Abnormal recognition processing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of non-contact payment, and provides an abnormal recognition processing method and device, equipment and a storage medium. The method is used for solving the problem that the rejection rate of the hand-brushing equipment is relatively high, and comprises the following steps: when a to-be-recognized object is detected, creating a target recognition session, and based on the target recognition session, repeatedly executing the following operations until a session ending condition is met: based on the current shooting parameters of the hand-brushing equipment, executing the target recognition session; obtaining a to-be-recognized palm image of the to-be-recognized object, and performing feature extraction on the to-be-recognized palm image to obtain to-be-recognized palm features; matching the to-be-identified palm feature with each reference palm feature recorded in a palm feature library; when it is determined that the successfully matched reference palm features do not exist, the current shooting parameters are adjusted, and the adjusted shooting parameters are used for next shooting.

Description

Technical Field

[0001] This application relates to the field of contactless payment technology, and provides a method, apparatus, device and storage medium for identifying and handling anomalies. Background Technology

[0002] Palm scan payment is a payment method that uses a palm scan device to identify the palm print features of the payment recipient, thereby determining the recipient's information and processing the payment.

[0003] However, since palm payment is a relatively new payment method, there may be instances where the palm-swiping gesture differs from the gesture used when the palm print was previously recorded, or the palm may be obscured by clothing, leading to a rejection by the palm-swiping device. A rejection occurs when, although the person is registered, the palm-swiping device cannot identify their identity information because the palm print features do not match.

[0004] Furthermore, once the palm-swiping device refuses to accept payment, it repeatedly prompts the recipient to retry until the device successfully identifies them. This leads to long payment times and low efficiency when dealing with a large number of recipients. Therefore, reducing the rejection rate of palm-swiping devices is an urgent issue. Summary of the Invention

[0005] This application provides an anomaly identification method, apparatus, device, and storage medium to address the problem of high rejection rates in palm-swiping devices.

[0006] In a first aspect, embodiments of this application provide a method for identifying and handling anomalies, including:

[0007] When an object to be identified is detected, a target identification session is created, and based on the target identification session, the following operations are repeated until the session ends: Based on the current shooting parameters of the palm-scanning device, an image of the palm of the object to be identified is acquired, and feature extraction is performed on the palm image to obtain the palm features to be identified; The palm features to be identified are matched with each reference palm feature recorded in the palm feature library; If it is determined that there is no successfully matched reference palm feature, the current shooting parameters are adjusted, and the adjusted shooting parameters are used for the next shooting.

[0008] Secondly, embodiments of this application also provide an anomaly identification and handling device, including:

[0009] The detection unit is used to detect the object to be identified.

[0010] The session management unit is used to create a target identification session when an object to be identified is detected.

[0011] The identification unit is configured to repeatedly perform the following operations based on the target identification session until the session ends: based on the current shooting parameters of the palm-scanning device, acquire the palm image of the object to be identified, and extract features from the palm image to obtain the palm features to be identified; match the palm features to be identified with each reference palm feature recorded in the palm feature database; when it is determined that there is no successfully matched reference palm feature, adjust the current shooting parameters, and use the adjusted shooting parameters for the next shooting.

[0012] In one possible implementation, when the recognition unit determines that no successfully matched reference palm feature exists, after adjusting the current shooting parameters, it is further configured to: associate and save the palm image to be recognized as an abnormal palm image with the target recognition session; then, when the session termination condition is reached, the recognition unit is further configured to: if it is determined that at least one abnormal palm image is associated and saved with the target recognition session, filter the at least one abnormal palm image according to the degree of matching; extract features from the filtered target palm images to obtain target feature information; upload the obtained target feature information to the server so that the server associates the target feature information with the object to be recognized and sends the feature difference between the target feature information and the reference palm feature associated with the object to be recognized to the palm-scanning device; and update the palm feature database based on the received feature difference.

[0013] In one possible implementation, when the identification unit matches the palm feature to be identified with each reference palm feature recorded in the palm feature database, it is configured to: calculate the first similarity between the palm feature to be identified and each reference palm feature recorded in the palm feature database, and determine the reference palm features whose first similarity is greater than or equal to the qualifying similarity threshold as successfully matched reference palm features; the step of filtering the at least one abnormal palm image according to the matching degree includes: taking the abnormal palm image among the at least one abnormal palm images whose first similarity is greater than or equal to the intermediate similarity threshold as the target palm image; the intermediate similarity threshold is less than the qualifying similarity threshold.

