Identity recognition method, device, apparatus, computer device and storage medium

Abstract

The present application relates to an identity recognition method, device, apparatus, computer device, storage medium, and computer program product. The method includes: obtaining a first image collected from an identity feature collection entrance of an identity recognition device, performing attachment detection on the first image to obtain a first detection result; when the first detection result indicates that there is an attachment at the identity feature collection entrance, triggering a cleaning process for the identity feature collection entrance; after triggering the cleaning process, obtaining a second image collected from the identity feature collection entrance, performing attachment detection on the second image to obtain a second detection result; when the second detection result indicates that the attachment at the identity feature collection entrance has been cleared, in response to collecting an identity feature image from the identity feature collection entrance, performing identity recognition based on the identity feature image. Using this method can improve the accuracy of identity recognition based on identity feature images.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and in particular, to an identity recognition method, device, apparatus, computer device, storage medium, and computer program product. Background Art

[0002] With the development of computer technologies, the increasingly mature identity recognition technologies have been widely applied in various fields such as business cooperation, consumer payment, social media, security access control, etc. The implementation methods of identity recognition are becoming more and more diverse, such as identity recognition based on two-dimensional codes, identity recognition based on biometric features, etc. Among them, identity recognition based on biometric features, which uses inherent biometric features of people, such as hand shape, fingerprint, face shape, retina, auricle and other biometric features for identity recognition, has become the development trend of identity recognition technologies.

[0003] Currently, when performing identity recognition based on two-dimensional codes or biometric features, it is often necessary to use a set camera to collect images and perform identity recognition through the collected images. However, in different scenarios, water stains, dust, etc. that affect the image collection effect are likely to adhere to the camera for collecting images, and the collected images are prone to distortion problems such as blurring and missing, which reduces the accuracy of identity recognition. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide an identity recognition method, device, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of identity recognition.

[0005] In a first aspect, the present application provides an identity recognition method. The method includes:

[0006] Obtain a first image collected from an identity feature collection entrance of an identity recognition device, perform an attachment detection on the first image, and obtain a first detection result;

[0007] When the first detection result indicates that there is an attachment at the identity feature collection entrance, trigger a cleaning process for the identity feature collection entrance;

[0008] After triggering the cleaning process, obtain a second image collected from the identity feature collection entrance, perform an attachment detection on the second image, and obtain a second detection result;

[0009] When the second detection result indicates that the attachment at the identity feature collection entrance has been cleaned, in response to collecting an identity feature image from the identity feature collection entrance, perform identity recognition based on the identity feature image.

[0010] In a second aspect, the present application further provides an identity recognition device, which includes: a processor, an image sensor, and an identity feature collection entrance;

[0011] The image sensor performs image acquisition through the identity feature acquisition entrance;

[0012] A processor, configured to obtain a first image acquired by the image sensor through the identity feature acquisition entrance, perform attachment detection on the first image to obtain a first detection result; when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, trigger a cleaning process for the identity feature acquisition entrance; after triggering the cleaning process, obtain a second image acquired for the identity feature acquisition entrance, perform attachment detection on the second image to obtain a second detection result; when the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleared, in response to acquiring an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image.

[0013] In a third aspect, the present application further provides an identity recognition device. The device includes:

[0014] A first image detection module, configured to obtain a first image acquired for the identity feature acquisition entrance of the identity recognition device, perform attachment detection on the first image to obtain a first detection result;

[0015] An attachment cleaning module, configured to trigger a cleaning process for the identity feature acquisition entrance when the first detection result indicates that there is an attachment at the identity feature acquisition entrance;

[0016] A second image detection module, configured to obtain a second image acquired for the identity feature acquisition entrance after triggering the cleaning process, perform attachment detection on the second image to obtain a second detection result;

[0017] An identity recognition processing module, configured to perform identity recognition based on the identity feature image in response to acquiring an identity feature image from the identity feature acquisition entrance when the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleared.

[0018] In a fourth aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0019] Obtain a first image acquired for the identity feature acquisition entrance of the identity recognition device, perform attachment detection on the first image to obtain a first detection result;

[0020] When the first detection result indicates that there is an attachment at the identity feature acquisition entrance, trigger a cleaning process for the identity feature acquisition entrance;

[0021] After triggering the cleaning process, obtain a second image collected for the identity feature acquisition entrance, perform an attachment detection on the second image, and obtain a second detection result;

[0022] When the second detection result indicates that the attachments at the identity feature acquisition entrance have been cleared, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image.

[0023] In a fifth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0024] Obtain a first image collected for the identity feature acquisition entrance of the identity recognition device, perform an attachment detection on the first image, and obtain a first detection result;

[0025] When the first detection result indicates that there are attachments at the identity feature acquisition entrance, trigger a cleaning process for the identity feature acquisition entrance;

[0026] After triggering the cleaning process, obtain a second image collected for the identity feature acquisition entrance, perform an attachment detection on the second image, and obtain a second detection result;

[0027] When the second detection result indicates that the attachments at the identity feature acquisition entrance have been cleared, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image.

[0028] In a sixth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0029] Obtain a first image collected for the identity feature acquisition entrance of the identity recognition device, perform an attachment detection on the first image, and obtain a first detection result;

[0030] When the first detection result indicates that there are attachments at the identity feature acquisition entrance, trigger a cleaning process for the identity feature acquisition entrance;

[0031] After triggering the cleaning process, obtain a second image collected for the identity feature acquisition entrance, perform an attachment detection on the second image, and obtain a second detection result;

[0032] When the second detection result indicates that the attachments at the identity feature acquisition entrance have been cleared, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image.

[0033] The above identity recognition method, device, apparatus, computer device, storage medium, and computer program product acquire a first image collected from an identity feature acquisition entrance of an identity recognition device, perform attachment detection based on the first image, and when it is determined that there is an attachment at the identity feature acquisition entrance, perform a cleaning process on the identity feature acquisition entrance. When the attachment at the identity feature acquisition entrance has been cleared, identity recognition is performed based on the identity feature image collected from the identity feature acquisition entrance. After clearing the attachment existing at the identity feature acquisition entrance and performing identity recognition based on the identity feature image collected from the identity feature acquisition entrance, the influence of the attachment existing at the identity feature acquisition entrance on the imaging of the identity feature image can be reduced, the imaging quality of the identity feature image can be ensured, and thus the accuracy of identity recognition based on the identity feature image is improved. Description of the Drawings

[0034] Figure 1 It is an application environment diagram of the identity recognition method in an embodiment;

[0035] Figure 2 It is a schematic flowchart of the identity recognition method in an embodiment;

[0036] Figure 3 It is a schematic flowchart of training an attachment detection model in an embodiment;

[0037] Figure 4 It is a structural block diagram of an identity recognition device in an embodiment;

[0038] Figure 5 It is a schematic diagram of the identity recognition method applied to an access control scenario in an embodiment;

[0039] Figure 6 It is a schematic diagram of the identity recognition method applied to a palm brushing payment scenario in an embodiment;

[0040] Figure 7 It is a schematic flowchart of the identity recognition method in another embodiment;

[0041] Figure 8 It is a schematic diagram of the camera lens setting in an embodiment;

[0042] Figure 9 It is a schematic flowchart of building a water stain detection model in an embodiment;

[0043] Figure 10 It is a schematic diagram of a palm image being distorted due to water stains in an embodiment;

[0044] Figure 11 It is another schematic diagram of a palm image being distorted due to water stains in an embodiment;

[0045] Figure 12 It is also a schematic diagram of the distortion of the palm image due to water stains in an embodiment;

[0046] Figure 13 It is a schematic flowchart of water stain detection by a water stain detection model in an embodiment;

[0047] Figure 14 It is a structural block diagram of an identity recognition device in an embodiment;

[0048] Figure 15 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The identity recognition method provided by the embodiments of the present application can be applied to the application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other servers. The terminal 102 can obtain a first image collected from the identity feature acquisition entrance of the identity recognition device, perform attachment detection on the first image, and obtain a first detection result. When the first detection result indicates that there is an attachment at the identity feature acquisition entrance, the terminal 102 can trigger a cleaning process for the identity feature acquisition entrance. After triggering the cleaning process, the terminal 102 obtains a second image collected from the identity feature acquisition entrance, performs attachment detection on the second image, and obtains a second detection result. When the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleaned, the terminal 102 responds to the acquisition of the identity feature image from the identity feature acquisition entrance, and performs identity recognition based on the identity feature image. Specifically, the terminal 102 can send the collected identity feature image to the server 104, and the server 104 performs identity recognition based on the identity feature image and feeds back the obtained identity recognition result to the terminal 102.

[0051] In addition, the identity recognition method can also be directly implemented by the terminal 102 or the server 104 alone, that is, the terminal 102 can directly perform identity recognition on the collected identity feature image, or the server 104 can implement the identity recognition method alone.

[0052] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The terminal 102 can be configured with an image sensor device for image acquisition. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers. Multiple servers involved can form a blockchain, and the server 104 can be a node on the blockchain.

[0053] In one embodiment, as Figure 2 shown, an identity recognition method is provided. This method is executed by a computer device, and specifically can be executed alone by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the terminal in it as an example for illustration, it includes the following steps:

[0054] Step 202, obtain a first image collected from the identity feature acquisition entrance of the identity recognition device, and perform attachment detection on the first image to obtain a first detection result.

[0055] Among them, identity recognition is the process of identifying the true identity information of a user, and specifically can also verify whether the true identity information of the user matches the identity information claimed by the user. An identity recognition device is a device used for identity recognition, which can identify the identity of a user so as to perform corresponding processing based on the identity of the user. For example, in an access control scenario, the identity recognition device can identify the identity of a user to determine whether the user belongs to a legitimate user, so as to determine whether to allow the user to enter. The identity feature acquisition entrance is the entrance for the identity recognition device to collect identity features for identity recognition. When the identity features collected by the identity recognition device include images, the identity feature acquisition entrance can be the acquisition entrance of the image sensor of the identity recognition device, that is, the image sensor performs image acquisition through the identity feature acquisition entrance. In specific implementation, the image sensor can include various types of cameras, and the identity feature acquisition entrance can be the respective lenses corresponding to various types of cameras.

[0056] The first image is acquired by the identity feature acquisition entrance of the identity recognition device, and specifically can be an image acquired by the image sensor of the identity recognition device through the identity feature acquisition entrance. Attachment detection refers to detecting whether there is attachment, such as dust, water stains, stains, etc., on the identity feature acquisition entrance. If there is attachment on the identity feature acquisition entrance, when the identity recognition device acquires images through the identity feature acquisition entrance, the attachment will interfere with the imaging, resulting in distortion problems in the acquired image, such as blur, missing, occlusion, etc., which will affect the accuracy of identity recognition. For example, when there are water droplets at the identity feature acquisition entrance, when the image sensor acquires the image, such as when the camera captures the image, the water droplets at the identity feature acquisition entrance will also be captured, introducing imaging noise, resulting in the capture of water droplets in the imaging, which interferes with the object that actually needs to be captured. The first detection result is the detection result obtained by performing attachment detection on the first image, and the first detection result may include data information such as whether there is attachment, attachment type, and attachment distribution area. Based on the first detection result, it can be determined whether there is an object that will interfere with the imaging attached to the identity feature acquisition entrance of the identity recognition device, so as to determine whether the identity feature acquisition entrance needs to be cleaned.

