currently, palm-scanning devices primarily use cameras to capture images of the palm and then perform identity verification based on these images. However, image information is easily obtained and forged, leading to low accuracy in current palm-scanning identification methods. Summary of the Invention

[0004] Therefore, it is necessary to provide a palm data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of identity recognition in response to the above-mentioned technical problems.

[0005] This application provides a method for processing palm data, including:

[0006] Acquire the current echo information received from the ultrasonic waves emitted to the target palm by the palm-swiping device, and acquire the current palm image obtained by the palm-swiping device from the target palm.

[0007] Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, a current echo feature set is generated;

[0008] Based on the current echo feature set, liveness detection is performed on the target hand to obtain the liveness detection result corresponding to the target hand;

[0009] When the liveness detection result indicates that the target is a live person, the target identity information corresponding to the target hand is determined based on the current hand image.

[0010] This application also provides a palm data processing device, including:

[0011] The data acquisition module is used to acquire the current echo information received by the ultrasonic waves emitted to the target palm through the palm brushing device, and to acquire the current palm image obtained by the palm brushing device by capturing the target palm.

[0012] The feature generation module is used to generate a current echo feature set based on the current echo information and the ultrasonic wave emission information corresponding to the current echo information;

[0013] The liveness detection module is used to perform liveness detection on the target hand based on the current echo feature set, and obtain the liveness detection result corresponding to the target hand.

[0014] The identity determination module is used to determine the target identity information corresponding to the target hand based on the current hand image when the liveness detection result indicates that the target is a live person.

[0015] In one embodiment, the feature generation module is further configured to:

[0016] Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, the target hand is located to obtain the first echo feature for the geometric information of the hand.

[0017] Based on the data difference between the ultrasonic wave emission information and the current echo information, a second echo feature for the palm material information is obtained.

[0018] Echo intensity analysis is performed on the current echo information to obtain the third echo feature for palm tissue information;

[0019] Based on the first echo feature, the second echo feature, and the third echo feature, the current echo feature set is obtained.

[0020] In one embodiment, the feature generation module is further configured to:

[0021] Ultrasonic imaging is performed based on the current echo information and the ultrasonic emission information corresponding to the current echo information to obtain an ultrasonic image, and the palm size features and palm texture features are obtained based on the ultrasonic image.

[0022] Based on the waveform morphology of multiple echo signals in the current echo information, the spatial morphological features of the palm are obtained;

[0023] Based on the palm size features, palm texture features, and palm spatial morphology features, a first echo feature for palm geometric information is obtained.

[0024] In one embodiment, the feature generation module is further configured to:

[0025] Based on the ultrasonic wave emission information and the current echo information, the absorption-reflection ratio of the ultrasonic wave is calculated.

[0026] The absorption-reflectance ratio is used as a second echo characteristic for palm material information.

[0027] In one embodiment, the feature generation module is further configured to:

[0028] By comparing the signal strengths of multiple echo signals in the current echo information, the echo strength distribution characteristics and echo strength ratio characteristics are obtained.

[0029] Based on the signal strength, receiving location, and receiving time of multiple echo signals in the current echo information, the target palm is divided into tissues to obtain tissue distribution characteristics.

[0030] Based on at least one of the echo intensity distribution characteristics, the echo intensity ratio characteristics, and the tissue distribution characteristics, a third echo feature for palm tissue information is obtained.

[0031] In one embodiment, the liveness detection module is further configured to:

[0032] The spatial morphological features of the palm are obtained from the current echo feature set;

[0033] When the spatial morphological features of the palm belong to planar morphological features, the liveness detection result corresponding to the target palm is determined to be a prosthesis;

[0034] When the spatial morphological features of the palm belong to three-dimensional morphological features, the other features in the current echo feature set are compared with the reference echo feature set corresponding to the real palm to obtain the liveness detection result corresponding to the target palm.

[0035] In one embodiment, the current echo feature set further includes a second echo feature for palm material information and a third echo feature for palm tissue information, and the reference echo feature set includes a reference echo feature range for palm material information and a reference echo feature range for palm tissue information. The liveness detection module is also used for:

[0036] Compare the second echo feature for palm material information with the reference echo feature range for palm material information;

[0037] When the second echo feature for palm material information belongs to the reference echo feature range for palm material information, the third echo feature for palm tissue information is compared with the reference echo feature range for palm tissue information.

[0038] When the third echo feature of the palm tissue information belongs to the reference echo feature range of the palm tissue information, the liveness detection result corresponding to the target palm is determined to be a live body.

[0039] If any comparison result is not within the corresponding reference echo feature range, the liveness detection result corresponding to the target hand is determined to be a prosthesis.

[0040] In one embodiment, the second echo feature for palm material information includes echo intensity distribution features, echo intensity ratio features, and tissue distribution features, and the reference echo feature range for palm tissue information includes a reference intensity distribution feature range, a reference intensity ratio feature range, and a reference tissue distribution feature range. The liveness detection module is also used for:

[0041] The echo strength distribution characteristics are compared with the range of the reference strength distribution characteristics;

[0042] When the echo strength distribution feature belongs to the reference strength distribution feature range, the echo strength ratio feature and the reference strength ratio feature range are compared.

[0043] When the echo intensity ratio characteristic falls within the reference intensity ratio characteristic range, the tissue distribution characteristic is compared with the reference tissue distribution characteristic range.

[0044] In one embodiment, the identity verification module is further configured to:

[0045] Determine the initial identity information corresponding to the target hand based on the current hand image;

[0046] Obtain the historical echo feature set corresponding to the initial identity information;

[0047] Based on the historical echo feature set, the current echo feature set is used for identity verification to obtain the identity verification result;

[0048] When the identity verification result is an identity match, the initial identity information is used as the target identity information corresponding to the target hand.

[0049] In one embodiment, the identity verification module is further configured to:

[0050] Extract palm print and palm vein features from the current palm image to obtain the current palm print and palm vein features;

[0051] From the identity database, identify registered palm prints and palm vein features that match the current palm print and palm vein features, and use the identity information to which the registered palm print and palm vein features belong as the initial identity information corresponding to the target palm.

[0052] In one embodiment, the identity verification module is further configured to:

[0053] Calculate the feature similarity between the current echo feature set and the historical echo feature set;

[0054] When the feature similarity is less than the similarity threshold, the identity verification result is determined to be an identity match;

[0055] When the feature similarity is greater than or equal to the similarity threshold, the identity verification result is determined to be an identity mismatch.

[0056] In one embodiment, the palm-swiping device is a palm-swiping payment device, which includes an image acquisition unit, an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix deployed around the image acquisition unit.

[0057] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps described in the above-described palm data processing method.

[0058] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps described in the above-described palm data processing method.

[0059] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps described in the above-described palm data processing method.

[0060] The aforementioned palm data processing method, apparatus, computer equipment, storage medium, and computer program product acquire current echo information received from ultrasonic waves emitted to a target palm via a palm-scanning device, and acquire a current palm image captured by the palm-scanning device. Based on the current echo information and the corresponding ultrasonic wave emission information, a current echo feature set is generated. Based on the current echo feature set, a liveness detection is performed on the target palm to obtain a liveness detection result. If the liveness detection result indicates a live target, the target identity information corresponding to the target palm is determined based on the current palm image. Thus, by emitting ultrasonic waves to a target palm via a palm-scanning device, receiving the echoes, and acquiring a palm image, and combining the echo features determined based on the emission and echo information with the palm image for identity recognition, the accuracy of identity recognition can be effectively improved. Ultrasonic waves are unaffected by ambient light, resulting in high detection accuracy. The current echo feature set generated based on the current echo information and the corresponding ultrasonic wave emission information includes multiple echo features. Liveness detection based on the current echo feature set can effectively eliminate spurious interference and ensure detection accuracy. When the target hand is confirmed to be alive, identity recognition based on the current hand image can effectively improve the accuracy of identity recognition. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is an application environment diagram of a palm data processing method in one embodiment;

[0063] Figure 2 This is a flowchart illustrating a palm data processing method in one embodiment;

[0064] Figure 3 This is a schematic diagram of a palm-swiping device in one embodiment;

[0065] Figure 4 This is a schematic diagram of the internal structure of a real hand in one embodiment;

[0066] Figure 5 This is a schematic diagram of the current echo feature set in one embodiment;

[0067] Figure 6 This is a schematic diagram of a liveness detection process based on the current echo feature set in one embodiment;

[0068] Figure 7 This is a schematic diagram of the palm-swiping device in another embodiment;

[0069] Figure 8 This is a schematic diagram of a process for determining whether a hand is a real hand based on echo in one embodiment;

[0070] Figure 9 This is a schematic diagram illustrating an application scenario of a palm payment device in one embodiment;

[0071] Figure 10 This is a schematic diagram illustrating an application scenario of a palm-swipe access control device in one embodiment;

[0072] Figure 11 This is a structural block diagram of a palm data processing device in one embodiment;

[0073] Figure 12 This is an internal structural diagram of a computer device in one embodiment;

[0074] Figure 13 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0076] The palm data processing method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other devices. Terminal 102 can be, but is not limited to, various handheld devices, personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0077] Both the terminal and the server can be used independently to execute the palm data processing method provided in the embodiments of this application. The terminal and the server can also be used collaboratively to execute the palm data processing method provided in the embodiments of this application.