[0014] In one possible implementation, after the identification unit associates and saves the palm image to be identified as an abnormal palm image with the target identification session, it is further configured to: if there are other abnormal palm images associated and saved with the target identification session, calculate a second similarity between the palm features to be identified and the palm features to be identified in the other abnormal palm images respectively; when there is a second similarity less than the substandard similarity threshold, determine that the session termination condition has been met; the substandard similarity threshold is less than the intermediate similarity threshold.

[0015] In one possible implementation, when the recognition unit filters the at least one abnormal palm image based on the degree of matching, it is configured to: display the at least one abnormal palm image; and, in response to the selection operation of the object to be identified on the at least one abnormal palm image, use the selected abnormal palm image as the target palm image.

[0016] In one possible implementation, the session termination condition further includes at least one of the following: determining that there is a successfully matched reference palm feature; detecting that the distance between the object to be identified and the palm-swiping device is greater than a preset distance threshold.

[0017] Thirdly, embodiments of this application also provide a computer device, including a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor performs the steps of any of the above-described exception handling methods.

[0018] Fourthly, embodiments of this application also provide a computer-readable storage medium including program code, which, when the program product is run on a computer device, is used to cause the computer device to perform the steps of any of the above-described anomaly identification and handling methods.

[0019] Fifthly, embodiments of this application also provide a computer program product, including computer instructions, which are executed by a processor using the steps of any of the above-described anomaly identification and handling methods.

[0020] The beneficial effects of this application are as follows:

[0021] This application provides an anomaly identification method, apparatus, device, and storage medium. The method can create a target identification session associated with the object to be identified when the object to be identified is detected, and perform palm recognition in the identification session. This can avoid the situation where the palm image to be identified is mistakenly saved with other objects, thereby ensuring the information security of the object to be identified.

[0022] When a palm-scanning device repeatedly uses the same parameters to capture images, the resulting palm images and extracted palm features may all be identical. In this case, because the same features are repeatedly matched, the results are also identical. If a match fails, the number of rejections unnecessarily increases. However, the recognition anomaly handling method provided in this application can adjust the shooting parameters when the palm image acquired based on the current shooting parameters fails to match the reference palm features. Therefore, this situation can be avoided, improving the matching success rate when acquiring the next palm image and thus reducing the rejection rate of the palm-scanning device.

[0023] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0025] Figure 1 This is an optional schematic diagram of an application scenario in the embodiments of this application;

[0026] Figure 2 A flowchart illustrating the anomaly identification and handling method provided in this application embodiment;

[0027] Figure 3 A schematic diagram illustrating the feature matching process provided in this application embodiment;

[0028] Figure 4 A schematic diagram of a parameter adjustment process provided in an embodiment of this application;

[0029] Figure 5 This is a schematic diagram illustrating another parameter adjustment process provided in an embodiment of this application;

[0030] Figure 6 This is a schematic diagram of the reminder information provided in the embodiments of this application;

[0031] Figure 7 This is a schematic diagram of the abnormal palm image selection process provided in an embodiment of this application;

[0032] Figure 8 A schematic diagram of the system architecture for the anomaly identification and handling method provided in the embodiments of this application;

[0033] Figure 9 An exemplary flowchart of the anomaly identification and handling method provided in the embodiments of this application;

[0034] Figure 10 This is an exemplary information interaction flowchart of the anomaly identification and handling method provided in the embodiments of this application;

[0035] Figure 11 This is a schematic diagram of the structure of an anomaly identification and processing device provided in an embodiment of this application;

[0036] Figure 12This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application;

[0037] Figure 13 This is a schematic diagram of the hardware structure of another computer device that applies an embodiment of this application. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this application. Obviously, the described embodiments are only some embodiments of the technical solutions of this application, and not all embodiments. Based on the embodiments recorded in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the technical solutions of this application.

[0039] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0040] (1) Palm recognition: a technology that identifies the identity information of payment recipients by identifying features such as palm prints and veins on the palm.

[0041] (2) Palm recognition device: A terminal device that uses palm recognition technology to identify the identity information of the payment recipient, thereby enabling the payment recipient to complete the payment operation.

[0042] (3) 3D camera: including depth camera and infrared camera. Compared with traditional camera, it adds software and hardware related to liveness detection to ensure information security.

[0043] The design concept of the embodiments of this application is briefly introduced below:

[0044] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0045] Palm payment is a new type of payment method that uses artificial intelligence technology to identify the palm print features of the payment recipient through a palm-scanning device, thereby determining the recipient's information and processing the payment.