[0057] Specifically, the terminal can obtain the first image collected by the identity feature collection entrance of the identity recognition device, such as the terminal can receive the first image sent by the identity recognition device. In a specific implementation, the identity recognition device itself can directly implement the identity recognition method, that is, the identity recognition device can be used as a terminal to obtain the first image collected by the identity feature collection entrance, and perform attachment detection on the first image to obtain a first detection result. When performing attachment detection on the first image, the terminal can perform attachment detection on the first image based on target detection algorithms, such as sliding window algorithms (Sliding Window Algorithm), candidate region algorithms (Region Proposal Algorithms), selective search algorithms (Selective Search), R-CNN (Region-Convolutional Neural Networks, regional convolutional neural networks) and other algorithms to obtain a first detection result.

[0058] Step 204 : When the first detection result indicates that there is attachment at the identity feature collection entrance, a cleaning process for the identity feature collection entrance is triggered.

[0059] Among them, the cleaning process for the identity feature acquisition inlet refers to the process of removing the attachments existing at the identity feature acquisition inlet. Through the cleaning process, the attachments at the identity feature acquisition inlet can be removed to ensure the imaging quality when acquiring images through the identity feature acquisition inlet, that is, to obtain a better image acquisition effect and a clearer image.

[0060] Specifically, if the first detection result indicates that there are attachments at the identity feature acquisition inlet, that is, if continuing to acquire images through the identity feature acquisition inlet will result in distorted images, the terminal triggers the cleaning process for the identity feature acquisition inlet, that is, the terminal performs a cleaning process on the attachments at the identity feature acquisition inlet. In a specific implementation, the terminal can control a cleaning device to perform the cleaning process for the identity feature acquisition inlet. For example, if the attachment at the identity feature acquisition inlet is water stains, the terminal can control a water stain removal device to remove the water stains, such as drying through a drying device or blowing and evaporating through a fan. In addition, for different types of attachments, different cleaning methods can be corresponding, and specifically, different cleaning devices can be controlled to implement the cleaning process. If the attachment at the identity feature acquisition inlet is dust or stains, the terminal can control a scrubbing device to scrub the identity feature acquisition inlet to remove the dust or stains at the identity feature acquisition inlet.

[0061] Step 206, after triggering the cleaning process, obtain a second image acquired for the identity feature acquisition inlet, and perform an attachment detection on the second image to obtain a second detection result.

[0062] Among them, the second image is an image acquired by the identity recognition device for the identity feature acquisition inlet after triggering the cleaning process, that is, the second image is an image acquired again through the identity feature acquisition inlet after the cleaning process for the attachments.

[0063] Specifically, after triggering the cleaning process, that is, after performing a cleaning process on the attachments existing at the identity feature acquisition inlet, the terminal obtains a second image acquired for the identity feature acquisition inlet. The terminal performs an attachment detection on the second image again to obtain a second detection result. Based on the second detection result, it can be determined whether there are still objects that will interfere with imaging attached to the identity feature acquisition inlet of the identity recognition device, so as to determine whether the attachments have been cleaned. In a specific application, the attachment detection for the second image can adopt the same detection method as the attachment detection for the first image to ensure the consistency of the detection method.

[0064] Step 208, when the second detection result indicates that the attachments at the identity feature acquisition inlet have been cleaned, in response to acquiring an identity feature image from the identity feature acquisition inlet, perform identity recognition based on the identity feature image.

[0065] The identity feature image is an image collected through the identity feature collection portal for identity recognition, and may specifically include a biometric feature image, a credential feature image, etc. For example, the identity feature image may include a palm image, a face image, a QR code image, etc.

[0066] Specifically, if the second detection result indicates that the attachments at the identity feature collection entrance have been cleared, that is, the attachments at the identity feature collection entrance have been cleared, which can ensure the subsequent image collection effect, the terminal performs identity recognition based on the identity feature image collected from the identity feature collection entrance. In a specific application, when the second detection result indicates that there are no attachments at the identity feature collection entrance, the terminal obtains the identity feature image collected from the identity feature collection entrance, and performs identity recognition based on the identity feature image. The identity feature image is no longer interfered by the attachments at the identity feature collection entrance, and the imaging quality is high. Identity recognition based on the identity feature image can ensure the accuracy of identity recognition.

[0067] In addition, when the second detection result indicates that the attachments at the identity feature collection entrance have not been cleaned, that is, after the cleaning process, the attachments at the identity feature collection entrance have not been removed, the terminal can trigger the cleaning process of the identity feature collection entrance again, until it is determined that the attachments at the identity feature collection entrance have been cleaned, and then collect the identity feature image through the identity feature collection entrance for identity recognition. In a specific application, the terminal can record the number of cleaning processes. When the number of cleaning processes reaches a threshold number of times and the attachments are still not cleaned, the cleaning process for the identity feature collection entrance can be ended to avoid repeated cleaning processes for a long time without being able to clean the attachments. In addition, when the attachments at the identity feature collection entrance are not cleaned, the terminal can also generate a prompt message and send the prompt message to the control end to prompt the control personnel of the control end to clean the identity feature collection entrance to ensure that the attachments at the identity feature collection entrance can be removed immediately. In specific implementation, a threshold for the number of cleaning processes can be set. When the number of cleaning processes does not exceed the threshold, if the attachments at the entrance of the identity feature collection are still not cleaned after cleaning, the cleaning process can be repeated until the attachments are cleaned or the number of cleaning times exceeds the threshold. Statistical analysis can also be performed on the historical records of the cleaning process. For example, the cleaning mode corresponding to the cleaning of the attachments can be statistically analyzed, which can include cleaning time, cleaning method, cleaning intensity, etc., so that when the attachments are detected, the corresponding cleaning mode can be determined according to the parameters of the attachments, such as the type of attachments, distribution range, etc., so that the attachments can be effectively cleaned according to the determined cleaning mode to ensure the cleaning effect.

[0068] In the above identity recognition method, the terminal obtains a first image collected by the identity feature acquisition entrance of the identity recognition device, performs attachment detection based on the first image, and when it is determined that there is an attachment at the identity feature acquisition entrance, performs a cleaning process on the identity feature acquisition entrance. When the attachment at the identity feature acquisition entrance has been cleared, identity recognition is performed based on the identity feature image collected from the identity feature acquisition entrance. After clearing the attachment existing at the identity feature acquisition entrance and performing identity recognition based on the identity feature image collected from the identity feature acquisition entrance, the influence of the attachment existing at the identity feature acquisition entrance on the imaging of the identity feature image can be reduced, the imaging quality of the identity feature image can be ensured, and thus the accuracy of identity recognition based on the identity feature image is improved.

[0069] In one embodiment, performing attachment detection on the first image to obtain a first detection result includes: extracting image features of the first image to obtain the image features of the first image; obtaining a distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image; and performing attachment detection based on the image features and the distance parameter to obtain the first detection result.

[0070] Among them, the image features of the first image are obtained by extracting the image features of the first image, and specifically can be obtained by processing the first image through various object detection algorithms. Based on the image features of the first image, it can be determined whether there is an attachment at the identity feature acquisition entrance of the identity recognition device. The acquisition object is the object included in the first image, specifically the shooting target in the first image. The identity recognition device shoots the acquisition object through the identity feature acquisition entrance to obtain the first image. The distance parameter may include the distance between the identity feature acquisition entrance and the shooting target, specifically may include the distance from the lens of the camera to the shooting target. The distance parameter can be determined by a distance sensor set in the identity recognition device, such as by an optical distance sensor. When there is an attachment at the identity feature acquisition entrance of the identity recognition device, specifically when there is a liquid attachment, the liquid attachment itself will form a lens, resulting in abnormal detection of the distance parameter. The distance parameter can be used to assist in determining whether there is an attachment at the identity feature acquisition entrance of the identity recognition device.

[0071] Specifically, the terminal extracts image features from the first image. The terminal can perform image feature extraction on the first image through various image feature extraction methods. For example, it can extract image features from the first image through feature extraction algorithms such as SIFT (Scale-Invariant Features Transform), SURF (Speeded Up Robust Features), and HOG (Histogram of Oriented Gradient). In addition, the terminal can also perform image feature extraction on the first image based on artificial neural network algorithms, such as through various pre-trained artificial neural network models to obtain the image features of the first image. The terminal obtains the distance parameter between the identity feature collection entrance and the collection object included in the first image, and the distance parameter can be detected by an optical distance sensor.

[0072] The terminal performs attachment detection based on the image features and distance parameter of the first image to obtain a first detection result. The terminal can perform attachment detection based on the image features and distance parameter respectively, and then synthesize the detection results of the two to obtain the first detection result. The terminal can also directly synthesize the image features and distance parameter to perform attachment detection uniformly to obtain the first detection result. In specific implementation, the terminal can perform target detection based on the image features of the first image to detect whether there is an attachment at the identity feature collection entrance. For example, when there are distortion problems such as blur, occlusion, and missing in the first image, it may be caused by the presence of an attachment at the identity feature collection entrance. The terminal can perform abnormal analysis based on the distance parameter to determine whether the distance parameter is abnormal. If the distance parameter is abnormal, it may be caused by the presence of an attachment at the identity feature collection entrance. The terminal uses the image features and distance parameter of the first image to perform attachment detection, which can determine whether there is an attachment at the identity feature collection entrance from multiple dimensions and improve the accuracy of attachment detection.

[0073] In addition, the terminal can also perform attachment detection based on the image features of the first image alone to obtain a first detection result, that is, the terminal can perform attachment detection only using the image features of the first image. Further, if attachment detection is performed based on the image features of the first image alone and the obtained first detection result indicates that there is an attachment at the identity feature acquisition entrance, the terminal triggers a cleaning process for the identity feature acquisition entrance. If the first detection result indicates that there is no attachment at the identity feature acquisition entrance, the terminal can further obtain the distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image, and perform attachment detection based on this distance parameter, so as to ensure the accuracy of attachment detection through a two-stage detection method. The terminal can also perform weighted attachment detection using the image features and distance parameters of the first image. Specifically, it can perform attachment detection using the image features and distance parameters of the first image respectively, and weight the attachment detection results of the two according to the preset weight parameters to obtain a fused first detection result. Among them, the weight parameters can be set based on the historical records of attachment detection to distinguish the importance of image features and distance parameters in attachment detection.

[0074] In this embodiment, the terminal performs attachment detection through the image features extracted from the first image and the distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image, so as to detect whether there is an attachment at the identity feature acquisition entrance from the features of multiple dimensions, which can improve the accuracy of attachment detection.

[0075] In one embodiment, the first image includes a visible light image and an infrared image collected for the same acquisition object; image feature extraction is performed on the first image to obtain the image features of the first image, including: performing image feature extraction on the visible light image and the infrared image respectively to obtain the visible light image features of the visible light image and the infrared image features of the infrared image.

[0076] Among them, the visible light image is a color image collected by a visible light image sensor, and the infrared image is an image collected by an infrared image sensor. The visible light image and the infrared image are collected for the same acquisition object. A visible light image sensor and an infrared image sensor can be set in the identity recognition device. When triggering image acquisition, the visible light image sensor and the infrared image sensor can perform image acquisition simultaneously, so as to respectively collect a visible light image and an infrared image for the same acquisition object. Both the visible light image and the infrared image can be used for identity recognition. The visible light image features are the image features extracted from the visible light image, and the infrared image features are the image features extracted from the infrared image.

[0077] Specifically, the terminal extracts image features from the visible light image and the infrared image respectively, obtaining the visible light image features of the visible light image and the infrared image features of the infrared image. The visible light image features and the infrared image features can be used as the image features of the first image. In specific implementation, the visible light image and the infrared image have different image characteristics, and different feature extraction algorithms can be used respectively to extract different image features, which is beneficial to ensuring the accuracy of the image features.