[0078] For example, the terminal acquires the current echo information received from the ultrasonic waves emitted towards the target hand via a palm-scanning device, and acquires a current palm image captured by the palm-scanning device. Based on the current echo information and the corresponding ultrasonic wave emission information, the terminal generates a current echo feature set. It then performs liveness detection on the target hand based on this feature set, obtaining a liveness detection result for the target hand. If the liveness detection result indicates a live target, the terminal determines the target's identity information based on the current palm image.

[0079] In one embodiment, such as Figure 2 As shown, a method for processing palm data is provided. Taking the application of this method to a computer device as an example, the computer device can be a terminal or a server. It can be understood that this method can be executed independently by the terminal or server, or it can be implemented through interaction between the terminal and the server. Wherein:

[0080] Step S202: Obtain the current echo information received by the ultrasonic waves emitted to the target palm through the palm-swiping device, and obtain the current palm image obtained by the palm-swiping device.

[0081] The palm-swiping device is a biometric identification technology device that verifies identity by recognizing the user's palm. It can be understood that palm-swiping devices can be applied to multiple technical fields. For example, in the payment field, a palm-swiping device can be a palm-swiping payment device; in the access control field, it can be a palm-swiping access control device; in the attendance management field, it can be a palm-swiping attendance device; in the public transportation field, it can be a palm-swiping boarding device; and so on. The palm-swiping device in this application includes an ultrasonic transmitting unit, an ultrasonic receiving unit, and an image acquisition unit. The ultrasonic transmitting unit emits ultrasonic waves towards the palm to obtain ultrasonic transmission information; the ultrasonic receiving unit receives the echoes to obtain echo information; and the image acquisition unit captures an image of the palm.

[0082] It can be understood that ultrasonic transmission information includes information related to signal transmission, such as the transmission frequency, signal strength, transmission location, and transmission time. Echo information includes information related to signal reception, such as the reception time, signal strength, reception frequency, and reception location.

[0083] The target hand refers to the hand currently being processed. This can be either a user's hand or a forged hand. Current echo information refers to the echo information received when an ultrasonic wave is emitted towards the target hand, and current hand image refers to the image of the target hand currently being captured.

[0084] Specifically, the computer device acquires the current echo information received from the ultrasonic waves emitted to the target palm by the palm-scanning device, acquires the current palm image obtained by the palm-scanning device, and identifies the target palm based on the current echo information and the current palm image.

[0085] Step S204: Generate the current echo feature set based on the current echo information and the ultrasonic emission information corresponding to the current echo information.

[0086] Ultrasonic emission information refers to the emission information of ultrasonic waves. It can be understood that the palm-swiping device emits ultrasonic waves, which are reflected back when they encounter obstacles. Echo information refers to the information about the signal received by the palm-swiping device after the ultrasonic waves are emitted.

[0087] An echo feature set is a set of features generated based on echo information and the corresponding ultrasonic wave emission information. The current echo feature set is a set of features generated based on the current echo information and the corresponding ultrasonic wave emission information. The current echo feature set includes multiple echo features. Different echo features can reflect different dimensions of information about the target hand.

[0088] Specifically, the computer equipment acquires the ultrasonic wave emission information corresponding to the current echo information, and performs feature extraction based on the current echo information and its corresponding ultrasonic wave emission information to generate a current echo feature set. Specifically, feature extraction can be performed on the current echo information based on its corresponding ultrasonic wave emission information to obtain a subset of echo features, and these echo features are then combined to form the current echo feature set. For example, based on the current echo information and its corresponding ultrasonic wave emission information, the signal difference between the emitted and received ultrasonic waves can be analyzed to obtain an echo feature that can reflect the material of the target hand. As another example, based on the current echo information, the intensity distribution of the received ultrasonic wave signal can be analyzed to obtain an echo feature that can reflect the structure of the target hand.

[0089] In one embodiment, reference Figure 3 The palm-scanning device includes a palm-scanning module and an ultrasonic module. The palm-scanning module is used to acquire images, and the ultrasonic module is used to emit ultrasonic waves and receive echoes. After the target palm enters the detection area, the palm-scanning module acquires the current image of the target palm, and the ultrasonic module emits ultrasonic waves to the target palm and receives the echoes to obtain ultrasonic wave emission information and current echo information.

[0090] Step S206: Perform liveness detection on the target hand based on the current echo feature set to obtain the liveness detection result corresponding to the target hand.

[0091] Liveness detection refers to verifying whether a hand belongs to a real user. Liveness detection results are categorized as either "live" or "fake." "Live" indicates the hand is from a real user, while "fake" indicates the hand is a forged hand.

[0092] Specifically, the current echo feature set can reflect various characteristics of the target hand. Computer equipment can perform liveness detection on the target hand based on this feature set, analyzing whether the hand belongs to a real user to obtain the corresponding liveness detection result. For example, if the current echo feature set determines that the target hand's material is not skin, the liveness detection result is determined to be a prosthetic. As another example, if the current echo feature set determines that the target hand has high flatness, meaning it is close to a plane, the liveness detection result is determined to be a prosthetic.

[0093] In one embodiment, a reference echo feature set corresponding to the real user's palm (i.e., the real palm) is obtained. The current echo feature set corresponding to the target palm is compared with the reference echo feature set corresponding to the real palm to determine the liveness detection result corresponding to the target palm. For example, the feature similarity between the current echo feature set and the reference echo feature set is calculated. If the feature similarity is greater than a similarity threshold, the liveness detection result corresponding to the target palm is determined to be a live object; if the feature similarity is less than or equal to the similarity threshold, the liveness detection result corresponding to the target palm is determined to be a spoofed object.

[0094] In one embodiment, the echo feature set includes multiple echo features. According to the comparison priority of the echo features, the current echo feature set corresponding to the target hand is compared with the reference echo feature set corresponding to the real hand. If, based on a comparison result, the liveness detection result for the target hand is determined to be a prosthesis, the comparison can be stopped, and no further echo feature comparisons are needed. The comparison priority of the echo features can be set as needed. For example, the comparison priority of the echo features can be determined based on their computational complexity; the lower the computational complexity, the higher the comparison priority, and the earlier they are compared. Echo features can be generated and compared simultaneously. If the target hand is found to be a prosthesis, there is no need to continue generating echo features. Therefore, determining the comparison priority of the echo features based on their computational complexity helps save computer resources. For example, the spurious object recognition rate of each echo feature can be statistically analyzed. The spurious object recognition rate of an echo feature refers to the frequency at which a spurious object is identified based on the echo feature. The comparison priority of the echo feature is determined based on the spurious object recognition rate. The higher the spurious object recognition rate, the higher the comparison priority. In other words, echo features that identify spurious objects at a high frequency correspond to higher comparison priority, which helps to improve the efficiency of liveness detection.

[0095] Step S208: When the liveness detection result indicates that the target is a live person, determine the target identity information corresponding to the target hand based on the current hand image.

[0096] The identity information refers to the user's identity, indicating the user's identity. For example, identity information could be a username, account name, job title, or other information that identifies the user. The target identity information is the user's identity, indicating the user's identity.

[0097] Specifically, when the liveness detection result for the target hand indicates that the hand is alive, the computer device can determine the target identity information corresponding to the target hand based on the current hand image. For example, palmprint and palm vein features are extracted from the current hand image to obtain the current palmprint and palm vein features; from the identity database, registered palmprint and palm vein features that match the current palmprint and palm vein features are identified, and the identity information to which the registered palmprint and palm vein features belong is used as the target identity information corresponding to the target hand. In other words, the palmprint and palm vein features of the current hand image are extracted, and the identity information of users with those palmprint and palm vein features is searched from the identity database as the target identity information corresponding to the target hand.

[0098] Once the target's identity information corresponding to the target's hand is determined, other operations can be performed based on that information. For example, mobile payments can be made based on the target's identity information; access control can be implemented based on the target's identity information; membership registration can be performed based on the target's identity information; data queries can be performed based on the target's identity information; and so on.

[0099] In one embodiment, the computer device is a palm-scanning device. The palm-scanning device acquires the current echo information received when it emits ultrasonic waves towards the target palm, acquires the current palm image obtained by itself from capturing the target palm, generates a current echo feature set based on the current echo information and the corresponding ultrasonic wave emission information, performs liveness detection on the target palm based on the current echo feature set, obtains the liveness detection result corresponding to the target palm, and determines the target identity information corresponding to the target palm based on the current palm image when the liveness detection result indicates that the target is alive.