[0046] However, since palm payment is a relatively new payment method, there may be instances where the palm-swiping gesture differs from the gesture used when the palm print was previously recorded, or the palm may be obscured by clothing, leading to a rejection by the palm-swiping device. A rejection occurs when, although the person is registered, the palm-swiping device cannot identify their identity information because the palm print features do not match.

[0047] Furthermore, once the palm-swiping device refuses to accept payment, it repeatedly prompts the recipient to retry until the device successfully identifies them. This leads to long payment times and low efficiency when dealing with a large number of recipients. Therefore, reducing the rejection rate of palm-swiping devices is an urgent issue.

[0048] In view of this, embodiments of this application provide a method, apparatus, device, and storage medium for identifying anomalies. The method can be applied to a palm-scanning device and includes: when an object to be identified is detected, creating a target identification session, and repeatedly performing the following operations based on the target identification session until the session termination condition is met: acquiring an image of the palm of the object to be identified based on the current shooting parameters of the palm-scanning device, and extracting features from the image to obtain palm features; matching the palm features to be identified with each reference palm feature recorded in a palm feature database; when it is determined that no successfully matched reference palm feature exists, adjusting the current shooting parameters, and using the adjusted shooting parameters for the next shooting.

[0049] By using the above method, when the identity information of the subject cannot be identified based on the current palm image, the shooting parameters of the palm scanning device can be adjusted, thereby improving the matching success rate when acquiring the palm image next time, and thus reducing the rejection rate of the palm scanning device.

[0050] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0051] Figure 1 One application scenario is shown, which includes a swipe device 110 and a server 120. The swipe device 110 can establish a communication connection with the server 120 through a wired network or a wireless network.

[0052] The palm-scanning device 110 can be used to detect objects to be identified and, upon detection, create a target recognition session. In this session, an image of the hand to be identified is acquired, and features are extracted from this image to obtain hand features. These features are then matched against reference hand features recorded in the hand feature library within the device. If a match fails, the shooting parameters are adjusted, and a new hand image is acquired using the adjusted parameters. The hand features from this new image are then matched against the reference hand features recorded in the hand feature library until the session ends.

[0053] Optionally, if at least one hand image fails to be recognized when the session ends, the target feature information of each of the at least one failed hand image can be uploaded to the server 120. This allows the server 120 to associate the target feature information with the object to be recognized and send the feature differences between the target feature information and the reference hand features associated with the object to be recognized to the palm-scanning device 110.

[0054] The palm-scanning device 110 can update the palm feature database based on the received feature differences.

[0055] The server 120 in this application embodiment can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. This application does not impose any restrictions on these services.

[0056] Figure 1 The application scenarios shown are merely illustrative, and this application does not limit the number of the palm-swiping devices 110.

[0057] based on Figure 1 For the application scenarios shown, please refer to [link / reference]. Figure 2 This is an exemplary flowchart of an anomaly identification and handling method provided in an embodiment of this application. This process can be applied to… Figure 1 The palm-swiping device 110 includes steps 201-202, and step 202 further includes steps 2021-2023:

[0058] Step 201: When an object to be identified is detected, create a target identification session.

[0059] In one possible implementation, the palm-swiping device can detect the presence of an object to be identified in real time within the detection range using millimeter-wave radar after powering on. After detecting the presence of an object to be identified, it can further detect the movement trajectory of the object to be identified, such as the object approaching or moving away.

[0060] The palm-swiping device can create a target recognition session associated with the target object when it detects the presence of the object within its detection range and the object approaches. Step 202 is then executed within this target recognition session. "Approaching" can refer to the distance between the target object and the palm-swiping device being less than or equal to a preset distance threshold.

[0061] In some embodiments, to enable the palm-swiping device to perform high-performance detection and motion trajectory recognition of the object to be identified, a millimeter-wave radar module with high resolution, large detection range, and high sensitivity can be configured in the palm-swiping device. The millimeter-wave radar module may include an integrated antenna array, a signal processor, and a data interface. When detecting the object to be identified using the millimeter-wave radar module, the signal processor can process the raw data generated by the antenna array using signal processing algorithms to obtain information such as the position, velocity, and angle of the object to be identified. Then, the signal processor can also perform real-time detection of the approach and departure of the object to be identified using target detection and target tracking algorithms, and send the detected information to the session management module in the palm-swiping device through the data interface, enabling the session management module to create and close identification sessions.

[0062] The antenna array can be a linear array or a planar array, which can be selected according to the actual application scenario and detection requirements; this application does not impose any limitation on this. A linear array can realize one-dimensional distance and velocity measurement, while a planar array can realize two-dimensional distance, velocity, and angle measurement.