[0078] Further, based on the image features and the distance parameter, attachment detection is performed to obtain a first detection result, including: fusing the visible light image features, the infrared image features, and the distance features of the distance parameter to obtain detection features; performing attachment detection based on the detection features to obtain a first detection result.

[0079] Among them, the distance feature is a feature determined based on the distance parameter, and specifically, it can be obtained by performing feature mapping on the distance parameter. For example, the terminal can perform linear or non-linear mapping processing on the distance parameter to obtain the distance feature of the distance parameter. The detection feature is obtained by fusing the visible light image features, the infrared image features, and the distance feature, and can characterize whether there is an attachment at the identity feature acquisition entrance of the identity recognition device.

[0080] Specifically, the terminal obtains the distance feature of the distance parameter, and the distance feature can be obtained by the terminal performing feature mapping on the distance parameter. The terminal fuses the visible light image features, the infrared image features, and the distance feature. Specifically, the terminal can first connect the visible light image features, the infrared image features, and the distance feature, and fuse the connected features to obtain detection features. In specific applications, different weights can be set for the visible light image features, the infrared image features, and the distance feature, and the visible light image features, the infrared image features, and the distance feature are weighted and fused according to their respective weights to obtain detection features. The respective weights of the visible light image features, the infrared image features, and the distance feature can be preset, and different weights can be set under different environmental conditions. For example, in an environment with strong light, the imaging quality of the visible light image is high, and the detection effect for the visible light image is good, so the weight of the visible light image features can be increased; while in an environment with weak light, the weight of the infrared image features can be increased to ensure the expression ability of the detection features. The terminal performs attachment detection based on the detection features. For example, the target detection algorithm selected in advance can be used to perform attachment detection on the detection features to obtain a first detection result. In specific implementation, the terminal can input the detection features into a pre-trained attachment detection model to perform attachment detection based on the input detection features by the attachment detection model, and the attachment detection model outputs a first detection result. The first detection result can describe whether there is an attachment at the identity feature acquisition entrance of the identity recognition device.

[0081] In this embodiment, the first image includes a visible light image and an infrared image. The terminal performs attachment detection on the detection features obtained by fusing the features of the visible light image, the features of the infrared image, and the distance features of the distance parameter, which can make full use of the features of different types of images and the distance features between the acquisition object and the identity feature acquisition entrance for attachment detection, and can improve the accuracy of attachment detection.

[0082] In one embodiment, the attachment detection of the first image to obtain the first detection result is implemented based on an attachment detection model; the attachment detection of the second image to obtain the second detection result is implemented based on the attachment detection model; as Figure 3 shown, the training steps of the attachment detection model include:

[0083] Step 302, obtain a sample image and the distance sample parameter between the identity feature acquisition entrance and the acquisition object included in the sample image; the sample image and the distance sample parameter carry an attachment detection label.

[0084] Among them, the attachment detection of the first image and the second image is both implemented through a pre-trained attachment detection model. That is, the first image and the second image can be respectively input into the attachment detection model, and the attachment detection model performs attachment detection respectively and outputs the corresponding detection results. The sample image is an image historically acquired through the identity feature acquisition entrance, and the distance sample parameter is the distance parameter between the identity feature acquisition entrance and the acquisition object included in each sample image. The sample image and the distance sample parameter both carry an attachment detection label, and the attachment detection label is used to mark whether there is an attachment at the identity feature acquisition entrance.

[0085] Specifically, the training of the attachment detection model can be executed by a computing device, which can specifically be a terminal or a server. The computer device obtains training samples, including a sample image and the distance sample parameter between the identity feature acquisition entrance and the acquisition object included in the sample image, and the sample image and the distance sample parameter carry an attachment detection label.

[0086] Step 304, extract the image features of the sample image through the attachment detection model to be trained, and obtain the sample image features of the sample image.

[0087] Among them, the sample image features are the image features extracted from the sample image. Specifically, the computer device extracts the image features of the sample image through the attachment detection model to be trained. Specifically, the sample image can be input into the attachment detection model, and the attachment detection model performs image feature extraction to obtain the sample image features of the sample image.

[0088] Step 306: Based on the sample image features and distance sample parameters, perform attachment detection through the attachment detection model to be trained, and obtain the sample detection result.

[0089] Specifically, the computer device performs attachment detection through the attachment detection model to be trained. The attachment detection model to be trained performs attachment detection based on the obtained sample image features and distance sample parameters, and obtains the sample detection result output by the attachment detection model to be trained.

[0090] Step 308: Based on the sample detection result and the attachment detection label, update the attachment detection model to be trained and continue training until the training is completed, and obtain the trained attachment detection model.

[0091] Specifically, the computer device updates the attachment detection model to be trained based on the sample detection result and the attachment detection label. The computer device can compare the sample detection result with the attachment detection label, and adaptively adjust the model parameters in the attachment detection model to be trained according to the comparison result, so as to realize the training update of the attachment detection model to be trained. The computer device continues to train based on the updated attachment detection model, and specifically can train through the next sample image until the training is completed. For example, when the number of training times reaches the training times threshold, or when the attachment detection accuracy reaches the accuracy threshold, the computer device ends the training and obtains the trained attachment detection model. The trained attachment detection model can perform attachment detection on the input image and output the attachment detection result for the input image.

[0092] In this embodiment, the computer device trains the attachment detection model through the sample image and the distance sample parameters, and performs attachment detection through the trained attachment detection model, which can ensure the accuracy and detection processing efficiency of the attachment detection.

[0093] In one embodiment, the sample image includes a visible light sample image and an infrared sample image; the attachment detection model to be trained extracts image features from the sample image to obtain the sample image features of the sample image, including: the attachment detection model to be trained extracts image features from the visible light sample image and the infrared sample image respectively, and obtains the visible light sample image features of the visible light sample image and the infrared sample image features of the infrared sample image.

[0094] Among them, the visible light sample image is a color sample image collected by a visible light image sensor, and the infrared sample image is a sample image collected by an infrared image sensor. The visible light sample image and the infrared sample image are collected for the same acquisition object.

[0095] Specifically, the computer device extracts image features from the visible light sample image and the infrared sample image respectively through the attachment detection model to be trained, obtaining the visible light sample image features of the visible light sample image and the infrared sample image features of the infrared sample image. The visible light sample image features and the infrared sample image features can be used as the sample image features of the sample image. In specific implementation, the visible light sample image and the infrared sample image can be input into the attachment detection model to be trained together, and different feature extraction layers in the attachment detection model to be trained are used for feature extraction.

[0096] Further, through the attachment detection model to be trained, attachment detection is performed based on the sample image features and the distance sample parameters to obtain a sample detection result, including: performing feature mapping on the distance sample parameters through the attachment detection model to be trained to obtain distance sample features; fusing the visible light sample image features, the infrared sample image features, and the distance sample features to obtain detection sample features; and performing attachment detection based on the detection sample features to obtain a sample detection result.

[0097] Among them, the distance sample features are features determined based on the distance sample parameters, and specifically can be obtained by performing feature mapping on the distance sample parameters. For example, the distance sample parameters can be input into the attachment detection model to be trained, and the feature mapping layer in the attachment detection model to be trained is used to perform feature mapping on the distance sample parameters to obtain distance sample features. The detection sample features are obtained by fusing the visible light sample image features, the infrared sample image features, and the distance sample features, and can represent whether there is an attachment at the identity feature acquisition entrance of the identity recognition device.

[0098] Specifically, the computer device performs feature mapping on the distance sample parameters through the attachment detection model to be trained. For example, the distance sample parameters can also be input into the attachment detection model to be trained, so that the feature mapping layer in the attachment detection model to be trained performs feature mapping on the distance sample parameters to obtain distance sample features. The computer device fuses the visible light sample image features, the infrared sample image features, and the distance sample features through the attachment detection model to be trained. Specifically, the feature fusion layer in the attachment detection model to be trained can fuse the visible light sample image features, the infrared sample image features, and the distance sample features to obtain detection sample features. The computer device performs attachment detection based on the detection sample features through the attachment detection model to be trained. For example, the attachment detection layer in the attachment detection model to be trained can perform attachment detection on the detection sample features and output the obtained sample detection result. The sample detection result is used to describe whether there is an attachment at the identity feature acquisition entrance when collecting the sample image through the identity feature acquisition entrance of the identity recognition device.

[0099] In this embodiment, the sample image includes a visible light sample image and an infrared sample image. By using the visible light sample image, the infrared sample image, and the corresponding distance sample parameters to train the attachment detection model, the features of different types of images and the distance features between the acquisition object and the identity feature acquisition entrance can be fully utilized for training the attachment detection model, which can improve the accuracy of attachment detection by the attachment detection model.

[0100] In one embodiment, the identity recognition method further includes: obtaining historical identity recognition data of the identity recognition device; determining recognition statistical parameters according to the historical identity recognition data.

[0101] Among them, the historical identity recognition data is the data of the identity recognition device's historical identity recognition. The historical identity recognition data may record the trigger time, identity recognition result, etc. of each identity recognition by the identity recognition device. The recognition statistical parameters are obtained by statistically processing the historical identity recognition data, and specifically may include the identity recognition success rate, identity recognition duration, etc. The identity recognition success rate can be obtained according to the proportion of the number of successful identity recognition times in each identity recognition by the identity recognition device; the identity recognition duration can be obtained by statistically processing the time consumption of each identity recognition by the identity recognition device. The recognition statistical parameters can reflect the sensitivity of identity recognition based on the identity recognition device. The higher the identity recognition success rate and the shorter the identity recognition duration, the higher the sensitivity of the identity recognition device.

[0102] Specifically, the terminal obtains the historical identity recognition data of the identity recognition device, and specifically can obtain the historical identity recognition data according to different dimensions. For example, according to the time dimension, the terminal can obtain the historical identity recognition data within a certain time range; or according to the number of times dimension, the terminal can obtain the historical identity recognition data of the most recent preset number of identity recognitions. The terminal determines the recognition statistical parameters according to the historical identity recognition data. Specifically, the terminal can analyze the historical identity recognition data, count the number of successful identity recognitions in the historical identity recognition data, and obtain the identity recognition success rate; by statistically processing the time consumption of each identity recognition, the identity recognition duration is obtained. The recognition statistical parameters are used to characterize the sensitivity in the historical identity recognition process of the identity recognition device. The higher the sensitivity, the more efficient and accurate the identity recognition device can perform the identity recognition process.

[0103] Further, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, triggering a cleaning process for the identity feature acquisition entrance, including: when the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the recognition statistical parameters meet the cleaning trigger conditions, triggering a cleaning process for the identity feature acquisition entrance.

[0104] Among them, the cleaning trigger condition is used to determine whether there is actually an attachment at the identity feature acquisition entrance, so as to determine whether to trigger the cleaning process for the identity feature acquisition entrance. The cleaning trigger condition can be adaptively set based on the recognition statistical parameters according to actual needs. For example, the cleaning trigger condition can be that the identity recognition success rate is lower than the success rate threshold, or the change in the identity recognition success rate reaches the success rate change threshold. The cleaning trigger condition can also be that the identity recognition duration reaches the preset duration, or the change in the identity recognition duration reaches the duration change threshold.