[0100] In one embodiment, the current echo information and the ultrasonic emission information corresponding to the current echo information are first obtained. After determining that the target hand is a living body based on the current echo information and the ultrasonic emission information, the current hand image is then obtained. Based on the current hand image, the target identity information corresponding to the target hand is determined. This can effectively avoid the waste of computer resources.

[0101] In the aforementioned palm data processing method, the current echo information received from the ultrasonic waves emitted to the target palm by the palm-scanning device is acquired, and the current palm image obtained by capturing the target palm using the palm-scanning device is acquired. Based on the current echo information and the corresponding ultrasonic wave emission information, a current echo feature set is generated. Based on the current echo feature set, a liveness detection is performed on the target palm to obtain the corresponding liveness detection result. If the liveness detection result indicates a live target, the target identity information corresponding to the target palm is determined based on the current palm image. Thus, by emitting ultrasonic waves to the target palm using the palm-scanning device, receiving the echoes, and acquiring palm images, and combining the echo features determined based on the emission and echo information with the palm image for identity recognition, the accuracy of identity recognition can be effectively improved. Ultrasonic waves are not affected by ambient light and have high detection accuracy. The current echo feature set generated based on the current echo information and the corresponding ultrasonic wave emission information includes multiple echo features. Liveness detection based on the current echo feature set can effectively eliminate spurious interference and ensure detection accuracy. When the target hand is confirmed to be alive, identity recognition based on the current hand image can effectively improve the accuracy of identity recognition.

[0102] In one embodiment, a current echo feature set is generated based on the current echo information and the corresponding ultrasonic wave emission information, including:

[0103] Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, the target hand is located, and the first echo feature based on the geometric information of the hand is obtained.

[0104] Based on the data difference between ultrasonic emission information and current echo information, a second echo feature for palm material information is obtained.

[0105] Echo intensity analysis is performed on the current echo information to obtain the third echo characteristics specific to palm tissue information;

[0106] Based on the first echo feature, the second echo feature, and the third echo feature, the current echo feature set is obtained.

[0107] Among these, palm geometric information describes the geometric shape of the palm. For example, palm geometric information can include palm size, palm shape, and other information. The first echo feature for palm geometric information is an echo feature used to reflect the palm geometric information. For example, the first echo feature could be a palm size feature, which indicates the size of the palm.

[0108] Hand material information describes the texture of the material used to make the hand. For example, hand material information could refer to the material used on the surface of the hand. The second echo characteristic for hand material information refers to the echo characteristics used to reflect this information. For example, the second echo characteristic could be the absorption-reflection ratio of ultrasonic waves. Different materials absorb ultrasonic waves differently, and the absorption-reflection ratio can be used to distinguish the material used in the hand.

[0109] Palm tissue information describes the internal structures of the palm. For example, palm tissue information can refer to the internal structure of the palm. The third echo feature for palm tissue information is an echo characteristic used to reflect this information. For example, the third echo feature can be a tissue distribution feature, which indicates the location of different tissues within the palm.

[0110] Echo intensity analysis refers to the analysis of the signal strength of the echo signal.

[0111] Specifically, computer equipment can locate a target hand based on the current echo information and the corresponding ultrasonic wave emission information, obtaining the first echo feature targeting the hand's geometric information. This can be understood as follows: the hand-brushing device emits ultrasonic waves towards the target hand; the ultrasonic waves are emitted by the target hand; and the hand-brushing device receives the echoes. Based on the emission and reception information of the ultrasonic waves, the position and size of the target hand in space can be analyzed. Therefore, based on the current echo information and the corresponding ultrasonic wave emission information, the spatial information of the target hand can be determined, thus obtaining the first echo feature targeting the hand's geometric information. For example, based on the current echo information and the corresponding ultrasonic wave emission information, ultrasonic imaging of the target hand can be performed to obtain an ultrasonic image, and the first echo feature targeting the hand's geometric information can be determined based on the ultrasonic image.

[0112] Computer equipment can obtain a second echo feature specific to the palm material information based on the data difference between the current echo information and the corresponding ultrasonic emission information. For example, based on the current echo information and the corresponding ultrasonic emission information, the absorption-reflection ratio of the ultrasonic wave can be calculated, and this ratio can be used as the second echo feature specific to the palm material information.

[0113] Ultrasound waves propagate, reflect, and are absorbed to varying degrees across different tissues, resulting in differences in echo intensity. Therefore, computer equipment can analyze the current echo information to obtain a third echo characteristic specific to hand tissue information. For example, based on the current echo information, it can analyze whether there are differences in intensity between echoes received at different times, thus obtaining a third echo characteristic specific to hand tissue information.

[0114] Finally, the computer device obtains the current echo feature set based on the first echo feature, the second echo feature, and the third echo feature.

[0115] It is understood that the first echo feature for palm geometry information may include at least one echo feature, the second echo feature for palm material information may include at least one echo feature, and the third echo feature for palm tissue information may include at least one echo feature.

[0116] In the above embodiments, the current echo feature set includes a first echo feature for palm geometry information, a second echo feature for palm material information, and a third echo feature for palm tissue information. The first, second, and third echo features are features of different dimensions, which can reflect information of different dimensions of the palm. Such a current echo feature set contains a rich amount of information. Based on such a current echo feature set, liveness detection of the target palm can effectively improve the accuracy of liveness detection.

[0117] In one embodiment, the current echo feature set may also include at least one of a first echo feature for palm geometry information, a second echo feature for palm material information, and a third echo feature for palm tissue information.

[0118] In one embodiment, besides locating the target hand based on the current echo information and the corresponding ultrasonic wave emission information to obtain the first echo feature for the hand's geometry, the first echo feature for the hand's geometry can also be obtained based solely on the current echo information. That is, the current echo information can be specifically analyzed to obtain the first echo feature for the hand's geometry. For example, the first echo feature for the hand's geometry can be obtained based on the waveform morphology of multiple echo signals in the current echo information.

[0119] In one embodiment, based on the current echo information and the corresponding ultrasonic wave emission information, the target hand is located to obtain a first echo feature based on the hand's geometric information, including:

[0120] Ultrasonic imaging is performed based on the current echo information and the corresponding ultrasonic emission information to obtain an ultrasonic image. Based on the ultrasonic image, the palm size features and palm texture features are obtained.

[0121] Based on the waveform morphology of multiple echo signals in the current echo information, the spatial morphological features of the palm are obtained.

[0122] Based on palm size features, palm texture features, and palm spatial morphology features, the first echo feature for palm geometric information is obtained.

[0123] The palm-swiping device can simultaneously emit multiple ultrasonic signals towards the target palm, and correspondingly, it can receive multiple echo signals. Ultrasonic imaging refers to the process of processing and reconstructing the emitted and received ultrasonic signals to obtain a visualized image.

[0124] Hand size features reflect the size information of the hand. Hand size features can be used to distinguish between a prosthetic hand and a real hand, and also to distinguish between the real hands of different users. For example, if the hand size does not match the size of a real hand, the liveness detection result is determined to be a prosthetic. Hand texture features reflect the texture information of the hand. For example, hand texture features can reflect the roughness of the hand; it can be understood that the echoes reflected back from ultrasonic waves emitted to hands with different roughnesses are different. Hand texture features can be used to distinguish between a prosthetic hand and a real hand. For example, if the roughness of the hand does not match the roughness of a real hand, the liveness detection result is determined to be a prosthetic. Hand spatial morphology features reflect the spatial morphology of the hand. Spatial morphology is divided into planar morphology and three-dimensional morphology. Hand spatial morphology features can be used to distinguish between a prosthetic hand and a real hand. If the hand has a planar morphology, the liveness detection result is determined to be a prosthetic.

[0125] Specifically, computer equipment can perform ultrasonic imaging based on the current echo information and the corresponding ultrasonic wave emission information to obtain an ultrasonic image of the target hand. This ultrasonic image can visually reflect the geometric information of the target hand. Hand size features can be obtained by identifying the size of the target hand from the ultrasonic image, and hand texture features can be obtained by identifying the texture of the target hand from the ultrasonic image. For example, hand texture features can be obtained based on the reflectivity of the ultrasonic image; the smoother the hand surface, the greater the reflectivity of the ultrasonic image.

[0126] Furthermore, the computer equipment can analyze the waveform morphology of each echo signal in the current echo information to obtain the spatial morphological characteristics of the palm. For example, by comparing the waveform morphologies of different echo signals, if a large proportion of the echo signals have similar waveform morphologies, the palm spatial morphological characteristics are determined to be planar; otherwise, they are determined to be three-dimensional. Similarly, if a large proportion of the echo signals have simple and regular waveforms, the palm spatial morphological characteristics are determined to be planar; if a large proportion of the echo signals have complex and varied waveforms, they are determined to be three-dimensional.

[0127] Ultimately, computer devices can use palm size features, palm texture features, and palm spatial shape features as the first echo features for palm geometric information.

[0128] In the above embodiments, the first echo features for palm geometric information include palm size features, palm texture features, and palm spatial shape features. Different first echo features can reflect the geometric information of the palm in different dimensions. Based on multiple first echo features, liveness detection of the target palm can effectively improve the accuracy of liveness detection.