[0063] Signal processing algorithms, target detection algorithms, and target tracking algorithms can all be selected based on actual conditions or experience, and this application does not impose any limitations on them. For example, signal processing algorithms can include Fast Fourier Transform (FFT), Doppler processing, clutter suppression, and constant false alarm rate (CFAR) control. Target detection algorithms can include Constant False Alarm Rate (CFAR) detection and Kalman filters. Target tracking algorithms can include multi-target tracking algorithms, such as Multiple Hypothesis Tracking (MHT) and Probabilistic Data Association (PDA).

[0064] Step 202: Based on the target recognition session, repeat steps 2021-2023 until the session termination condition is met:

[0065] Step 2021: Based on the current shooting parameters of the palm-scanning device, acquire the palm image of the object to be identified, and extract features from the palm image to obtain the palm features to be identified.

[0066] The palm-scanning device can capture an image of the palm of the object to be identified using a 3D camera based on the current shooting parameters, and then extract the features of the palm to be identified through the feature extraction module.

[0067] The current shooting parameters of the palm-scanning device can refer to the current parameters of the 3D camera included in the device, such as the 3D camera's field of view (FOV), frame rate, and resolution. The palm features to be identified mainly include palm print features and hand shape features.

[0068] Optionally, during feature extraction, features of clothing, watches, and other accessories of the object to be identified can also be extracted and used as one of the features of the hand to be identified.

[0069] Step 2022: Match the palm features to be identified with each of the reference palm features recorded in the palm feature database.

[0070] The palm feature database can be pre-configured in the palm-scanning device. When a new palm feature is found, the server can update the palm feature database in each palm-scanning device connected to the server via the network.

[0071] Optionally, the palm feature library in the palm-swiping device can be implemented using a lightweight database, for example, by configuring a lightweight database (SQLite) in the palm-swiping device.

[0072] In one possible implementation, step 2022 can be specifically performed as follows: calculate the first similarity between the palm feature to be identified and each reference palm feature recorded in the palm feature database, and determine the reference palm features whose first similarity is greater than or equal to the qualifying similarity threshold as successfully matched reference palm features.

[0073] In one example, see Figure 3 This is a schematic diagram illustrating the feature matching process provided in an embodiment of this application. Figure 3As shown, assuming the palm feature database includes n reference palm features: reference palm feature 1, reference palm feature 2, ..., reference palm feature n. Then, during feature matching, the first similarity S1 between the palm feature to be identified and reference palm feature 1, the first similarity S2 between the palm feature to be identified and reference palm feature 2, ..., the first similarity Sn between the palm feature to be identified and reference palm feature n can be calculated, resulting in a first similarity set composed of S1, S2, ..., Sn. If there is a similarity greater than or equal to the qualifying similarity threshold in the first similarity set, the match is considered successful, and the session ends. If there is no similarity greater than or equal to the qualifying similarity threshold in the first similarity set, the match is considered unsuccessful, and step 2022 continues.

[0074] For example, if S1 in the first similarity set is greater than the qualifying similarity threshold, then the match is considered successful, and the session ends. If S1, S2...Sn in the first similarity set are all less than the qualifying similarity threshold, then the match is considered unsuccessful, and step 2022 continues.

[0075] Optionally, a distance metric or a similarity metric can be used to determine the first similarity. The distance metric calculates the distance between the hand feature to be identified and each reference hand feature, and determines the first similarity based on this distance. This distance is negatively correlated with the first similarity and can be Euclidean distance, Manhattan distance, etc., which are not limited in this application. The similarity metric directly calculates the first similarity between the hand feature to be identified and each reference hand feature. The first similarity can be cosine similarity, correlation coefficient, etc., which are not limited in this application.

[0076] It should be noted that the threshold value for achieving the first similarity score varies depending on the method used to calculate it. For example, if the first similarity score is expressed as a similarity score with a maximum of 100 points, then the threshold value for achieving the first similarity score could be 80 points. This application does not impose any limitation on this.

[0077] Step 2023: If it is determined that there is no successfully matched reference palm feature, adjust the current shooting parameters and use the adjusted shooting parameters for the next shooting.

[0078] If no matching reference hand feature is found, the match is considered a failure. Matching failure may be due to one of the following two situations: Situation 1: The object to be identified is not registered in the application corresponding to the palm-swiping device; Situation 2: The object to be identified is registered in the application corresponding to the palm-swiping device, but due to the object's posture, palm being obscured by clothing, or other reasons, a matching reference hand feature cannot be determined.