[0105] Specifically, the terminal compares the recognition statistical parameters with the pre-set cleaning trigger condition to determine whether the recognition statistical parameters meet the cleaning trigger condition. If the recognition statistical parameters meet the cleaning trigger condition, and the first detection result indicates that there is an attachment at the identity feature acquisition entrance, it is considered that there is indeed an attachment at the identity feature acquisition entrance, and the terminal triggers the cleaning process for the identity feature acquisition entrance. For example, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, and the identity recognition success rate statistically calculated based on historical identity recognition data is lower than the success rate threshold, it indicates that the attachment existing at the identity feature acquisition entrance has affected the identity recognition success rate of the identity recognition device, that is, affected the sensitivity of the identity recognition device, then the terminal triggers the cleaning process for the identity feature acquisition entrance. In a specific application, the terminal can periodically detect whether there is an attachment at the identity feature acquisition entrance, and periodically determine whether the recognition statistical parameters meet the cleaning trigger condition. When it is detected that there is an attachment at the identity feature acquisition entrance or the recognition statistical parameters meet the cleaning trigger condition, it can trigger to determine whether the trigger condition for another cleaning process is met. For example, when it is first detected that there is an attachment at the identity feature acquisition entrance, the terminal can further determine whether the recognition statistical parameters meet the cleaning trigger condition. If it is met, the cleaning process for the identity feature acquisition entrance is triggered; another example is that when it is first detected that the recognition statistical parameters meet the cleaning trigger condition, the terminal can further determine whether there is an attachment at the identity feature acquisition entrance. If there is, the cleaning process for the identity feature acquisition entrance is triggered.

[0106] In this embodiment, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, and the recognition statistical parameters determined based on historical identity recognition data meet the cleaning trigger condition, the terminal determines that there is an attachment at the identity feature acquisition entrance and needs to be processed. The terminal triggers the cleaning process for the identity feature acquisition entrance, and can accurately determine the attachment in combination with historical identity recognition data.

[0107] In one embodiment, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, a cleaning process for the identity feature acquisition entrance is triggered, including: when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, the attachment cleaning device of the identity recognition device is used to perform a cleaning process on the identity feature acquisition entrance.

[0108] Among them, the attachment cleaning device is a device for performing a cleaning process on the identity feature acquisition entrance, and specifically may include a drying device, a scrubbing device, etc. When there is an attachment at the identity feature acquisition entrance, the attachment cleaning device can be activated to perform a cleaning process on the identity feature acquisition entrance to clean the attachment at the identity feature acquisition entrance.

[0109] Specifically, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance, the terminal can activate the attachment cleaning device of the identity recognition device, and the attachment cleaning device is used to perform a cleaning process on the identity feature acquisition entrance. For example, the terminal can start the drying device or the scrubbing device to perform a drying process or a scrubbing process on the identity feature acquisition entrance, so as to achieve the cleaning process of the identity feature acquisition entrance and remove the attachment at the identity feature acquisition entrance. In a specific application, for different types of attachments, different types of attachment cleaning devices can be used to perform a cleaning process. Further, for different parameters of the attachment, different cleaning modes can be used to perform a cleaning process. Among them, the parameters of the attachment may include but are not limited to the type and distribution range of the attachment; the cleaning mode may include but is not limited to the cleaning device, the cleaning method, the cleaning time, the cleaning intensity, etc.

[0110] In this embodiment, the terminal uses the attachment cleaning device of the identity recognition device to perform a cleaning process on the identity feature acquisition entrance, and can effectively clean the attachment at the identity feature acquisition entrance through a dedicated attachment cleaning device, ensuring the effect of the cleaning process.

[0111] In one embodiment, the attachment at the identity feature acquisition entrance includes water stains; using the attachment cleaning device of the identity recognition device to perform a cleaning process on the identity feature acquisition entrance includes: controlling the infrared lamp of the identity recognition device to start, so as to perform a cleaning process on the water stains at the identity feature acquisition entrance through the infrared lamp.

[0112] Among them, water stains refer to water droplets at the identity feature collection entrance. When water stains adhere to the identity feature collection entrance, it will affect the imaging effect of the image collected through the identity feature collection entrance, and further affect the accuracy of identity recognition. The infrared lamp includes a lamp that emits infrared light. The infrared lamp can also provide supplementary light for the infrared image sensor to improve the imaging effect of the infrared image. The infrared lamp can be set at relevant positions of the identity feature collection entrance, so as to be able to provide supplementary light when collecting images through the identity feature collection entrance, and can also clean the water stains adhering to the identity feature collection entrance.

[0113] Specifically, the attachments adhering to the identity feature collection entrance include water stains. When cleaning the water stains, the terminal can control the infrared lamp of the identity recognition device to start, so as to clean the water stains at the identity feature collection entrance through the irradiation of the infrared lamp. Specifically, the infrared lamp can dry the water stains to accelerate the evaporation of the water stains, so as to achieve the cleaning of the water stains. In specific implementation, when cleaning the water stains at the identity feature collection entrance by starting the infrared lamp, the terminal can keep detecting the water stains. When it is detected that the water stains have been cleaned, the infrared lamp can be turned off to end the cleaning process.

[0114] In this embodiment, the terminal controls the infrared lamp of the identity recognition device to start to clean the water stains at the identity feature collection entrance, which can safely clean the water stains without contact and ensure the cleaning effect of the water stains.

[0115] In one embodiment, the identity recognition method further includes: when the second detection result indicates that no attachment is detected, determining that the attachment at the identity feature collection entrance has been cleaned.

[0116] Among them, the second detection result indicates that no attachment is detected, that is, when detecting the attachment according to the second image, it indicates that there is no longer an attachment at the identity feature collection entrance, then it can be determined that the original attachment has been cleaned. Specifically, when the second detection result indicates that no attachment is detected, the terminal determines that the attachment at the identity feature collection entrance has been cleaned, that is, there is no attachment at the identity feature collection entrance.

[0117] In this embodiment, when the second detection result indicates that no attachment is detected, the terminal determines that the attachment has been cleaned, which can ensure the imaging effect of the image collected through the identity feature collection entrance subsequently.

[0118] In one embodiment, the identity recognition method further includes: determining the attachment distribution area based on the second detection result. When the attachment distribution area is smaller than the attachment distribution area determined based on the first detection result, determining that the attachment at the identity feature collection entrance has been cleaned.

[0119] Among them, the attachment distribution area refers to the area range where the attachments are distributed at the identity feature acquisition entrance. The larger the attachment distribution area, the larger the surface area of the attachments attached at the identity feature acquisition entrance, and generally the greater its impact on the imaging effect. Specifically, the terminal determines the attachment distribution area based on the second detection result. When the second detection result indicates that there are still attachments, the terminal can determine the attachment distribution area of the attachments at the identity feature acquisition entrance based on the second detection result. The terminal compares the attachment distribution area determined based on the second detection result with the attachment distribution area determined based on the first detection result to compare the size relationship of the area ranges. If the attachment distribution area determined based on the second detection result is smaller than the attachment distribution area determined based on the first detection result, it is considered that although the attachments have not been completely cleaned, a certain degree of cleaning has still been performed on the attachments to reduce the range of its distribution area, and the terminal can determine that the attachments at the identity feature acquisition entrance have been cleaned.

[0120] In this embodiment, when the attachment distribution area determined based on the second detection result is smaller than the attachment distribution area determined based on the first detection result, the terminal determines that the attachments have been cleaned, which can improve the imaging effect of the subsequent images collected through the identity feature acquisition entrance.

[0121] In one embodiment, in response to collecting an identity feature image from the identity feature acquisition entrance, identity recognition based on the identity feature image is performed, including: in response to an identity recognition trigger event, obtaining the identity feature image collected from the identity feature acquisition entrance; performing identity information matching between the identity feature image and the pre-stored registered identity information to perform identity recognition based on the identity feature image.

[0122] Among them, the identity recognition trigger event refers to the event that triggers the identity recognition, which can specifically include but is not limited to operations, instructions, etc. that trigger the identity recognition. For example, in the scenario of an access control system, when a user needs to pass through the access control, the event that triggers the identity recognition; another example is when a user makes a payment at a payment terminal, the event that triggers the identity recognition. In addition, identity recognition can also be applied to the scenario of an anti-addiction system. For example, in the anti-addiction system of online games, it is necessary to limit the online game time of minors. Then, when the anti-addiction is triggered, such as when the cumulative online game time of a game user reaches a preset time threshold, it is necessary to perform identity recognition on the game user. At this time, the identity recognition event is triggered to determine whether the game user is an adult or whether it is the owner of the game account, so as to realize the limitation of the online game time of minors.

[0123] In a specific implementation, an identity recognition trigger event is an event that triggers identity recognition through biometric features. The biometric features are biometric features of measurable body parts of a user, such as various types of biometric features like hand shape, fingerprint, face shape, iris, retina, palm, etc. When performing identity recognition processing through the biometric features of the user's measurable body parts, it is necessary to collect biometric data for the user's body parts and extract biometric features from the collected biometric data, so as to perform identity recognition for the user based on the extracted biometric features. For example, if the identity recognition trigger event is to trigger identity recognition through the face, the terminal needs to collect face data for the user's face and perform identity recognition for the user based on the collected face data, such as a face image; another example is that if the identity recognition trigger event is to trigger identity recognition through the palm, the terminal needs to collect palm data for the user's palm and perform identity recognition for the user based on the collected palm data. The registered identity information is the identity information entered by the user during pre - registration of identity, and specifically may include a registered feature image.

[0124] Specifically, when detecting an identity recognition trigger event, such as detecting that a user is performing identity recognition, the terminal responds to this identity recognition trigger event and obtains an identity feature image collected from the identity feature acquisition entrance. The terminal queries the pre - stored registered identity information and performs identity information matching between the identity feature image and the registered identity information. Specifically, it can perform image feature matching between the identity feature image and the registered feature image, so as to perform identity recognition based on the identity feature image. Specifically, it can determine the identity recognition result based on the identity feature image according to the image feature matching result between the identity feature image and the registered feature image.

[0125] In this embodiment, after the attachments at the identity feature acquisition entrance have been cleared, the terminal responds to the identity recognition trigger event and performs identity information matching between the identity feature image collected through the identity feature acquisition entrance and the registered identity information, so as to realize identity recognition based on the identity feature image. This can reduce the influence of the attachments existing at the identity feature acquisition entrance on the imaging of the identity feature image, ensure the imaging quality of the identity feature image, and thus improve the accuracy of identity recognition based on the identity feature image.

[0126] In one embodiment, the identity feature image is an image acquired by collecting the palm part; the registered identity information includes the palmprint registration feature and the palm vein registration feature obtained by registering the palm of the registered user; matching the identity feature image with the pre-stored registered identity information for identity recognition based on the identity feature image includes: extracting the palmprint feature and the palm vein feature from the identity feature image; matching the palmprint feature with the palmprint registration feature to obtain a palmprint feature matching result; matching the palm vein feature with the palm vein registration feature to obtain a palm vein feature matching result; and obtaining an identity recognition result according to the palmprint feature matching result and the palm vein feature matching result.

[0127] Among them, the identity feature image is an image acquired by collecting the palm part, that is, identity recognition is performed through the user's palm. The palmprint registration feature is the palmprint feature input when the registered user registers their identity through the palm; the palm vein registration feature is the palm vein feature input when the registered user registers their identity through the palm.