[0129] In one embodiment, a second echo feature for the hand material information is obtained based on the data difference between the ultrasonic wave emission information and the current echo information, including:

[0130] The absorption-reflection ratio of the ultrasonic wave is calculated based on the ultrasonic wave emission information and the current echo information.

[0131] The absorption-reflectance ratio is used as the second echo characteristic for palm material information.

[0132] The absorption-reflection ratio of ultrasound refers to the proportion of energy absorbed and reflected during the propagation of ultrasound to the total emitted energy.

[0133] Specifically, computer equipment can calculate the absorption-reflection ratio of ultrasonic waves based on the emitted and current echo information, using this ratio as a second echo characteristic for the palm's material information. Three-dimensional prostheses are generally made of silicone. Silicone and skin have significant differences in their ultrasonic wave absorption-reflection ratios. Therefore, based on the ultrasonic wave absorption-reflection ratio, it's possible to distinguish whether the target palm's epidermis is skin. If the target palm's epidermis is not skin, then the corresponding liveness detection result indicates that the target palm is a prosthesis.

[0134] In the above embodiments, the absorption and reflection ratio of ultrasound is calculated based on the ultrasonic emission information and the current echo information. The absorption and reflection ratio of ultrasound is used as the second echo feature for the material information of the palm. The absorption and reflection ratio of ultrasound can easily distinguish the material between a fake palm and a real palm, which helps to improve the efficiency of liveness detection.

[0135] In one embodiment, echo intensity analysis is performed on the current echo information to obtain a third echo feature specific to the palm tissue information, including:

[0136] By comparing the signal strengths of multiple echo signals in the current echo information, the characteristics of echo strength distribution and echo strength ratio are obtained.

[0137] Based on the signal strength, receiving location, and receiving time of multiple echo signals in the current echo information, the target hand is divided into tissues to obtain tissue distribution characteristics.

[0138] Based on at least one of the echo intensity distribution characteristics, echo intensity ratio characteristics, and tissue distribution characteristics, a third echo feature for palm tissue information is obtained.

[0139] Among these, the echo intensity distribution characteristic indicates whether there are differences in the intensity of the echo signal. The echo intensity ratio characteristic indicates the ratio of the intensity of the echo signal. The tissue distribution characteristic indicates the location of tissues in the palm.

[0140] Specifically, refer to Figure 4 The interior of a real hand contains various tissues, formed by the epidermis, fat, muscle, blood vessels, and bones sequentially surrounding it. During the transmission of ultrasound waves within the hand, different types of tissues will produce echoes of varying intensities. Therefore, by extracting the third echo features specific to the hand's tissues, we can determine whether the target hand possesses the tissue characteristics of a real hand.

[0141] Computer equipment can compare the signal strengths of multiple echo signals in the current echo information to obtain echo strength distribution characteristics and echo strength ratio characteristics. For example, if the intensity difference between multiple echo signals in the current echo information is less than a preset threshold, the echo strength distribution characteristic is determined to be a single intensity distribution characteristic; otherwise, it is determined to be a multiple intensity distribution characteristic. Another example is calculating the ratio between echo signals with signal strengths higher than a first threshold and echo signals with signal strengths lower than a second threshold to obtain the echo strength ratio characteristic, where the first threshold is greater than or equal to the second threshold. Furthermore, computer equipment can also extract spatiotemporal variation information of echo intensity based on the signal strength, receiving location, and receiving time of multiple echo signals in the current echo information. Tissues at different depths will produce echoes of different intensities, and tissues at different locations within the same depth may also produce echoes of different intensities. Therefore, tissue distribution characteristics can be obtained based on the spatiotemporal variation information of echo intensity. Based on the spatiotemporal variation information of echo intensity, the target hand is divided into tissue regions, revealing the location of each tissue within the hand. The tissue distribution characteristics are then derived from these regions. Each tissue region exhibits a stable signal intensity with minimal fluctuations.

[0142] Ultimately, the computer device obtains a third echo feature for palm tissue information based on at least one of the echo intensity distribution characteristics, echo intensity ratio characteristics, and tissue distribution characteristics.

[0143] In the above embodiments, the third echo feature for palm tissue information includes at least one of echo intensity distribution feature, echo intensity ratio feature, and tissue distribution feature. Different third echo features can reflect the tissue information of the palm from different perspectives. Based on the third echo feature, liveness detection of the target palm can effectively improve the accuracy of liveness detection.

[0144] In a specific application, refer to Figure 5 The echo feature set includes the spatial morphological features of the palm, the absorption and reflection ratio of ultrasound waves, the echo intensity distribution characteristics, the echo intensity ratio characteristics, and the tissue distribution characteristics. The palm-brushing device emits ultrasound waves into the palm, receives the echoes, and analyzes the echoes to obtain the echo feature set. Based on the waveform morphology of multiple echo signals, the spatial morphological features of the palm are obtained; based on the transmission and reception information of ultrasound waves, the absorption and reflection ratio of ultrasound waves is obtained; by comparing the signal intensities of multiple echo signals in the current echo information, the echo intensity distribution characteristics and echo intensity ratio characteristics are obtained; and based on the signal intensity, reception location, and reception time of multiple echo signals in the current echo information, the target palm is divided into tissues to obtain the tissue distribution characteristics.

[0145] In one embodiment, liveness detection of the target hand is performed based on the current echo feature set to obtain the liveness detection result corresponding to the target hand, including:

[0146] Obtain the spatial morphological features of the palm from the current echo feature set;

[0147] When the spatial morphological features of the palm belong to planar morphological features, the liveness detection result corresponding to the target palm is determined to be a prosthesis;

[0148] When the spatial morphological features of the palm belong to the three-dimensional morphological features, the other features in the current echo feature set are compared with the reference echo feature set corresponding to the real palm to obtain the liveness detection result corresponding to the target palm.

[0149] Among them, planar morphological features represent the reflected echo characteristics of a planar object. Three-dimensional morphological features represent the reflected echo characteristics of a three-dimensional object. Planar morphological features are spatial morphological features of an object generated based on the echo information obtained from the reflection of ultrasonic waves by a planar object. Three-dimensional morphological features are spatial morphological features of an object generated based on the echo information obtained from the reflection of ultrasonic waves by a three-dimensional object.

[0150] A real hand refers to the hand of a real user. The reference echo feature set corresponding to a real hand is generated based on the echo information obtained by reflecting ultrasound waves from a real hand.

[0151] Specifically, the computer device can effectively identify whether a target hand is forged from a photograph, quickly filtering out fake hands created from photographs. The current echo feature set includes at least two echo features, one of which is the spatial morphological feature of the hand. The computer device can acquire the spatial morphological feature of the hand from the current echo feature set, and determine whether the target hand is a planar or three-dimensional object based on the spatial morphological feature. If the target hand is a planar object, the corresponding liveness detection result is determined to be a fake. The computer device can acquire both planar and three-dimensional morphological features, and compare the hand's spatial morphological feature with the planar and three-dimensional morphological features. When the hand's spatial morphological feature belongs to the planar morphological feature, the corresponding liveness detection result is determined to be a fake. When the hand's spatial morphological feature belongs to the three-dimensional morphological feature, other features in the current echo feature set are compared with the reference echo feature set corresponding to the real hand to obtain the corresponding liveness detection result for the target hand. For example, the feature similarity between the spatial morphological features and the planar morphological features of the palm can be calculated. If the feature similarity is greater than the similarity threshold, the spatial morphological features of the palm are determined to be planar morphological features. If the feature similarity is less than or equal to the similarity threshold, the spatial morphological features of the palm are determined to be three-dimensional morphological features.

[0152] In one embodiment, the current echo feature set includes not only the spatial morphological features of the palm but also at least two other echo features. Based on the comparison priority of the echo features, other features in the current echo feature set corresponding to the target palm are compared with the corresponding features in the reference echo feature set corresponding to the real palm. If, based on a comparison result, it is determined that the liveness detection result corresponding to the target palm belongs to a prosthesis, the comparison can be stopped, and no further feature comparison is needed.

[0153] In the above embodiments, liveness detection is first performed based on the spatial morphological features of the palm, which can quickly identify palms forged from planar objects. After determining that the target palm is not a planar object, other echo features of the target palm are further compared with the echo features of a real palm to determine whether the target palm is a real palm.

[0154] In one embodiment, the current echo feature set further includes a second echo feature for palm material information and a third echo feature for palm tissue information, and the reference echo feature set includes a reference echo feature range for palm material information and a reference echo feature range for palm tissue information.

[0155] The other features in the current echo feature set are compared with the reference echo feature set corresponding to the real hand to obtain the liveness detection result corresponding to the target hand, including:

[0156] The range of the second echo feature for palm material information and the range of the reference echo feature for palm material information are compared.

[0157] When the second echo feature for palm material information falls within the reference echo feature range for palm material information, the third echo feature for palm tissue information is compared with the reference echo feature range for palm tissue information.