[0079] In the first scenario, the object to be identified may attempt palm recognition due to interest in the palm-swiping device. However, since the palm feature database does not contain the corresponding palm feature of this object, even adjusting the shooting parameters will not identify its identity information. In other words, the identification anomaly handling method provided in this application embodiment is mainly applicable to the second scenario.

[0080] In one example, when the object to be identified has been registered in the application corresponding to the palm-swiping device, the reason for the mismatch may be that the palm of the object to be identified is too close or too far from the position of the 3D camera of the palm-swiping device. In this case, the field of view (FOV) of the 3D camera can be adjusted to adjust the shooting range of the 3D camera, so that the palm image captured next time is closer to the palm image captured when the object to be identified was registered, thereby improving the accuracy of the feature matching of the palm-swiping device.

[0081] See Figure 4 This is a schematic diagram illustrating a parameter adjustment process provided in an embodiment of this application. Figure 4 As shown, under the current shooting parameters, the palm-scanning device can acquire image A of the hand to be recognized. However, because the hand of the object to be recognized is placed too close to the position of the 3D camera of the palm-scanning device, the hand of the object to be recognized in image A is not complete. In order to obtain a complete image of the hand of the object to be recognized, the FOV can be increased when adjusting the shooting parameters, so that the hand image B to be recognized in the next shooting can contain the complete image of the hand of the object to be recognized.

[0082] See another example. Figure 5 This is a schematic diagram illustrating another parameter adjustment process provided in an embodiment of this application. For example... Figure 5 As shown, under the current shooting parameters, the palm-scanning device can acquire an image C of the hand to be recognized. However, due to factors such as the ring light around the camera of the palm-scanning device not being turned on or malfunctioning, the image C of the hand to be recognized is relatively dark, making it impossible to accurately extract the hand features. Therefore, when adjusting the shooting parameters, the brightness of the image of the hand to be recognized can be adjusted by increasing the aperture, so that the image D of the hand to be recognized can be brighter in the next shot, allowing for accurate extraction of the hand features.

[0083] In another example, even when the object to be identified is already registered in the application corresponding to the palm-swiping device, the matching and identification might fail because the object's clothing obscures the palm, causing the camera's focus to be on the clothing. This results in the palm portion in the acquired palm image being too blurry to extract accurate palm features. In this case, adjusting the 3D camera's focal length and other shooting parameters can make the palm portion clearer in the next captured image, thereby improving the accuracy of the palm-swiping device's feature matching.

[0084] Optionally, if it is determined that no matching reference palm feature exists, a message can be displayed in the palm-swiping device to remind the object to be identified to adjust its palm-swiping posture, for example, see [link to relevant documentation]. Figure 6 This is a schematic diagram illustrating the reminder information provided in an embodiment of this application. For example... Figure 6 As shown, when the palm of the object to be identified is detected to be too close to the camera, the device can display "Please move your palm away from the camera" to remind the object to move their palm away from the camera.

[0085] Alternatively, if no matching reference hand feature is found, the palm-scanning device can use voice prompts to remind the subject to adjust their palm-scanning posture. For example, if the device detects that the subject's palm is too close to the camera, it can announce "Please move your palm away from the camera" to remind the subject to move their palm away from the camera.

[0086] In one possible implementation, to address the matching failure caused by the second scenario, after executing step 2023, the palm image to be identified can be associated with and saved as an abnormal palm image in the target recognition session. Then, after the session termination condition is met, if it is determined that at least one abnormal palm image is associated with and saved in the target recognition session, the at least one abnormal palm image is filtered based on the matching degree. Then, feature extraction can be performed on the filtered target palm images to obtain target feature information. Next, the palm-scanning device can upload the obtained target feature information to the server, so that the server associates the target feature information with the object to be identified and sends the feature difference between the target feature information and the reference palm features associated with the object to be identified to the palm-scanning device. Upon receiving the feature difference, the palm-scanning device can update its palm feature database based on that feature difference.

[0087] In some embodiments, after determining that the session termination condition has been met, if it is determined that there is no abnormal palm image associated with and saved in the target recognition session, the target recognition session can be terminated and the data in the target recognition session can be cleared.

[0088] The above method can expand the palm features corresponding to the object to be identified, so that when the object to be identified performs palm recognition again, the reference palm features that match the palm features of the object to be identified can be determined more quickly and accurately, thereby improving the recognition efficiency of the palm recognition device and solving the problem of rejection in the palm recognition device in related technologies.