[0128] The palmprint refers to the palm image from the fingertips to the wrist, which includes various features such as main lines, wrinkles, fine textures, ridge endings, and bifurcation points that can be used for identity recognition. The palmprint feature refers to the feature reflected by the texture information of the palm, which can be obtained by taking an image of the palm and extracting it from the palm image. Different users generally correspond to different palmprint features, that is, the palms of different users have different texture features, and identity recognition processing of different users can be realized based on the palmprint feature. The palm vein refers to the vein information image of the palm, which is used to reflect the vein image information in the human palm and has the ability to identify living bodies, and can be obtained by shooting with an infrared camera. The palm vein feature is the vein feature of the palm part obtained based on palm vein analysis. Different users generally correspond to different palm vein features, that is, the palms of different users have different vein features, and identity recognition processing of different users can also be realized based on the palm vein feature. The palmprint feature matching result is the matching result obtained by feature matching based on the palmprint feature, which reflects the recognition result of identity recognition through the palmprint. The palm vein feature matching result is the matching result obtained by feature matching based on the palm vein feature, which reflects the recognition result of identity recognition through the palm vein.

[0129] Specifically, the terminal can extract features from the identity feature image to obtain palmprint features and palm vein features. In a specific application, the identity feature image is an image collected for the palm part, which can include visible light images and infrared images. The terminal extracts features from the visible light image to obtain palmprint features, and the terminal extracts features from the infrared image to obtain palm vein features. The terminal performs palmprint feature matching between the palmprint features and the palmprint registration features to obtain a palmprint feature matching result. In a specific implementation, the palmprint feature matching can be the calculation of the palmprint feature similarity, so as to obtain a palmprint feature matching result including the palmprint similarity. If the palmprint similarity exceeds the palmprint similarity threshold, it can be considered that the palmprint matching is consistent, otherwise it is considered that the palmprint matching is inconsistent. The terminal performs palm vein feature matching between the palm vein features and the palm vein registration features to obtain a palm vein feature matching result. In a specific implementation, the palm vein feature matching can be the calculation of the palm vein feature similarity, so as to obtain a palm vein feature matching result including the palm vein similarity. If the palm vein similarity exceeds the palm vein similarity threshold, it can be considered that the palm vein matching is consistent, otherwise it is considered that the palm vein matching is inconsistent. The terminal obtains an identity recognition result based on the palmprint feature matching result and the palm vein feature matching result. For example, the terminal can perform weighted fusion on the palmprint feature matching result and the palm vein feature matching result, so as to obtain an identity recognition result according to the weighted fusion result.

[0130] In this embodiment, feature matching is performed through the palmprint features and palm vein features at the palm to achieve identity recognition, and accurate identity recognition can be performed based on the palm image.

[0131] In one embodiment, the identity recognition method further includes: during the process of triggering the cleaning process, in a perceptible manner, providing waiting prompt information for instructing the user to wait for identity recognition through the identity recognition device.

[0132] Among them, the perceptible manner refers to a manner that can be intuitively perceived by the user, such as playing sound through a speaker, displaying content through a display screen, indicating through a light, etc. The waiting prompt information is used to instruct the user to wait. After the cleaning process for the identity feature acquisition entrance is completed, identity recognition through the identity recognition device can be supported. The content form of the waiting prompt information can be flexibly configured according to actual needs, such as being one of text, pictures, graphics, videos, audio, or a combination of multiple forms of content. Specifically, during the process of triggering the cleaning process, the terminal can provide waiting prompt information for instructing the user to wait for identity recognition through the identity recognition device in a manner perceptible to the user. For example, the cleaning waiting prompt information can be displayed on the display screen of the identity recognition device, or the waiting prompt information can be announced through the speaker by voice.

[0133] In this embodiment, during the process of triggering the cleaning process, the terminal provides a waiting prompt message in a perceptible manner to indicate to the user to wait for identity recognition through the identity recognition device, which can timely remind the user to wait for the cleaning process to complete, avoid the user's identity recognition failure caused by identity recognition during the triggering of the cleaning process, and ensure the user experience.

[0134] In one embodiment, obtaining a first image collected from the identity feature collection entrance of the identity recognition device includes: when a detection trigger condition is met, obtaining a first image collected from the identity feature collection entrance of the identity recognition device; the detection trigger condition being met includes at least one of reaching the attachment detection time, detecting an identity recognition trigger event, or the recognition statistical parameters of the identity recognition device meeting the statistical parameter trigger condition.

[0135] Among them, the detection trigger condition is used to determine whether it is necessary to trigger the attachment detection for the identity feature collection entrance, that is, whether it is necessary to detect whether there is an attachment at the identity feature collection entrance. The attachment detection time is a set time for attachment detection set in advance according to actual needs. When the attachment detection time is reached, it is considered that the detection trigger condition is met. The identity recognition trigger event refers to an event that triggers identity recognition. When an identity recognition trigger event is detected, it can be considered that the detection trigger condition is met. The recognition statistical parameters are obtained by statistically analyzing historical identity recognition data, and specifically may include the identity recognition success rate, identity recognition duration, etc. The statistical parameter trigger condition is used to determine whether it is necessary to perform the attachment detection process for the identity feature collection entrance according to the recognition statistical parameters. For example, meeting the statistical parameter trigger condition can be that the identity recognition success rate is lower than the success rate threshold, or the change in the identity recognition success rate reaches the success rate change threshold. Meeting the statistical parameter trigger condition can also be that the identity recognition duration reaches the preset duration, or the change in the identity recognition duration reaches the duration change threshold.

[0136] Specifically, the terminal obtains the preset detection trigger condition, determines whether the detection trigger condition is met. When the detection trigger condition is met, it indicates that it is necessary to perform the attachment detection process for the identity feature collection entrance. The terminal obtains a first image collected from the identity feature collection entrance of the identity recognition device to perform the attachment detection on the identity feature collection entrance based on the first image. In a specific application, when the attachment detection time is reached, an identity recognition trigger event is detected, or the recognition statistical parameters of the identity recognition device meet the statistical parameter trigger condition, it can be considered that the detection trigger condition is met, and the attachment detection for the identity feature collection entrance is triggered. When the first detection result based on the first image indicates that there is no attachment at the identity feature collection entrance, it can return to continue determining the detection trigger condition, and when the detection trigger condition is met again next time, the attachment detection process for the identity feature collection entrance is triggered again.

[0137] In this embodiment, when the attachment detection time is reached, an identity recognition trigger event is detected, or the recognition statistical parameters of the identity recognition device meet the statistical parameter trigger conditions, the attachment detection process for the identity feature acquisition entry is triggered. This can promptly detect the attachments at the identity feature acquisition entry and perform cleaning, thereby reducing the impact of the attachments at the identity feature acquisition entry on the imaging of the identity feature image, ensuring the imaging quality of the identity feature image, and thus improving the accuracy of identity recognition based on the identity feature image.

[0138] In one embodiment, the identity recognition method further includes: in response to a resource transfer trigger event, determining resource transfer parameters; based on the identity recognition result of the identity feature image, determining a target resource account; and performing a resource transfer on the target resource account based on the resource transfer parameters.

[0139] Among them, a resource is an asset that can be exchanged for a subject matter. Resources can be funds, electronic vouchers, shopping vouchers, virtual red envelopes, etc. A virtual red envelope is a virtual object with a certain capital numerical attribute. For example, funds can be exchanged for equivalent goods after a transaction. Resource transfer refers to the exchange of resources, including a resource transferor and a resource transferee. Resources are transferred from the resource transferor to the resource transferee. For example, during the payment process of shopping, funds are transferred as resources. A resource transfer trigger event refers to an event that triggers a resource transfer, which can specifically include but is not limited to operations, instructions, etc. that trigger a resource transfer. A resource transfer trigger event can be triggered by a user who needs to perform a resource transfer process. For example, it can be triggered by the resource transferee in the resource transfer process or by the resource transferor in the resource transfer process. Resource transfer means transferring a certain amount of the resources held by the resource transferor to the resource transferee. The resource transfer trigger event can be flexibly set according to actual needs. The resource transfer parameters are the relevant parameters corresponding to the resource transfer trigger event for the resource transfer process to be performed, which can specifically include but are not limited to various parameter information such as the resource transferee, the resource transferor, the resource transfer amount, the discount amount, the order number, the resource transfer time, and the resource transfer terminal. The target resource account is the resource account associated with the user who triggers the resource transfer trigger event. By performing a resource transfer operation on the target resource account, the resource transfer process for the user can be realized.

[0140] Specifically, the terminal can determine resource transfer parameters in response to a resource transfer trigger event, such as determining the amount of resource transfer, the resource recipient, etc. When the user's corresponding user identity can be determined according to the identity recognition result, the terminal can determine the target resource account associated with the user according to the identity recognition result. Specifically, the terminal can determine the user's corresponding user identity based on the identity recognition result, and determine the target resource account associated with the user according to the user's corresponding user identity. The target resource account includes the user's resources. Based on the determined resource transfer parameters, the terminal performs a resource transfer on the target resource account. For example, according to the amount of resource transfer in the resource transfer parameters, the resources in the target resource account are transferred to the resource recipient in the resource transfer parameters, thereby implementing the resource transfer process for the user.

[0141] In this embodiment, the target resource account is determined based on the identity recognition result, and when a resource transfer trigger event is triggered, resource transfer processing is performed according to the corresponding resource transfer parameters through the determined target resource account. Resource transfer processing is performed based on the identity recognition result, which improves the processing efficiency of resource transfer.

[0142] In one embodiment, as Figure 4 shown, an identity recognition device 400 is provided, including: an image sensor 402, an identity feature acquisition inlet 404, and a processor 406; where:

[0143] The image sensor 402 performs image acquisition through the identity feature acquisition inlet 404;

[0144] The processor 406 is configured to obtain a first image acquired by the image sensor through the identity feature acquisition inlet, perform attachment detection on the first image to obtain a first detection result; when the first detection result indicates that there is an attachment at the identity feature acquisition inlet, trigger a cleaning process for the identity feature acquisition inlet; after triggering the cleaning process, obtain a second image acquired for the identity feature acquisition inlet, perform attachment detection on the second image to obtain a second detection result; when the second detection result indicates that the attachment at the identity feature acquisition inlet has been cleaned, in response to acquiring an identity feature image from the identity feature acquisition inlet, perform identity recognition based on the identity feature image.

[0145] Among them, the image sensor 402 is used for image acquisition to perform identity recognition through the acquired images. For different types of identity feature images acquired, the image sensor 402 can correspond to different types of sensors. For example, the image sensor 402 can include a visible light image sensor, an infrared image sensor, etc. The identity feature acquisition entrance 404 is the entrance for the identity recognition device 400 to acquire identity features for identity recognition, that is, the image sensor 402 performs image acquisition through the identity feature acquisition entrance 404. The processor 406 is used to detect attachments in the images acquired by the image sensor 402. When the attachments at the identity feature acquisition entrance have been cleared, the processor 406 can perform identity recognition based on the identity feature images acquired from the identity feature acquisition entrance.

[0146] In the above identity recognition device, the image sensor in the identity recognition device performs image acquisition through the identity feature acquisition entrance, and the processor in the identity recognition device obtains the first image acquired by the identity feature acquisition entrance through the identity feature acquisition entrance, performs attachment detection based on the first image, and performs cleaning treatment on the identity feature acquisition entrance when it is determined that there are attachments at the identity feature acquisition entrance. When the attachments at the identity feature acquisition entrance have been cleared, identity recognition is performed based on the identity feature images acquired from the identity feature acquisition entrance. After clearing the attachments existing at the identity feature acquisition entrance and then performing identity recognition based on the identity feature images acquired from the identity feature acquisition entrance, the influence of the attachments existing at the identity feature acquisition entrance on the imaging of the identity feature images can be reduced, the imaging quality of the identity feature images can be ensured, and thus the accuracy of identity recognition based on the identity feature images is improved.