[0158] When the third echo feature of palm tissue information falls within the reference echo feature range of palm tissue information, the liveness detection result corresponding to the target palm is determined to be a live body.

[0159] If any comparison result is not within the corresponding reference echo feature range, the liveness detection result corresponding to the target hand is determined to be a prosthesis.

[0160] The reference echo feature range for hand material information refers to the range of features of a real hand on the echo features corresponding to hand material information. The reference echo feature range for hand tissue information refers to the range of features of a real hand on the echo features corresponding to hand tissue information. It's understandable that different users' hands are different; therefore, the echo features of a real hand are not fixed, and different users' hands will show differences in the same type of echo feature. Various reference echo feature ranges can be set as needed. For example, statistical analysis of a large amount of real hand echo information can yield various reference echo feature ranges.

[0161] Specifically, the current echo feature set corresponding to the target hand includes a first echo feature for hand geometry, a second echo feature for hand material information, and a third echo feature for hand tissue information. The first echo feature includes the hand's spatial morphological features. The reference echo feature set corresponding to the real hand includes a reference echo feature range for hand material information and a reference echo feature range for hand tissue information. When the target hand's spatial morphological features belong to three-dimensional morphological features, the computer device first compares the second echo feature for hand material information with the reference echo feature range for hand material information. If the second echo feature for hand material information does not belong to the reference echo feature range for hand material information, the liveness detection result corresponding to the target hand is determined to be a prosthesis; if the second echo feature for hand material information belongs to the reference echo feature range for hand material information, the third echo feature for hand tissue information is further compared with the reference echo feature range for hand tissue information. For example, the second echo feature for palm material information includes the absorption-reflectance ratio of ultrasound waves. If the absorption-reflectance ratio of the target palm is outside the reference range, the corresponding liveness detection result is determined to be a prosthesis. Similarly, if the third echo feature for palm tissue information is not within the reference echo feature range for palm tissue information, the corresponding liveness detection result is determined to be a prosthesis; if the third echo feature for palm tissue information is within the reference echo feature range, the corresponding liveness detection result is determined to be a live hand. For instance, the third echo feature for palm tissue information includes echo intensity ratio characteristics. If the echo intensity ratio characteristic of the target palm is outside the reference echo intensity ratio characteristic range, the corresponding liveness detection result is determined to be a prosthesis.

[0162] In the above embodiments, compared with the third echo feature targeting palm tissue information, the second echo feature targeting palm material information has lower computational complexity or fewer features. First, the second echo feature targeting palm material information is compared with the reference echo feature range targeting palm material information to determine whether the target palm is a prosthesis. Once the liveness detection result corresponding to the target palm is determined to be a prosthesis, the data comparison can be stopped, which helps improve the efficiency of liveness detection. If the second echo feature targeting palm material information falls within the reference echo feature range targeting palm material information, then the third echo feature targeting palm tissue information is further compared with the reference echo feature range targeting palm tissue information. Determining the liveness detection result through comparison of multiple echo features helps improve the accuracy of liveness detection.

[0163] In one embodiment, the second echo feature for palm material information includes echo strength distribution feature, echo strength ratio feature, and tissue distribution feature, and the reference echo feature range for palm tissue information includes reference strength distribution feature range, reference strength ratio feature range, and reference tissue distribution feature range.

[0164] The third echo feature for palm tissue information and the reference echo feature range for palm tissue information are compared, including:

[0165] Compare the echo strength distribution characteristics with the reference strength distribution characteristics range;

[0166] When the echo strength distribution characteristics fall within the range of the reference strength distribution characteristics, the echo strength ratio characteristics are compared with the range of the reference strength ratio characteristics.

[0167] When the echo intensity ratio characteristic falls within the range of the reference intensity ratio characteristic, the tissue distribution characteristic is compared with the range of the reference tissue distribution characteristic.

[0168] Among them, the reference strength distribution characteristic range refers to the characteristic range of the actual palm in terms of echo strength distribution characteristics. The reference strength ratio characteristic range refers to the characteristic range of the actual palm in terms of echo strength ratio characteristics. The reference tissue distribution characteristic range refers to the characteristic range of the actual palm in terms of tissue distribution characteristics.

[0169] Specifically, the second echo features for palm material information include echo intensity distribution features, echo intensity ratio features, and tissue distribution features. In order to improve the detection efficiency of liveness detection, the features can be compared in a certain order.

[0170] The computer equipment first compares the echo intensity distribution characteristics with a reference intensity distribution characteristic range. If the echo intensity distribution characteristics do not fall within the reference range, the liveness detection result for the target hand is determined to be a prosthesis. If the echo intensity distribution characteristics fall within the reference range, the equipment further compares the echo intensity ratio characteristics with the reference ratio range. If the echo intensity ratio characteristics do not fall within the reference range, the liveness detection result for the target hand is determined to be a prosthesis. If the echo intensity ratio characteristics fall within the reference range, the equipment further compares the tissue distribution characteristics with a reference tissue distribution characteristic range. If the tissue distribution characteristics do not fall within the reference range, the liveness detection result for the target hand is determined to be a prosthesis. If the tissue distribution characteristics fall within the reference range, the liveness detection result for the target hand is determined to be a live organ.

[0171] In the above embodiments, the second echo features for palm material information include echo intensity distribution features, echo intensity ratio features, and tissue distribution features. The echo intensity distribution features, echo intensity ratio features, and tissue distribution features are progressively compared in distinguishing between real and fake hands. First, the echo intensity distribution features are compared, then the echo intensity ratio features are compared, and finally the tissue distribution features are compared, which helps to improve the detection efficiency and accuracy of liveness detection.

[0172] In a specific application, refer to Figure 6 The current echo feature set corresponding to the target hand includes the spatial morphological features of the hand, the absorption and reflection ratio of ultrasound waves, the echo intensity distribution characteristics, the echo intensity ratio characteristics, and the tissue distribution characteristics. When performing liveness detection on the target hand based on the current echo feature set, the spatial morphological features of the hand are first used to determine whether the target hand is a planar object. If the target hand is a planar object, it is determined to be a dummy hand. If the target hand is not a planar object, the absorption and reflection ratio of ultrasound waves is further used to determine whether it matches the absorption and reflection ratio of ultrasound waves by the skin. If the absorption and reflection ratio of ultrasound waves by the target hand does not match the absorption and reflection ratio of ultrasound waves by the skin, it is determined to be a dummy hand. If the absorption and reflection ratio of ultrasound waves by the target hand matches the absorption and reflection ratio of ultrasound waves by the skin, the echo intensity distribution characteristics are further used to determine whether it is a single intensity. If the echo intensity distribution characteristics are a single intensity, the target hand is determined to be a dummy hand. If the echo intensity distribution characteristics are not a single intensity, the echo intensity ratio characteristics are further used to determine whether it matches the echo intensity ratio of a real hand. If the echo intensity ratio does not match that of a real hand, the target hand is determined to be a fake hand. If the echo intensity ratio matches that of a real hand, then the tissue distribution characteristics are further used to determine whether it matches the tissue distribution of a real hand. If the tissue distribution characteristics do not match that of a real hand, the target hand is determined to be a fake hand; if the tissue distribution characteristics match that of a real hand, the target hand is determined to be a real hand.

[0173] In one embodiment, determining the target identity information corresponding to the target hand based on the current hand image includes:

[0174] Determine the initial identity information corresponding to the target hand based on the current hand image;

[0175] Obtain the historical echo feature set corresponding to the initial identity information;

[0176] Based on the historical echo feature set, the current echo feature set is used to verify the identity and obtain the identity verification result.

[0177] When the identity verification result is a match, the initial identity information is used as the target identity information corresponding to the target hand.

[0178] The initial identity information corresponding to the target palm is derived from the image features of the current palm image. The historical echo feature set corresponding to the initial identity information refers to the echo feature set determined by the user corresponding to the initial identity information through palm swiping within a historical time period. For example, based on the current palm image corresponding to the target palm, the identity information of user A is found as the initial identity information, and the echo feature set determined by user A in the last palm swiping is obtained as the historical echo feature set corresponding to the initial identity information; or, the echo feature set determined by user A when registering the palm is obtained as the historical echo feature set corresponding to the initial identity information. It can be understood that the current echo feature set is the echo feature set determined by the current palm swiping.

[0179] Identity verification refers to checking whether the current echo feature set belongs to the user corresponding to the initial identity information. Identity verification results are divided into identity matching and identity mismatch. Identity matching indicates that the current echo feature set belongs to the user corresponding to the initial identity information. Identity mismatch indicates that the current echo feature set does not belong to the user corresponding to the initial identity information.