[0089] In one possible implementation, to speed up the loading of abnormal hand images, these images can be cached in the memory of the application corresponding to the hand-swiping device. For example, the LruCache class can be used to implement memory caching. Specifically, the size of LruCache can first be initialized in the constructor, and the sizeOf method can be overridden. Then, a bitmap can be added to the cache using the addBitmapToMemoryCache method, and a bitmap can be retrieved from the cache using the getBitmapFromMemCache method, thus achieving memory caching.

[0090] In some embodiments, when the palm-scanning device filters at least one abnormal palm image based on the degree of matching, it may select an abnormal palm image among the at least one abnormal palm images whose first similarity is greater than or equal to an intermediate similarity threshold as the target palm image. The intermediate similarity threshold is less than the aforementioned qualifying similarity threshold.

[0091] Since the abnormal hand images are all images saved in association with the target recognition session, they are likely to be hand images of the object to be identified to a large extent. Therefore, the similarity threshold can be appropriately lowered to filter the target hand images that need to be uploaded. For example, assuming the first similarity is expressed as a score, the acceptable similarity threshold can be 80 points, and the intermediate similarity threshold can be 60 points.

[0092] In one possible implementation, the palm-scanning device can also pre-store a facial feature database. When filtering at least one abnormal palm image based on the matching degree, a facial image of the object to be identified can be acquired via a 3D camera, and features can be extracted from that facial image to obtain the facial features of the object to be identified. The facial features of the object to be identified are matched with each reference facial feature in the facial feature database. If there is a reference facial feature among the reference facial features that is greater than or equal to the qualifying similarity threshold, the abnormal palm image with a first similarity greater than the non-qualifying similarity threshold among the at least one abnormal palm image can be used as the target palm image. If there is no reference facial feature among the reference facial features that is greater than or equal to the qualifying similarity threshold, all data of the target recognition session is cleared.

[0093] When facial recognition passes, the criteria for determining whether an abnormal hand image is the target hand image can be further lowered. For example, the intermediate similarity threshold is 60 points, and the unqualified similarity threshold is 40 points. Before the introduction of facial recognition, only abnormal hand images with a similarity score greater than 60 points were considered target hand images. After the introduction of facial recognition, abnormal hand images with a similarity score greater than 40 points can be considered target hand images.

[0094] By using the above method, since the criteria for determining a palm image as a target image are lowered, the number of abnormal palm images that can be identified as target palm images can be increased. With a larger number of target palm images, the reference palm features of the object to be identified in the palm feature library can be expanded more, reducing the probability that the object to be identified will fail to be identified in the next palm recognition, thereby reducing the rejection rate of the palm scanning device.

[0095] It should be noted that the 3D camera must obtain the authorization of the person to be identified before it can be used to obtain their facial image.

[0096] In other embodiments, when the palm-scanning device filters at least one abnormal palm image based on the degree of matching, it may also display at least one abnormal palm image on the palm-scanning device, allowing the subject to be identified to select one or more abnormal palm images belonging to itself on the display screen of the palm-scanning device. Then, in response to the subject's selection operation of one or more abnormal palm images, the palm-scanning device may use the selected abnormal palm image as the target palm image.

[0097] See Figure 7 This is a schematic diagram illustrating the abnormal palm image selection process provided in an embodiment of this application. Assuming that four abnormal palm images are determined to be associated with the target recognition session, then... Figure 7 The screen displays four images of abnormal palms, and above each image, it displays "Please select your palm image:" to prompt the user to make a selection. The user can select the abnormal palm image by clicking, and then confirm the selection by clicking the confirmation button. The palm scanning device responds to the user's confirmation by using the selected abnormal palm image as the target palm image.

[0098] In some other embodiments, when the palm-scanning device filters at least one abnormal palm image based on the degree of matching, it may also display abnormal palm images among the at least one abnormal palm images whose first similarity is greater than or equal to an intermediate similarity threshold in the palm-scanning device, so that the object to be identified can select one or more abnormal palm images belonging to itself on the display screen of the palm-scanning device. Then, in response to the object to be identified's selection operation of one or more abnormal palm images belonging to itself, the palm-scanning device may use the selected abnormal palm image as the target palm image.

[0099] In one possible implementation, to achieve real-time updates of the palm feature database, an incremental update method can be used when updating the palm feature database in the palm-scanning device. The server can update the database with features that differ from the original palm feature database whenever the palm features in the database change or are added. Features that do not need updating or have already been updated will not be updated again.