[0147] In one embodiment, the image sensor 402 includes a visible light image sensor and an infrared image sensor; the attachments at the identity feature acquisition entrance 404 include water stains; the identity recognition device 400 further includes an infrared lamp; the processor 406 is further configured to control the infrared lamp to start to clean the water stains at the identity feature acquisition entrance 404 through the infrared lamp.

[0148] Among them, the visible light image sensor is used to collect visible light images, and the infrared image sensor is used to collect infrared images. The visible light image and the infrared image can be used as identity feature images for identity recognition. Water stains refer to water droplets at the entrance of the identity feature collection. When water stains adhere to the entrance of the identity feature collection, it will affect the imaging effect of the images collected through the entrance of the identity feature collection, and further affect the accuracy of identity recognition. The infrared lamp includes a lamp that emits infrared light. The infrared lamp can also be used to supplement light for the infrared image sensor to improve the imaging effect of the infrared image. The infrared lamp can be set at relevant positions of the entrance of the identity feature collection, so as to be able to supplement light when collecting images at the entrance of the identity feature collection, and can also perform cleaning on the attachments adhering to the entrance of the identity feature collection, such as cleaning the water stains adhering to the entrance of the identity feature collection.

[0149] Specifically, the identity recognition device 400 further includes an infrared lamp. The attachments adhering to the entrance 404 of the identity feature collection may include water stains. When cleaning the water stains, the processor 406 can control the infrared lamp of the identity recognition device 400 to start, so as to perform cleaning on the attachments at the entrance 404 of the identity feature collection through the irradiation of the infrared lamp. Specifically, the infrared lamp can dry the water stains to accelerate the evaporation of the water stains, so as to achieve the cleaning of the water stains. In a specific implementation, when cleaning the water stains at the entrance 404 of the identity feature collection by starting the infrared lamp, the processor 406 can keep detecting the water stains. When it detects that the water stains have been cleaned, it can turn off the infrared lamp to end the cleaning process.

[0150] In this embodiment, the processor in the identity recognition device controls the infrared lamp of the identity recognition device to start, so as to clean the water stains at the entrance of the identity feature collection through the infrared lamp, which can achieve safe cleaning of the water stains without contact and ensure the cleaning effect of the water stains.

[0151] This application also provides an application scenario that applies the above identity recognition method. Specifically, as Figure 5 shown, the application of the identity recognition method in this application scenario is as follows:

[0152] In the access control system scenario, users can identify their identities through identity recognition devices. When it is determined that the user has a legitimate identity, they can pass through the access control and are allowed to enter. Among them, the identity recognition device captures images of the user's palm area and performs identity recognition based on the palm images. An image sensor can be set in the identity recognition device to capture the palm extended by the user. If there are objects such as dust and water stains attached to the acquisition entrance of the identity feature, that is, the acquisition entrance of the image sensor, the captured palm image will be distorted, affecting the identity recognition process based on the palm image. Based on the identity recognition method in this embodiment, the identity recognition device can obtain a first image captured for the acquisition entrance of the identity feature, perform attachment detection based on the first image. When it is determined that there are attachments at the acquisition entrance of the identity feature, cleaning processing is performed on the acquisition entrance of the identity feature. When the attachments at the acquisition entrance of the identity feature have been cleared, identity recognition is performed based on the identity feature images captured from the acquisition entrance of the identity feature. After clearing the attachments existing at the acquisition entrance of the identity feature and performing identity recognition based on the identity feature images captured from the acquisition entrance of the identity feature, the influence of the attachments existing at the acquisition entrance of the identity feature on the imaging of the identity feature images can be reduced, ensuring the imaging quality of the identity feature images, thereby improving the accuracy of identity recognition based on the identity feature images.

[0153] This application also provides an application scenario that applies the above identity recognition method. Specifically, the application of the identity recognition method in this application scenario is as follows:

[0154] Palm brushing refers to a method of identity recognition through biometric features of the palm, such as palmprint features and palm vein features. Palmprint recognition can identify the identity information of different users based on pictures of the palmprint area on the palm. Information such as palmprints and palm veins on the human palm is similar to the human face, which are very important biometric features and are difficult to change. Therefore, identity recognition through the human palm and further resource transfer, such as shopping payment, is one of the trends in identity recognition research. When performing palmprint recognition, for shooting the palm part, it is necessary to detect the palm area of the captured image. Specifically, object detection technology can be used to locate the finger gap points and extract the palm area picture from the picture. In palm brushing recognition, generally, color images and infrared images need to be taken. The color image is a color picture formed by a color sensor Sensor collecting natural light. In face or palm brushing payment, it is generally used for face or palm preference, comparison recognition, etc. The infrared image is an infrared picture formed by an infrared sensor Sensor collecting infrared light. In face or palm payment, it is generally used for liveness detection and palm vein recognition. In specific applications, the collected images can also be selected. Specifically, a group of color pictures, depth pictures, and infrared pictures that meet the preconditions of the liveness detection and comparison recognition algorithms can be selected. For example, for face recognition, it can include color images, depth images, and infrared images; for palm brushing recognition, it can include color images and infrared images. Specifically, the color images can be selected based on the angle, size, centering degree, and clarity of the face or palm, the infrared images can be selected based on the brightness of the infrared pictures, and the depth images can be preferably selected based on the integrity of the depth images, so that body detection and comparison recognition and other processes can be performed through the selected images.

[0155] However, when applying palm brushing in scenarios such as water parks, it is easy to encounter the situation where water droplets drip on the camera lens, resulting in the failure of palm brushing. Based on this, the identity recognition method provided in this embodiment, such as Figure 6 shown, the user can make a payment by palm brushing at the payment device end. The user can extend the palm to the identity feature collection entrance of the payment device end, so that the payment device end can collect the palm image of the user for identity recognition and then perform payment processing. To ensure the success rate of palm brushing, the payment device end can identify water stains based on the attachment detection algorithm and turn on the infrared fill light to dry the water stains. The infrared fill light can cover near the camera lens to ensure the drying effect of the water stains. When performing attachment detection, typical water stain images can be collected to train the attachment detection model to identify water stains. When the water stains are identified by the attachment detection model and it is determined that the success rate of palm brushing of the payment device decreases, the infrared fill light is turned on to dry the water stains. At the same time, the user can be reminded through the user interface (UI, User Interface) of the payment device that the device is processing the water stains. After cleaning the water stains, it can be further determined in real time whether the water stains have been cleaned. After cleaning the water stains, palm brushing is restored, and the user's identity is recognized and payment processing is performed.

[0156] Specifically, as Figure 7 shown, the identity recognition method provided in this embodiment may include steps 702 to 708. Among them: Step 702, an infrared lamp is covered and set at the camera lens. The payment device collects a palm image through the camera for identity recognition to perform payment processing after the identity is recognized. An infrared lamp can be covered and set at the camera lens. On the one hand, the infrared lamp can be used to supplement light for the infrared camera, and on the other hand, the infrared lamp can be used to dry the water stains at the lens. Step 704, collect water stain sample images and train a water stain detection model to identify water stains. Train the water stain detection model through the collected water stain sample images, and perform water stain recognition through the trained water stain detection model. Step 706, when the water stain detection model detects water stains and the palm brushing success rate decreases, turn on the infrared lamp to dry the water stains and remind through the user interface that the water stains are being processed. When the water stain detection model detects water stains and the palm brushing success rate decreases, specifically, if the success rate of the payment device through palm brushing is lower than the success rate threshold, it is determined that there are water stains attached to the lens, turn on the infrared lamp to dry the water stains, and remind through the user interface that the water stains are being processed. Step 708, detect whether the water stains are cleared, and resume palm brushing after the water stains are cleared. The payment device can detect in real time whether the water stains at the lens are cleared. If it is determined that the water stains are cleared, resume the palm brushing work to support the user to make a payment through the palm. In specific applications, the setting of the infrared lamp and the training of the water stain detection model can be realized in advance, and directly execute steps 706 and 708, that is, directly perform water stain detection through the trained water stain detection model, and dry the detected water stains through the set infrared lamp.

[0157] Furthermore, as Figure 8 shown, when an infrared lamp is set at the camera lens, the camera includes a color camera and an infrared camera, which respectively collect color images and infrared images. Around the color camera and the infrared camera, 2 infrared supplementary lights and 2 color supplementary lights are respectively set to supplement light for the corresponding cameras to ensure the image acquisition effect. In addition, around the 4 supplementary lights, 4 light distance sensors psensor (Proximity Sensor) are also set to detect the distance from the shooting target to the lens. In specific applications, the distribution of the camera, supplementary lights, and light distance sensors at the lens can be flexibly set according to actual needs.

[0158] Furthermore, as Figure 9As shown, the process of building a water stain detection model includes steps 902 to 906, where: Step 902, determine the characteristics of the water stain image, analyze based on the water stain image, and determine the characteristics existing in the water stain image to determine the training samples. Specifically, the water stain image includes characteristic 1, that is, the image becomes blurred, and the entire palm image is particularly blurred. There is blur in a single IR (Infrared Radiation) image or RGB image, or both images are blurred, and the blurred areas in the image are different, or there is partial blur. As Figure 10 shown, the left side is the palmprint image collected for the palm, and the right side is the palm vein image collected for the palm. As shown in the shaded part, the palmprint image and the palm vein image are blurred and distorted as a whole due to water stains. The water stain image includes characteristic 2, that is, there are strange light and shadows in the image, which will cause partial blur and distortion. As Figure 11 shown, the left side is the palmprint image collected for the palm, and the right side is the palm vein image collected for the palm. As shown in the shaded part, the palmprint image and the palm vein image are blurred and distorted in the area of the four fingers of the palm due to water stains. The water stain image includes characteristic 3, that is, the brightness of the image in the area affected by the water stain is equivalent to or not very different from the brightness of the normal area, but the image becomes partially blurred. As Figure 12 shown, the left side is the palmprint image collected for the palm, and the right side is the palm vein image collected for the palm. As shown in the shaded part, the palmprint image and the palm vein image are blurred and distorted in most areas of the palm due to water stains.

[0159] Furthermore, in step 904, collect water stain sample images and distance sample data, and perform annotation. Specifically, some water droplets or sprays can be randomly scattered on the surface of the camera module manually. On the one hand, collect IR images, RGB images, and psensor data when there is no human hand. It is found that sometimes the psensor data is abnormal, either all abnormal or individually abnormal, and the RGB image may be blurred. On the other hand, when there is a human hand, collect IR images, RGB images, and psensor data at different distances. It is found that the IR image or RGB image may be blurred, and sometimes the psensor data is abnormal, either all abnormal or individually abnormal, and generally it will be the maximum value. In addition, collect IR images, RGB images, and psensor data under normal conditions to form water stain sample images and distance sample data. Perform annotation on the obtained water stain sample images and distance sample data to annotate whether there is a water stain in each water stain sample image and distance sample data.

[0160] Further, in step 906, a water stain detection model is obtained by training the water stain sample image and the distance sample data. A deep learning model can be constructed and trained with abnormal images with water stains or psensor values to obtain relevant parameters in the deep learning model for water stains. In actual application, relevant data, including IR images, RGB images, and psensor data, can be input according to this water stain detection model to determine whether there is a water stain.