[0180] Specifically, the current echo feature set can be used not only for liveness detection but also for identity verification to avoid identification errors. When the computer device determines that the target hand is a real hand, it first searches the identity database for matching identity information based on the current hand image to obtain the initial identity information corresponding to the target hand. Then, it acquires the historical echo feature set corresponding to the initial identity information. Based on the historical echo feature set, it performs identity verification against the current echo feature set to obtain the identity verification result. If the identity verification result is a match, the initial identity information is used as the target identity information corresponding to the target hand. If the identity verification result is a mismatch, ultrasound waves can be re-emitted to the target hand to generate a new echo feature set, and the target hand image can be re-acquired to obtain a new hand image for re-identification. Even if the identity verification result is a mismatch, the identity verification result can still be displayed to the user who swiped their hand.

[0181] In the above embodiments, the initial identity information corresponding to the target hand is determined based on the current hand image, and the historical echo feature set corresponding to the initial identity information is obtained. Based on the historical echo feature set, the current echo feature set is used for identity verification to obtain the identity verification result. When the identity verification result is a match, the initial identity information is used as the target identity information corresponding to the target hand. Adding an identity verification step to the surrounding recognition process can improve the accuracy of identity recognition. The initial identity information is only used as the target identity information when both the current hand image and the current echo feature set are associated with it, which can avoid identity recognition errors.

[0182] In one embodiment, determining the initial identity information corresponding to the target hand based on the current hand image includes:

[0183] Extract palm print and palm vein features from the current palm image to obtain the current palm print and palm vein features;

[0184] From the identity database, identify the registered palm print and palm vein features that match the current palm print and palm vein features, and use the identity information to which the registered palm print and palm vein features belong as the initial identity information corresponding to the target palm.

[0185] Among them, palm print and palm vein features are features that reflect the palm print and palm vein information on the palm. Current palm print and palm vein features are those extracted from the current palm image; that is, they are the palm print and palm vein features extracted from the current palm image of the user who registered. Registered palm print and palm vein features are those extracted from the palm image of the registered user when the user registers their palm.

[0186] The identity database includes user information for multiple registered users. This user information includes the user's identity information and the user's registered palm print and palm vein characteristics.

[0187] Specifically, the computer device can extract palmprint and palm vein features from the current palm image to obtain the current palmprint and palm vein features. Based on the current palmprint and palm vein features, it searches the identity database for matching registered palmprint and palm vein features, obtains the identity information to which the searched registered palmprint and palm vein features belong, and uses this identity information as the initial identity information corresponding to the target palm. For example, it calculates the feature similarity between the current palmprint and palm vein features and each registered palmprint and palm vein feature in the identity database, and selects the registered palmprint and palm vein features with the highest similarity value (greater than a similarity threshold) as the matching registered palmprint and palm vein features.

[0188] In the above embodiments, palm print and palm vein features are extracted from the current palm image. Palm print and palm vein features are biometric features with high security. Obtaining the initial identity information corresponding to the target palm through palm print and palm vein features can ensure the accuracy of identity recognition based on the current palm image.

[0189] In one embodiment, identity verification is performed on the current echo feature set based on the historical echo feature set to obtain the identity verification result, including:

[0190] Calculate the feature similarity between the current echo feature set and the historical echo feature set;

[0191] When the feature similarity is less than the similarity threshold, the identity verification result is determined to be an identity match;

[0192] When the feature similarity is greater than or equal to the similarity threshold, the identity verification result is determined to be an identity mismatch.

[0193] Specifically, when verifying identity based on the current echo feature set using the historical echo feature set, the computer device can calculate the feature similarity between the historical echo feature set and the current echo feature set, compare the feature similarity with a similarity threshold, and determine that the identity verification result is an identity match if the feature similarity is less than the similarity threshold; otherwise, determine that the identity verification result is an identity mismatch if the feature similarity is greater than or equal to the similarity threshold.

[0194] It's understandable that when calculating the feature similarity between the current echo feature set and the historical echo feature set, at least one echo feature can be obtained from each set to calculate the feature similarity between the two sets. For example, tissue distribution features can be obtained from both the current and historical echo feature sets to calculate feature similarity, as the tissue distribution of the hands differs among different users. Similarly, hand size features can be obtained from both the current and historical echo feature sets to calculate feature similarity, as the hand sizes of different users also differ.

[0195] In one embodiment, during identity verification, the feature similarity between the current echo feature set corresponding to the target hand and the historical echo feature set corresponding to the initial identity information is compared with a first similarity threshold. During liveness detection, the feature similarity between the current echo feature set corresponding to the target hand and the reference echo feature set corresponding to the real hand is compared with a second similarity threshold. The first similarity threshold is greater than the second similarity threshold. By increasing the strictness of identity verification, identity recognition errors are further avoided.

[0196] In the above embodiments, the feature similarity between the current echo feature set and the historical echo feature set is calculated, and the feature similarity is compared with the similarity threshold to quickly determine the identity verification result.

[0197] In one embodiment, the palm-swiping device is a palm-swiping payment device, which includes an image acquisition unit, an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix deployed around the image acquisition unit.

[0198] The palm-scanning payment device is a payment device that scans the user's palm for payment. Traditional palm-scanning payment devices do not typically include an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix. However, the palm-scanning payment device of this application includes not only an image acquisition unit but also an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix deployed around the image acquisition unit. The image acquisition unit is used to acquire images. The ultrasonic transmitting unit matrix is ​​an array of multiple ultrasonic transmitting units (i.e., ultrasonic transmitters), which emit ultrasonic waves. The ultrasonic transmitting unit matrix allows for better beamforming and directional control of the ultrasonic waves. The ultrasonic receiving unit matrix is ​​an array of multiple ultrasonic receiving units (i.e., ultrasonic receivers), which receive reflected ultrasonic waves, i.e., echoes. The ultrasonic receiving unit matrix allows for better beamforming of the echoes. For example, see reference... Figure 7 The palm payment device includes a palm module (i.e., an image acquisition unit). An ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix are added around the palm module. The ultrasonic transmitting unit matrix emits ultrasonic waves from various angles toward the palm. When the ultrasonic waves come into contact with the palm, they are reflected by the palm. However, due to the differences in the surface texture, shape, size, posture, and internal tissue of the palm, the echo will change and be received by the ultrasonic receiving unit matrix. By analyzing the echo, it can be identified whether the palm is the real user's palm.

[0199] It is understandable that ultrasonic transducers can be used to deploy ultrasonic transmitting unit matrices and ultrasonic receiving unit matrices. Ultrasonic transducers are transducers that realize the conversion between acoustic energy and electrical energy within the ultrasonic frequency range. They are mainly divided into three categories: transmitters, receivers, and transceiver transducers. A transducer used to emit ultrasonic waves is called a transmitter. When the transducer is in the transmitting state, it converts electrical energy into mechanical energy, and then into acoustic energy. A transducer used to receive sound waves is called a receiver. When the transducer is in the receiving state, it converts acoustic energy into mechanical energy, and then into electrical energy. In some cases, a transducer can be used as both a transmitter and a receiver; this is called a transceiver transducer. Based on the different physical effects that achieve the electromechanical conversion of ultrasonic transducers, they can be classified into electrodynamic, electromagnetic, magnetostrictive, piezoelectric, and electrostrictive types, etc.

[0200] Specifically, the palm-swipe payment device emits ultrasonic waves towards the target hand via an ultrasonic transmitting unit matrix, obtaining ultrasonic emission information. It then receives the echoes via an ultrasonic receiving unit matrix, obtaining current echo information. Finally, it captures an image of the target hand using an image acquisition unit. Based on the current echo information and the corresponding ultrasonic emission information, the device generates a current echo feature set. It then performs liveness detection on the target hand based on this feature set, obtaining a liveness detection result. If the liveness detection result indicates a live hand, the device determines the target's identity information based on the current hand image and performs payment based on that identity information. For example, it obtains the payment code corresponding to the target's identity information and performs payment based on that code.

[0201] It's understandable that, besides palm-swipe payment devices, other palm-swipe payment devices could also adopt a similar structure.

[0202] In the above embodiments, the method of this application can be applied to the scenario of palm payment, thereby improving the security of palm payment by improving the accuracy of identity recognition.

[0203] In one specific embodiment, the method of this application can be applied to a palm-swipe payment device. An ultrasonic module (an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix) is added around the palm-swipe module of the palm-swipe payment device to form an ultrasonic palm-swipe module. Ultrasonic waves are emitted from various angles towards the palm through the ultrasonic transmitting unit matrix. When the ultrasonic waves come into contact with the palm, they are reflected. However, due to differences in the texture, shape, size, and posture of the palm surface, the reflected ultrasonic echoes will vary and be received by the ultrasonic receiving unit matrix. The positional differences within the ultrasonic receiving unit matrix and the proportion of sound waves received at different times and frequency bands can be used to create an ultrasonic image of the palm. Furthermore, since the ratio of ultrasonic waves penetrating and reflecting from the palm varies at different frequencies, and different conditions of the palm's epidermis and tissues can also cause changes in the ultrasonic reflection state, the echo features can be used for liveness detection during palm-swipe payment. Combining echo features and image features can improve the payment accuracy and security of the palm-swipe payment device.