[0100] In another possible implementation, to ensure data consistency, a full update can be used when updating the palm feature database in the palm-scanning devices. The server can periodically or sequentially replace the palm feature databases in each palm-scanning device with the server's palm feature database. For example, the palm feature databases in each palm-scanning device can be completely replaced with the server's palm feature database every day at midnight.

[0101] In another possible implementation, updating the palm feature database in the palm-scanning device can combine incremental and full updates. For example, the server can update the database with features that differ from the original palm feature database whenever palm features in the database change or are added. Then, a full update of the palm feature database in the palm-scanning device can be performed weekly, ensuring both data consistency and real-time updates of the palm feature database.

[0102] In one possible implementation, after the image of the hand to be identified is associated with and saved as an abnormal hand image in the target recognition session, if other abnormal hand images are associated with and saved in the target recognition session, a second similarity is calculated between the features of the hand to be identified and the features of the hand to be identified in the other abnormal hand images. If a second similarity score below a threshold indicating a failure to meet the minimum similarity requirement is found, the session termination condition is determined, where the threshold indicating a failure to meet the minimum similarity requirement is less than an intermediate similarity threshold.

[0103] For example, assuming the second similarity is represented as a score, the intermediate similarity threshold can be 60 points, and the unsatisfactory similarity threshold can be 40 points. When a second similarity score of less than 40 points exists, it can be determined that data from other objects may have been mistakenly included in the target recognition session. To ensure the information security of the object to be identified and to avoid the situation where data from other objects is associated with and saved with the data of the object to be identified, it can be determined that the session termination condition has been met, and the data in the target recognition session can be cleared.

[0104] Optionally, since the clothing or accessories of the object to be identified usually do not change in the same target recognition session, when calculating the second similarity between the palm features to be identified and the palm features to be identified in other abnormal palm images, it can be calculated by calculating the similarity between the accessory features in the palm image to be identified and the accessory features in other abnormal palm images. This determines whether at least one abnormal palm image associated with the target recognition session belongs to the same object. If they do not belong to the same object, it can be determined that the session termination condition has been met, and the data in the target recognition session can be cleared.

[0105] In another possible implementation, in order to ensure the information security of the object to be identified and to avoid the situation where the data of other objects are associated with and saved with the data of the object to be identified, if the first similarity between the palm feature to be identified and each reference palm feature is less than the substandard similarity threshold when executing step 2022, then it is determined that the session termination condition has been met.

[0106] In one possible implementation, in addition to the two conditions mentioned above, the session termination condition can also be one or more of the following conditions (1)-(3):

[0107] (1) Identify the reference palm features that have a successful match.

[0108] Once a matching reference palm feature is identified, the palm-swiping device can obtain the identity information of the person to be identified via the network, and then obtain the payment information of the person to be identified based on the identity information to complete the payment operation. Therefore, it can be determined that the session termination condition has been met.

[0109] (2) The distance between the object to be identified and the palm-swiping device is detected to be greater than the preset distance threshold.

[0110] To enhance the security of the identity information of the object to be identified, if the distance between the object to be identified and the palm-swiping device exceeds a preset distance threshold, it can be confirmed that the object has left the palm-swiping device, ending the payment operation. Therefore, the session termination condition can be determined, and the data in the target identification session can be cleared. The data in the target identification session may include: abnormal palm images associated with the target identification session, the identity information of the identified object, etc.

[0111] (3) The distance between the new object to be identified and the palm-swiping device is less than or equal to the preset distance threshold.

[0112] To avoid situations that could affect payment security, such as recognition errors, the recognition session and the object to be recognized must be in one-to-one correspondence. Therefore, when a new object to be recognized is detected to be less than or equal to a preset distance threshold, it can be determined that the session has reached the end condition and the data in the target recognition session can be cleared.

[0113] In one possible implementation, the palm-scanning device can display a prompt asking the subject whether to upload an image of an abnormal palm. If the subject confirms the upload, the palm-scanning device can upload the obtained target feature information to the server in response to the subject's confirmation. For example, the subject can confirm the upload by clicking a confirmation button. If the subject refuses to upload, the palm-scanning device can terminate the process in response to the subject's refusal and will not upload the target feature information to the server.

[0114] After receiving the target feature information and associating it with the object to be identified, the server can use this information to train its palm recognition capabilities. Subsequent palm recognition attempts on the same object will then match it with the previously uploaded target feature information, thereby improving recognition efficiency and reducing the rejection rate of the palm recognition device.

[0115] See Figure 8 This is a schematic diagram of the system architecture for the anomaly identification and handling method provided in this application embodiment. The system may include a palm-swiping device and a server. The palm-swiping device may include a millimeter-wave radar module, a 3D camera, a feature extraction module, a palm-swiping recognition module, a session management module, a storage module, a display module, a security module, a network module, etc.