[0161] Further, for the water stain detection model, its input includes IR infrared images, RGB visible light images, and distance parameters, specifically the value of the pensor. As Figure 13 shown, the infrared image is subjected to feature extraction through the first feature extraction network, the distance parameter is subjected to feature extraction through the second feature extraction network, and the visible light image is subjected to feature extraction through the third feature extraction network. Among them, the first feature extraction network and the third feature extraction network can be CNN networks, while the second feature extraction network can be a fully connected network. The features extracted by the first feature extraction network, the second feature extraction network, and the third feature extraction network are further spliced together through the sub-network fusion layer. For the spliced features, they are fused through the feature fusion layer, and the feature fusion layer can be a fully connected network for fusing the features. The predicted value output by the feature fusion layer is detected through the water stain detection layer. Specifically, after classification by softmax, two outputs are obtained, namely the probability of having water droplets and the probability of having no water droplets. According to the probability of having water droplets and the probability of having no water droplets, it can be determined whether there is a water stain at the lens of the payment device.

[0162] Further, when the payment device end identifies a water stain through the attachment detection model and determines that the palm brushing success rate of the payment device has decreased, the infrared fill light is turned on to dry the water stain. At the same time, the user interface of the payment device can be used to remind the user that the device is processing the water stain. After cleaning the water stain, it can be further determined in real time whether the water stain has been cleaned. After cleaning the water stain, the palm brushing is restored, and the user is identified and payment processing is performed. When the palm brushing recognition technology is applied in scenarios such as water parks, the palm brushing device can automatically identify and clean the water stain to ensure the success rate of palm brushing recognition.

[0163] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0164] Based on the same inventive concept, an embodiment of the present application further provides an identity recognition device for implementing the above-mentioned identity recognition method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the identity recognition device provided below can refer to the limitations on the identity recognition method in the above text, and will not be repeated here.

[0165] In one embodiment, as Figure 14 shown, an identity recognition device 1400 is provided, including: a first image detection module 1402, an attachment cleaning module 1404, a second image detection module 1406, and an identity recognition processing module 1408, where:

[0166] The first image detection module 1402 is configured to obtain a first image collected from the identity feature collection entrance of the identity recognition device, perform attachment detection on the first image, and obtain a first detection result;

[0167] The attachment cleaning module 1404 is configured to trigger a cleaning process for the identity feature collection entrance when the first detection result indicates that there are attachments at the identity feature collection entrance;

[0168] The second image detection module 1406 is configured to obtain a second image collected from the identity feature collection entrance after the cleaning process is triggered, perform attachment detection on the second image, and obtain a second detection result;

[0169] The identity recognition processing module 1408 is configured to perform identity recognition based on the identity feature image in response to collecting an identity feature image from the identity feature collection entrance when the second detection result indicates that the attachments at the identity feature collection entrance have been cleaned.

[0170] In one embodiment, the first image detection module 1402 includes an image feature extraction module, a distance parameter acquisition module, and an attachment detection module; wherein: The image feature extraction module is configured to perform image feature extraction on the first image to obtain the image features of the first image; The distance parameter acquisition module is configured to acquire the distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image; The attachment detection module is configured to perform attachment detection based on the image features and the distance parameter to obtain a first detection result.

[0171] In one embodiment, the first image includes a visible light image and an infrared image collected for the same acquisition object; The image feature extraction module is further configured to perform image feature extraction on the visible light image and the infrared image respectively to obtain the visible light image features of the visible light image and the infrared image features of the infrared image; The attachment detection module is further configured to perform feature fusion on the visible light image features, the infrared image features, and the distance features of the distance parameter to obtain detection features; and perform attachment detection based on the detection features to obtain a first detection result.

[0172] In one embodiment, performing attachment detection on the first image to obtain the first detection result is implemented based on an attachment detection model; performing attachment detection on the second image to obtain the second detection result is implemented based on the attachment detection model; It further includes a training sample acquisition module, a sample feature extraction module, a sample detection module, and a model update module; wherein: The training sample acquisition module is configured to acquire a sample image and the distance sample parameter between the identity feature acquisition entrance and the acquisition object included in the sample image; The sample image and the distance sample parameter carry an attachment detection label; The sample feature extraction module is configured to perform image feature extraction on the sample image through the attachment detection model to be trained to obtain the sample image features of the sample image; The sample detection module is configured to perform attachment detection through the attachment detection model to be trained based on the sample image features and the distance sample parameter to obtain a sample detection result; The model update module is configured to perform model update on the attachment detection model to be trained based on the sample detection result and the attachment detection label, and then continue training until the training is completed to obtain a trained attachment detection model.

[0173] In one embodiment, the sample image includes a visible light sample image and an infrared sample image; the sample feature extraction module is further configured to perform image feature extraction on the visible light sample image and the infrared sample image respectively through a to-be-trained attachment detection model, so as to obtain a visible light sample image feature of the visible light sample image and an infrared sample image feature of the infrared sample image; the sample detection module is further configured to perform feature mapping on the distance sample parameter through the to-be-trained attachment detection model to obtain a distance sample feature; fuse the visible light sample image feature, the infrared sample image feature and the distance sample feature to obtain a detection sample feature; and perform attachment detection based on the detection sample feature to obtain a sample detection result.

[0174] In one embodiment, it further includes an identification statistical parameter determination module, configured to obtain historical identity identification data of the identity identification device; determine identification statistical parameters according to the historical identity identification data; the attachment cleaning module 1404 is further configured to trigger a cleaning process for the identity feature acquisition entrance when the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identification statistical parameters meet the cleaning trigger condition.

[0175] In one embodiment, the attachment cleaning module 1404 is further configured to perform a cleaning process on the identity feature acquisition entrance through the attachment cleaning device of the identity identification device when the first detection result indicates that there is an attachment at the identity feature acquisition entrance.

[0176] In one embodiment, the attachment at the identity feature acquisition entrance includes water stains; the attachment cleaning module 1404 is further configured to control the infrared lamp of the identity identification device to start, so as to perform a cleaning process on the water stains at the identity feature acquisition entrance through the infrared lamp.

[0177] In one embodiment, it further includes an attachment cleaning determination module, configured to determine that the attachment at the identity feature acquisition entrance has been cleaned when the second detection result indicates that no attachment is detected.

[0178] In one embodiment, it further includes an attachment cleaning determination module, configured to determine the attachment distribution area based on the second detection result, and determine that the attachment at the identity feature acquisition entrance has been cleaned when the attachment distribution area is smaller than the attachment distribution area determined based on the first detection result.

[0179] In one embodiment, the identity identification processing module 1408 is further configured to, in response to an identity identification trigger event, acquire an identity feature image collected from the identity feature acquisition entrance; perform identity information matching between the identity feature image and the pre-stored registered identity information, so as to perform identity identification based on the identity feature image.

[0180] In one embodiment, the identity feature image is an image acquired for the palm part; the registered identity information includes a palmprint registration feature and a palm vein registration feature obtained by registering the palm of the registered user; the identity recognition processing module 1408 is further configured to extract a palmprint feature and a palm vein feature from the identity feature image; perform palmprint feature matching between the palmprint feature and the palmprint registration feature to obtain a palmprint feature matching result; perform palm vein feature matching between the palm vein feature and the palm vein registration feature to obtain a palm vein feature matching result; and obtain an identity recognition result according to the palmprint feature matching result and the palm vein feature matching result.

[0181] In one embodiment, it further includes a waiting prompt module, configured to provide, in a perceptible manner, waiting prompt information for instructing the user to wait for identity recognition by the identity recognition device during the process of triggering the cleaning process.

[0182] In one embodiment, the first image detection module 1402 is further configured to, when the detection trigger condition is satisfied, acquire a first image acquired for the identity feature acquisition entrance of the identity recognition device; the detection trigger condition being satisfied includes at least one of reaching the attachment detection time, detecting an identity recognition trigger event, or the recognition statistical parameter of the identity recognition device satisfying the statistical parameter trigger condition.

[0183] In one embodiment, it further includes a resource transfer module, configured to determine resource transfer parameters in response to a resource transfer trigger event; determine a target resource account according to the identity recognition result of the identity feature image; and perform resource transfer on the target resource account based on the resource transfer parameters.

[0184] Each module in the above identity recognition device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0185] In one embodiment, a computer device is provided. The computer device can be a terminal or a server. If the computer device is a terminal, its internal structure diagram can be as Figure 15As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements an identity recognition method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0186] Those skilled in the art can understand that Figure 15 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0187] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0188] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0189] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0190] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0191] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0192] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0193] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An identity recognition method, characterized in that, the method includes: Obtain a first image collected from the identity feature acquisition entrance of the identity recognition device, perform image feature extraction on the first image to obtain the image features of the first image, perform attachment detection based on the image features to obtain a detection result based on the image features of the first image. When the detection result based on the image features of the first image indicates that there is no attachment at the identity feature acquisition entrance, obtain the distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image, and perform attachment detection based on the distance parameter to obtain a first detection result; When the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity recognition duration in the recognition statistical parameters of the identity recognition device meets the cleaning trigger condition, trigger a cleaning process for the identity feature acquisition entrance according to the cleaning mode corresponding to the parameters of the attachment; the recognition statistical parameters are used to characterize the sensitivity of the identity recognition device for historical identity recognition; the cleaning mode is determined by statistically analyzing the cleaning process history of the identity feature acquisition entrance; After triggering the cleaning process, obtain a second image collected from the identity feature acquisition entrance, perform image feature extraction on the second image to obtain the image features of the second image, perform attachment detection based on the image features to obtain a detection result based on the image features of the second image. When the detection result based on the image features of the second image indicates that there is no attachment at the identity feature acquisition entrance, obtain the distance parameter between the identity feature acquisition entrance and the acquisition object included in the second image, and perform attachment detection based on the distance parameter to obtain a second detection result; When the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleaned, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image; When the second detection result indicates that the attachment at the identity feature acquisition entrance has not been cleaned, trigger the cleaning process for the identity feature acquisition entrance again. When the number of times of the cleaning process for the identity feature acquisition entrance reaches the number threshold and the attachment has not been cleaned, end the cleaning process for the identity feature acquisition entrance and send a prompt message to the control end to prompt the control end to perform a cleaning process for the identity feature acquisition entrance.

2. The method according to claim 1, characterized in that, the first image includes a visible light image and an infrared image collected for the same acquisition object; the performing image feature extraction on the first image to obtain the image features of the first image includes: Performing image feature extraction on the visible light image and the infrared image respectively to obtain the visible light image features of the visible light image and the infrared image features of the infrared image; The method further includes: Fuse the visible light image features, the infrared image features, and the distance features of the distance parameter to obtain detection features; Perform attachment detection based on the detection features to obtain a first detection result.

3. The method according to claim 1, wherein, obtaining the first detection result is implemented based on an attachment detection model; performing attachment detection on the second image and obtaining a second detection result is implemented based on the attachment detection model; The training steps of the attachment detection model include: Obtain a sample image and the distance sample parameter between the identity feature acquisition entrance and the acquisition object included in the sample image; the sample image and the distance sample parameter carry an attachment detection label; Extract the sample image features of the sample image through the attachment detection model to be trained, and obtain the sample image features of the sample image; Perform attachment detection based on the sample image features and the distance sample parameter through the attachment detection model to be trained, and obtain a sample detection result; Based on the sample detection result and the attachment detection label, update the model of the attachment detection model to be trained and continue training until the training is completed, and obtain the trained attachment detection model.

4. The method according to claim 3, wherein, The sample image includes a visible light sample image and an infrared sample image.

5. The method according to claim 1, wherein, The method further includes: Obtain the historical identity recognition data of the identity recognition device; Determine the recognition statistical parameter according to the historical identity recognition data.

6. The method according to claim 1, wherein, When the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity recognition duration in the recognition statistical parameter of the identity recognition device meets the cleaning trigger condition, trigger the cleaning process for the identity feature acquisition entrance, including: When the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity recognition duration in the recognition statistical parameter of the identity recognition device meets the cleaning trigger condition, perform a cleaning process on the identity feature acquisition entrance through the attachment cleaning device of the identity recognition device.