[0204] refer to Figure 8When a hand approaches the ultrasonic palm-scanning module of the palm-scanning payment device, the module emits ultrasonic waves towards the hand and receives the echoes reflected back. The echoes are analyzed to determine if the hand is genuine. If the hand is displayed on a monitor or printed image, the echo will show obvious planar reflection characteristics (i.e., planar morphological characteristics), indicating a fake hand. If the echo shows multiple reflection characteristics (i.e., three-dimensional morphological characteristics), further analysis is performed using the biological and anatomical features of a real hand to determine if it is a fake hand. First, the absorption and reflection ratio of the ultrasonic waves is calculated and compared with the absorption and reflection ratio of the skin to determine if it matches the ultrasonic characteristics of the skin epidermis. If it does not match, the hand is considered fake; otherwise, the next step is performed. The echo intensity characteristics (i.e., the distribution of echo strength) are checked. A hand typically contains bones, muscles, blood vessels, and fat, resulting in varying reflection intensities rather than a single intensity. If the echo intensity distribution of the hand shows a single intensity characteristic, the hand is considered fake; otherwise, the next step is performed. Because the proportions of bones, muscles, soft tissues, and blood vessels in a real hand are relatively fixed, the intensity ratio of the echoes is also relatively fixed. If the intensity ratio of the palm's echoes deviates significantly from that of a real hand, the hand is determined to be a sham; otherwise, the next step is taken. Finally, since the palm is covered by epidermis, fat, muscle, blood vessels, and bones in sequence, the timing of echoes of different intensities also differs. Therefore, the tissue distribution of the palm can be determined based on the echo distribution. If the tissue distribution of the palm deviates significantly from that of a real hand, the hand is determined to be a sham; otherwise, the hand is determined to be a real hand. In the method of this application, liveness detection using ultrasound does not occupy optical module space, is unaffected by complex ambient light, provides rich echo features, and has high detection accuracy.

[0205] It's understandable that, because bones are located at the innermost part of the palm and have a higher density, ultrasound waves are reflected at their tissue interface, creating a high-energy reflection zone. This zone is easily distinguishable from muscles and soft tissues, with clear boundaries and distinct differences. The muscles in the palm, due to their denser tissue, form a medium-energy reflection zone along with the soft tissues, occupying a relatively larger proportion and area within the palm. As for fat, in most people's palms, fat is concentrated in only a few specific locations, with relatively loose tissue and weak echo intensity. Finally, the blood vessels in the palm produce a Doppler effect on ultrasound waves due to blood flow, resulting in specific echo patterns as ultrasound waves reflect at the interface between the vessel wall and the blood. Therefore, the distribution of these echoes can help identify whether the palm is a real hand.

[0206] After confirming the hand is genuine, the ultrasonic palm-scanning module optically captures an image of the user's hand. After grayscale processing, the image extracts palm print and vein features (e.g., primary texture, secondary texture, bifurcation, texture width, etc.). These extracted features are compared with user information in an identity database to ultimately identify the user of the palm-scanning payment device. Once the user's identity is confirmed, their payment code can be retrieved to complete the payment.

[0207] refer to Figure 9 You can set up a palm payment device using the method described in this application in the store. When a user needs to make a palm payment, the palm payment device first uses ultrasound to determine whether the user's palm is a real hand. If it is a real hand, then the payment is made based on the user's palm image.

[0208] In one specific embodiment, the method of this application can be applied to a palm-swipe access control device. When a user wants to enter a venue or area, the user swipes their palm onto the device. The ultrasonic palm-swipe module in the device emits ultrasonic waves towards the palm and receives the echoes reflected back from the palm. The echoes are analyzed to determine if the palm is genuine. After confirming the palm is genuine, the ultrasonic palm-swipe module identifies the user by acquiring an image of the palm. If the user's identity meets the requirements, the user is allowed to enter the venue or area. For example, refer to... Figure 10 The palm-scanning access management device can be an access gate that supports palm scanning, which opens the gate when the user's identity meets the requirements.

[0209] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0210] Based on the same inventive concept, this application also provides a palm data processing device for implementing the palm data processing method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more palm data processing device embodiments provided below can be found in the limitations of the palm data processing method described above, and will not be repeated here.

[0211] In one embodiment, such as Figure 11 As shown, a palm data processing device is provided, including: a data acquisition module 1102, a feature generation module 1104, a liveness detection module 1106, and an identity determination module 1108, wherein:

[0212] The data acquisition module 1102 is used to acquire the current echo information received by the ultrasonic waves emitted to the target palm through the palm brushing device, and to acquire the current palm image obtained by the palm brushing device from the target palm.

[0213] The feature generation module 1104 is used to generate a current echo feature set based on the current echo information and the ultrasonic emission information corresponding to the current echo information.

[0214] The liveness detection module 1106 is used to perform liveness detection on the target hand based on the current echo feature set, and obtain the liveness detection result corresponding to the target hand.

[0215] The identity determination module 1108 is used to determine the target identity information corresponding to the target hand based on the current hand image when the liveness detection result indicates that the target is a live person.

[0216] In one embodiment, the feature generation module 1104 is further configured to:

[0217] Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, the target hand is located, and the first echo feature based on the geometric information of the hand is obtained.

[0218] Based on the data difference between ultrasonic emission information and current echo information, a second echo feature for palm material information is obtained.

[0219] Echo intensity analysis is performed on the current echo information to obtain the third echo characteristics specific to palm tissue information;

[0220] Based on the first echo feature, the second echo feature, and the third echo feature, the current echo feature set is obtained.

[0221] In one embodiment, the feature generation module 1104 is further configured to:

[0222] Ultrasonic imaging is performed based on the current echo information and the corresponding ultrasonic emission information to obtain an ultrasonic image. Based on the ultrasonic image, the palm size features and palm texture features are obtained.

[0223] Based on the waveform morphology of multiple echo signals in the current echo information, the spatial morphological features of the palm are obtained.

[0224] Based on palm size features, palm texture features, and palm spatial morphology features, the first echo feature for palm geometric information is obtained.

[0225] In one embodiment, the feature generation module 1104 is further configured to:

[0226] The absorption-reflection ratio of the ultrasonic wave is calculated based on the ultrasonic wave emission information and the current echo information.

[0227] The absorption-reflectance ratio is used as the second echo characteristic for palm material information.

[0228] In one embodiment, the feature generation module 1104 is further configured to:

[0229] By comparing the signal strengths of multiple echo signals in the current echo information, the characteristics of echo strength distribution and echo strength ratio are obtained.

[0230] Based on the signal strength, receiving location, and receiving time of multiple echo signals in the current echo information, the target hand is divided into tissues to obtain tissue distribution characteristics.

[0231] Based on at least one of the echo intensity distribution characteristics, echo intensity ratio characteristics, and tissue distribution characteristics, a third echo feature for palm tissue information is obtained.

[0232] In one embodiment, the liveness detection module 1106 is further configured to:

[0233] Obtain the spatial morphological features of the palm from the current echo feature set;

[0234] When the spatial morphological features of the palm belong to planar morphological features, the liveness detection result corresponding to the target palm is determined to be a prosthesis;

[0235] When the spatial morphological features of the palm belong to the three-dimensional morphological features, the other features in the current echo feature set are compared with the reference echo feature set corresponding to the real palm to obtain the liveness detection result corresponding to the target palm.

[0236] In one embodiment, the current echo feature set further includes a second echo feature for palm material information and a third echo feature for palm tissue information, and the reference echo feature set includes a reference echo feature range for palm material information and a reference echo feature range for palm tissue information. The liveness detection module 1106 is also used for:

[0237] The range of the second echo feature for palm material information and the range of the reference echo feature for palm material information are compared.

[0238] When the second echo feature for palm material information falls within the reference echo feature range for palm material information, the third echo feature for palm tissue information is compared with the reference echo feature range for palm tissue information.

[0239] When the third echo feature of palm tissue information falls within the reference echo feature range of palm tissue information, the liveness detection result corresponding to the target palm is determined to be a live body.

[0240] If any comparison result is not within the corresponding reference echo feature range, the liveness detection result corresponding to the target hand is determined to be a prosthesis.

[0241] In one embodiment, the second echo feature for palm material information includes echo intensity distribution features, echo intensity ratio features, and tissue distribution features; the reference echo feature range for palm tissue information includes a reference intensity distribution feature range, a reference intensity ratio feature range, and a reference tissue distribution feature range. The liveness detection module 1106 is also used for:

[0242] Compare the echo strength distribution characteristics with the reference strength distribution characteristics range;

[0243] When the echo strength distribution characteristics fall within the range of the reference strength distribution characteristics, the echo strength ratio characteristics are compared with the range of the reference strength ratio characteristics.

[0244] When the echo intensity ratio characteristic falls within the range of the reference intensity ratio characteristic, the tissue distribution characteristic is compared with the range of the reference tissue distribution characteristic.