7. The method according to claim 6, wherein, The attachment at the identity feature acquisition entrance includes water stains; performing a cleaning process on the identity feature acquisition entrance through the attachment cleaning device of the identity recognition device includes: Control the infrared lamp of the identity recognition device to start, so as to perform a cleaning process on the water stains at the identity feature acquisition entrance through the infrared lamp.

8. The method according to claim 1, wherein, The method further includes at least one of the following: When the second detection result indicates that no attachment is detected, determine that the attachment at the identity feature acquisition entrance has been cleaned; Determine the attachment distribution area based on the second detection result. When the attachment distribution area is smaller than the attachment distribution area determined based on the first detection result, it is determined that the attachments at the identity feature acquisition entrance have been cleared.

9. The method according to claim 1, wherein, the performing identity recognition based on the identity feature image in response to collecting an identity feature image from the identity feature acquisition entrance includes: in response to an identity recognition trigger event, acquiring an identity feature image collected from the identity feature acquisition entrance; matching the identity feature image with pre-stored registered identity information to perform identity recognition based on the identity feature image.

10. The method according to claim 9, wherein, the identity feature image is an image collected for the palm part; the registered identity information includes palm print registration features and palm vein registration features obtained by performing identity registration on the palm of a registered user; the matching the identity feature image with pre-stored registered identity information to perform identity recognition based on the identity feature image includes: extracting palm print features and palm vein features from the identity feature image; matching the palm print features with the palm print registration features to obtain a palm print feature matching result; matching the palm vein features with the palm vein registration features to obtain a palm vein feature matching result; obtaining an identity recognition result according to the palm print feature matching result and the palm vein feature matching result.

11. The method according to claim 1, wherein, the method further includes: during the process of triggering the cleaning process, providing, in a perceivable manner, waiting prompt information for instructing a user to wait for identity recognition through the identity recognition device.

12. The method according to any one of claims 1 to 11, wherein, the acquiring a first image collected for the identity feature acquisition entrance of the identity recognition device includes: when a detection trigger condition is satisfied, acquiring a first image collected for the identity feature acquisition entrance of the identity recognition device; the satisfaction of the detection trigger condition includes at least one of reaching the attachment detection time, detecting an identity recognition trigger event, or the recognition statistical parameters of the identity recognition device satisfying a statistical parameter trigger condition.

13. The method according to any one of claims 1 to 11, wherein, the method further includes: in response to a resource transfer trigger event, determining a resource transfer parameter; determining a target resource account according to the identity recognition result of the identity feature image; performing resource transfer on the target resource account based on the resource transfer parameter.

14. An identity recognition device, wherein, the device includes: an image sensor, an identity feature acquisition entrance, and a processor; wherein, the image sensor performs image acquisition through the identity feature acquisition entrance; The processor is configured to obtain a first image collected by the image sensor through the identity feature acquisition entrance, extract image features from the first image to obtain the image features of the first image, perform attachment detection based on the image features to obtain a detection result based on the image features of the first image. When the detection result based on the image features of the first image indicates that there is no attachment at the identity feature acquisition entrance, obtain the distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image, and perform attachment detection based on the distance parameter to obtain a first detection result. When the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity recognition duration in the recognition statistical parameters of the identity recognition device meets the cleaning trigger condition, trigger a cleaning process for the identity feature acquisition entrance according to the cleaning mode corresponding to the parameters of the attachment. The recognition statistical parameters are used to characterize the sensitivity of the identity recognition device for historical identity recognition. The cleaning mode is determined based on the statistical record of the cleaning process for the identity feature acquisition entrance. After triggering the cleaning process, obtain a second image collected for the identity feature acquisition entrance, extract image features from the second image to obtain the image features of the second image, perform attachment detection based on the image features to obtain a detection result based on the image features of the second image. When the detection result based on the image features of the second image indicates that there is no attachment at the identity feature acquisition entrance, obtain the distance parameter between the identity feature acquisition entrance and the acquisition object included in the second image, and perform attachment detection based on the distance parameter to obtain a second detection result. When the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleaned, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image. When the second detection result indicates that the attachment at the identity feature acquisition entrance has not been cleaned, trigger the cleaning process for the identity feature acquisition entrance again. When the number of times of the cleaning process for the identity feature acquisition entrance reaches the number threshold and the attachment has not been cleaned, end the cleaning process for the identity feature acquisition entrance and send a prompt message to the control end to prompt the control end to perform a cleaning process for the identity feature acquisition entrance.

15. The device according to claim 14, wherein, the image sensor includes a visible light image sensor and an infrared image sensor; the attachment at the identity feature acquisition entrance includes water stains; the device further includes an infrared lamp; the processor is further configured to control the infrared lamp to start, so as to perform a cleaning process on the water stains at the identity feature acquisition entrance through the infrared lamp.

16. An identity recognition device, wherein, the device includes: The first image detection module is configured to obtain a first image collected through an identity feature acquisition entrance of an identity recognition device, extract image features from the first image to obtain the image features of the first image, perform attachment detection based on the image features to obtain a detection result based on the image features of the first image. When the detection result based on the image features of the first image indicates that there is no attachment at the identity feature acquisition entrance, obtain a distance parameter between the identity feature acquisition entrance and the acquisition object included in the first image, and perform attachment detection based on the distance parameter to obtain a first detection result; The attachment cleaning module is configured to, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity recognition duration in the recognition statistical parameters of the identity recognition device meets the cleaning trigger condition, trigger a cleaning process for the identity feature acquisition entrance according to the cleaning mode corresponding to the parameters of the attachment; the recognition statistical parameters are used to characterize the sensitivity of the identity recognition device for historical identity recognition; the cleaning mode is determined based on the statistical records of the cleaning process history of the identity feature acquisition entrance; The second image detection module is configured to, after triggering the cleaning process, obtain a second image collected through the identity feature acquisition entrance, extract image features from the second image to obtain the image features of the second image, perform attachment detection based on the image features to obtain a detection result based on the image features of the second image. When the detection result based on the image features of the second image indicates that there is no attachment at the identity feature acquisition entrance, obtain a distance parameter between the identity feature acquisition entrance and the acquisition object included in the second image, and perform attachment detection based on the distance parameter to obtain a second detection result; The identity recognition processing module is configured to, when the second detection result indicates that the attachment at the identity feature acquisition entrance has been cleaned, in response to collecting an identity feature image from the identity feature acquisition entrance, perform identity recognition based on the identity feature image; The device is further configured to, when the second detection result indicates that the attachment at the identity feature acquisition entrance has not been cleaned, trigger the cleaning process for the identity feature acquisition entrance again. When the number of times of the cleaning process for the identity feature acquisition entrance reaches the number threshold and the attachment has not been cleaned, end the cleaning process for the identity feature acquisition entrance and send a prompt message to the control end to prompt the control end to perform a cleaning process for the identity feature acquisition entrance.

17. The device according to claim 16, wherein, the first image includes a visible light image and an infrared image collected for the same acquisition object; The first image detection module is further configured to extract image features from the visible light image and the infrared image respectively, obtain the visible light image features of the visible light image and the infrared image features of the infrared image; fuse the visible light image features, the infrared image features and the distance features of the distance parameter to obtain detection features; and perform attachment detection based on the detection features to obtain a first detection result.

18. The apparatus according to claim 16, wherein, the obtaining of the first detection result is implemented based on an attachment detection model; the performing of attachment detection on the second image to obtain a second detection result is implemented based on the attachment detection model; and the apparatus further includes: a training sample acquisition module, configured to acquire a sample image and a distance sample parameter between the identity feature acquisition entrance and the acquisition object included in the sample image; the sample image and the distance sample parameter carry attachment detection labels; a sample feature extraction module, configured to extract image features of the sample image through the attachment detection model to be trained, to obtain the sample image features of the sample image; a sample detection module, configured to perform attachment detection through the attachment detection model to be trained based on the sample image features and the distance sample parameter, to obtain a sample detection result; a model update module, configured to update the attachment detection model to be trained based on the sample detection result and the attachment detection label, and continue training until the training is completed, to obtain the trained attachment detection model.

19. The apparatus according to claim 18, wherein, the sample image includes a visible light sample image and an infrared sample image.

20. The apparatus according to claim 16, wherein, the apparatus further includes: an identification statistical parameter determination module, configured to acquire historical identity identification data of the identity identification device; and determine the identification statistical parameter according to the historical identity identification data.

21. The apparatus according to claim 16, wherein, when the first detection result indicates that there is an attachment at the identity feature acquisition entrance and the identity identification duration in the identification statistical parameter of the identity identification device meets the cleaning trigger condition, the attachment cleaning module is further configured to perform a cleaning process on the identity feature acquisition entrance through the attachment cleaning device of the identity identification device.

22. The apparatus according to claim 21, wherein, the attachment at the identity feature acquisition entrance includes water stains; the attachment cleaning module is further configured to control the infrared lamp of the identity identification device to be turned on, so as to perform a cleaning process on the water stains at the identity feature acquisition entrance through the infrared lamp.

23. The apparatus according to claim 16, wherein, the apparatus further includes an attachment cleaning determination module, and the attachment cleaning determination module is configured to perform at least one of the following: when the second detection result indicates that no attachment is detected, determine that the attachment at the identity feature acquisition entrance has been cleaned; Determine the attachment distribution area based on the second detection result. When the attachment distribution area is smaller than the attachment distribution area determined based on the first detection result, it is determined that the attachments at the identity feature acquisition entrance have been cleared.

24. The device according to claim 16, wherein, the identity recognition processing module is further configured to, in response to an identity recognition trigger event, acquire an identity feature image collected from the identity feature acquisition entrance; perform identity information matching between the identity feature image and pre-stored registered identity information to perform identity recognition based on the identity feature image.

25. The device according to claim 24, wherein, the identity feature image is an image collected for the palm part; the registered identity information includes palmprint registration features and palm vein registration features obtained by performing identity registration on the palm of the registered user; the identity recognition processing module is further configured to extract palmprint features and palm vein features from the identity feature image; perform palmprint feature matching between the palmprint features and the palmprint registration features to obtain a palmprint feature matching result; perform palm vein feature matching between the palm vein features and the palm vein registration features to obtain a palm vein feature matching result; and obtain an identity recognition result according to the palmprint feature matching result and the palm vein feature matching result.

26. The device according to claim 16, wherein, the device further includes: a waiting prompt module, configured to, during the process of triggering the cleaning process, provide waiting prompt information for indicating that the user waits to perform identity recognition through the identity recognition device in a perceivable manner.

27. The device according to any one of claims 16 to 26, wherein, the first image detection module is further configured to, when a detection trigger condition is satisfied, acquire a first image collected for the identity feature acquisition entrance of the identity recognition device; the satisfaction of the detection trigger condition includes at least one of reaching the attachment detection time, detecting an identity recognition trigger event, or the recognition statistical parameters of the identity recognition device satisfying a statistical parameter trigger condition.

28. The device according to any one of claims 16 to 26, wherein, the device further includes: a resource transfer module, configured to, in response to a resource transfer trigger event, determine resource transfer parameters; determine a target resource account according to the identity recognition result of the identity feature image; and perform resource transfer on the target resource account based on the resource transfer parameters.

29. A computer device, including a memory and a processor, the memory stores a computer program, wherein, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 13 are implemented.

30. A computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

31. A computer program product, including a computer program, wherein, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 13.

Images