[0245] In one embodiment, the identity determination module 1108 is further configured to:

[0246] Determine the initial identity information corresponding to the target hand based on the current hand image;

[0247] Obtain the historical echo feature set corresponding to the initial identity information;

[0248] Based on the historical echo feature set, the current echo feature set is used to verify the identity and obtain the identity verification result.

[0249] When the identity verification result is a match, the initial identity information is used as the target identity information corresponding to the target hand.

[0250] In one embodiment, the identity determination module 1108 is further configured to:

[0251] Extract palm print and palm vein features from the current palm image to obtain the current palm print and palm vein features;

[0252] From the identity database, identify the registered palm print and palm vein features that match the current palm print and palm vein features, and use the identity information to which the registered palm print and palm vein features belong as the initial identity information corresponding to the target palm.

[0253] In one embodiment, the identity determination module 1108 is further configured to:

[0254] Calculate the feature similarity between the current echo feature set and the historical echo feature set;

[0255] When the feature similarity is less than the similarity threshold, the identity verification result is determined to be an identity match;

[0256] When the feature similarity is greater than or equal to the similarity threshold, the identity verification result is determined to be an identity mismatch.

[0257] In one embodiment, the palm-swiping device is a palm-swiping payment device, which includes an image acquisition unit, an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix deployed around the image acquisition unit.

[0258] The aforementioned palm data processing device emits ultrasonic waves to the target palm via a palm-scanning device, receives the echoes, and acquires palm images. It then combines the echo features determined based on the emission and echo information with the palm image for identity recognition, effectively improving the accuracy of identity verification. Ultrasonic waves are unaffected by ambient light, resulting in high detection accuracy. The current echo feature set generated based on the current echo information and the corresponding ultrasonic emission information includes multiple echo features. Liveness detection based on this feature set effectively eliminates spoofing interference, ensuring detection accuracy. When the target palm is determined to be alive, identity recognition based on the current palm image effectively improves the accuracy of identity verification.

[0259] Each module in the aforementioned palm data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0260] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 12As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data related to the hand data processing method. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a hand data processing method.

[0261] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 13 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a palm data processing method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0262] Those skilled in the art will understand that Figure 12 , Figure 13The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0263] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0264] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0265] In one embodiment, a computer program product is provided, the computer program product including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0266] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0267] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0268] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0269] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing palm data, characterized in that, The method includes: Acquire the current echo information received from the ultrasonic waves emitted to the target palm by the palm-swiping device, and acquire the current palm image obtained by the palm-swiping device from the target palm. Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, a current echo feature set is generated; Based on the current echo feature set, liveness detection is performed on the target hand to obtain the liveness detection result corresponding to the target hand; When the liveness detection result indicates that the target is a live person, the target identity information corresponding to the target hand is determined based on the current hand image.

2. The method according to claim 1, characterized in that, The step of generating a current echo feature set based on the current echo information and the corresponding ultrasonic wave transmission information includes: Based on the current echo information and the ultrasonic emission information corresponding to the current echo information, the target hand is located to obtain the first echo feature for the geometric information of the hand. Based on the data difference between the ultrasonic wave emission information and the current echo information, a second echo feature for the palm material information is obtained. Echo intensity analysis is performed on the current echo information to obtain the third echo feature for palm tissue information; Based on the first echo feature, the second echo feature, and the third echo feature, the current echo feature set is obtained.

3. The method according to claim 2, characterized in that, The step of locating the target hand based on the current echo information and the corresponding ultrasonic emission information, and obtaining a first echo feature for the geometric information of the hand, includes: Ultrasonic imaging is performed based on the current echo information and the ultrasonic emission information corresponding to the current echo information to obtain an ultrasonic image, and the palm size features and palm texture features are obtained based on the ultrasonic image. Based on the waveform morphology of multiple echo signals in the current echo information, the spatial morphological features of the palm are obtained; Based on the palm size features, palm texture features, and palm spatial morphology features, a first echo feature for palm geometric information is obtained.

4. The method according to claim 2, characterized in that, The second echo feature for the palm material information is obtained based on the data difference between the ultrasonic wave emission information and the current echo information, including: Based on the ultrasonic wave emission information and the current echo information, the absorption-reflection ratio of the ultrasonic wave is calculated. The absorption-reflectance ratio is used as a second echo characteristic for palm material information.

5. The method according to claim 2, characterized in that, The process of analyzing the echo intensity of the current echo information to obtain a third echo feature specific to the palm tissue information includes: By comparing the signal strengths of multiple echo signals in the current echo information, the echo strength distribution characteristics and echo strength ratio characteristics are obtained. Based on the signal strength, receiving location, and receiving time of multiple echo signals in the current echo information, the target palm is divided into tissues to obtain tissue distribution characteristics. Based on at least one of the echo intensity distribution characteristics, the echo intensity ratio characteristics, and the tissue distribution characteristics, a third echo feature for palm tissue information is obtained.

6. The method according to claim 1, characterized in that, The step of performing liveness detection on the target hand based on the current echo feature set to obtain the liveness detection result corresponding to the target hand includes: The spatial morphological features of the palm are obtained from the current echo feature set; When the spatial morphological features of the palm belong to planar morphological features, the liveness detection result corresponding to the target palm is determined to be a prosthesis; When the spatial morphological features of the palm belong to three-dimensional morphological features, the other features in the current echo feature set are compared with the reference echo feature set corresponding to the real palm to obtain the liveness detection result corresponding to the target palm.

7. The method according to claim 6, characterized in that, The current echo feature set also includes a second echo feature for palm material information and a third echo feature for palm tissue information; the reference echo feature set includes a reference echo feature range for palm material information and a reference echo feature range for palm tissue information. The step of comparing other features in the current echo feature set with the reference echo feature set corresponding to the real hand to obtain the liveness detection result corresponding to the target hand includes: Compare the second echo feature for palm material information with the reference echo feature range for palm material information; When the second echo feature for palm material information belongs to the reference echo feature range for palm material information, the third echo feature for palm tissue information is compared with the reference echo feature range for palm tissue information. When the third echo feature of the palm tissue information belongs to the reference echo feature range of the palm tissue information, the liveness detection result corresponding to the target palm is determined to be a live body. If any comparison result is not within the corresponding reference echo feature range, the liveness detection result corresponding to the target hand is determined to be a prosthesis.

8. The method according to claim 7, characterized in that, The second echo feature for palm material information includes echo strength distribution feature, echo strength ratio feature and tissue distribution feature, and the reference echo feature range for palm tissue information includes reference strength distribution feature range, reference strength ratio feature range and reference tissue distribution feature range. The comparison of the third echo feature for palm tissue information and the reference echo feature range for palm tissue information includes: The echo strength distribution characteristics are compared with the range of the reference strength distribution characteristics; When the echo strength distribution feature belongs to the reference strength distribution feature range, the echo strength ratio feature and the reference strength ratio feature range are compared. When the echo intensity ratio characteristic falls within the reference intensity ratio characteristic range, the tissue distribution characteristic is compared with the reference tissue distribution characteristic range.

9. The method according to claim 1, characterized in that, The step of determining the target identity information corresponding to the target hand based on the current hand image includes: Determine the initial identity information corresponding to the target hand based on the current hand image; Obtain the historical echo feature set corresponding to the initial identity information; Based on the historical echo feature set, the current echo feature set is used for identity verification to obtain the identity verification result; When the identity verification result is an identity match, the initial identity information is used as the target identity information corresponding to the target hand.

10. The method according to claim 9, characterized in that, The step of determining the initial identity information corresponding to the target hand based on the current hand image includes: Extract palm print and palm vein features from the current palm image to obtain the current palm print and palm vein features; From the identity database, identify registered palm prints and palm vein features that match the current palm print and palm vein features, and use the identity information to which the registered palm print and palm vein features belong as the initial identity information corresponding to the target palm.

11. The method according to claim 9, characterized in that, The step of verifying the identity of the current echo feature set based on the historical echo feature set to obtain the identity verification result includes: Calculate the feature similarity between the current echo feature set and the historical echo feature set; When the feature similarity is less than the similarity threshold, the identity verification result is determined to be an identity match; When the feature similarity is greater than or equal to the similarity threshold, the identity verification result is determined to be an identity mismatch.

12. The method according to any one of claims 1 to 11, characterized in that, The palm-swiping device is a palm-swiping payment device, which includes an image acquisition unit, an ultrasonic transmitting unit matrix and an ultrasonic receiving unit matrix deployed around the image acquisition unit.

13. A palm data processing device, characterized in that, The device includes: The data acquisition module is used to acquire the current echo information received by the ultrasonic waves emitted to the target palm through the palm brushing device, and to acquire the current palm image obtained by the palm brushing device by capturing the target palm. The feature generation module is used to generate a current echo feature set based on the current echo information and the ultrasonic wave emission information corresponding to the current echo information; The liveness detection module is used to perform liveness detection on the target hand based on the current echo feature set, and obtain the liveness detection result corresponding to the target hand. The identity determination module is used to determine the target identity information corresponding to the target hand based on the current hand image when the liveness detection result indicates that the target is a live person.

14. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

Images