[0116] Among them, the millimeter-wave radar module can use millimeter-wave radar to perform high-precision distance, speed and angle measurements on objects to be identified within a set range.

[0117] 3D cameras can be used to capture images of the hand of an object to be identified.

[0118] The feature extraction module can be used to extract features from the image of the hand to be identified, thereby obtaining the features of the hand to be identified.

[0119] The palm recognition module can perform feature matching on the palm of the person being identified to obtain their identity information. Furthermore, the module can also perform liveness detection to prevent the use of someone else's photo for palm payment.

[0120] The session management module can create a target recognition session when the millimeter-wave radar module identifies the object to be identified, and terminate the session when the session termination conditions are met.

[0121] The storage module can be used to store a palm feature library as well as abnormal palm images associated with the target recognition session.

[0122] The display module can be used to display reminder information, abnormal palm images that require the selection of the object to be identified, payment results, etc.

[0123] The security module can be implemented through a security chip to ensure the network security of the swipe device.

[0124] The network module is used to establish a network connection with the palm recognition service on the server side. For example, it can upload target feature information to the server and receive feature differences sent by the server.

[0125] The server-side can include services such as palm recognition, identity verification, and payment. The palm recognition service includes a feature database and a feature retrieval service. The feature database stores the mapping relationship between each registered object and palm features. Registered objects represent objects registered in the application corresponding to the palm recognition device. The feature retrieval service provides this service when the palm recognition device cannot identify the identity information of the object corresponding to the palm features being identified; that is, it retrieves the identity information of the object corresponding to the palm features being identified from the feature database. The identity verification service is used to obtain the identity information of the object to be identified. The payment service can be used to further obtain the payment information of the object to be identified based on the obtained identity information.

[0126] See Figure 9 This is an exemplary flowchart of an anomaly identification and handling method provided in an embodiment of this application. The process may include the following steps: 901-911.

[0127] Step 901: Detect the object to be identified.

[0128] The millimeter-wave radar module of the palm-swiping device can detect in real time whether there is an object to be identified within a specified range. When an object to be identified is detected, step 902 is executed.

[0129] It should be noted that during the execution of steps 902-911, step 901 is still executed in real time. If the target object is detected to have left the specified range, the target recognition session will end.

[0130] Step 902: Create a target recognition session.

[0131] Create a target identification session associated with the object to be identified, and continue to execute steps 903-907 in that target identification session.

[0132] Step 903: Obtain the image of the hand to be identified.

[0133] Under the current shooting parameters, the 3D camera of the palm-scanning device acquires an image of the palm to be recognized.

[0134] Step 904: Extract features from the image of the hand to be identified to obtain the hand features.

[0135] Step 905: Match the palm features to be identified with each of the reference palm features recorded in the palm feature database.

[0136] It should be noted that the matching method can be found in [reference needed]. Figure 2 The relevant descriptions in the method embodiments shown will not be repeated here.

[0137] Step 906: Was the match successful?

[0138] If a matching reference hand feature exists, the match is considered successful, and step 908 is executed; otherwise, the match is considered unsuccessful, and step 907 is executed.

[0139] It should be noted that the method for confirming the existence of a successfully matching reference palm feature can be found in [link to relevant documentation]. Figure 2 The relevant descriptions in the method embodiments shown will not be repeated here.

[0140] Step 907: Adjust shooting parameters.

[0141] It should be noted that the parameters and adjustment methods can be configured based on the actual situation or experience. This application does not limit the parameters and adjustment methods.

[0142] Step 908: Is there an abnormal palm image?

[0143] Determine if there is an abnormal palm image associated with the target recognition session. If it exists, proceed to step 909; otherwise, end the process.

[0144] It should be noted that the process termination means the end of the identification anomaly handling process provided in this application embodiment. The subsequent identity information identification and payment processes are not shown in this flowchart.

[0145] Step 909: Determine the target hand image.

[0146] The method for identifying the target hand image in an abnormal hand image can be found in [reference needed]. Figure 2 The relevant descriptions in the method embodiments shown will not be repeated here.

[0147] Step 910: Upload target feature information.

[0148] Once the target hand image is determined, feature extraction can be performed on the target hand image to obtain target feature information, and the obtained target feature information can be uploaded to the server.

[0149] Step 911: Update the palm feature library based on the obtained feature differences.

[0150] After the server sends the feature differences to the palm scanning device, the palm scanning device can update the palm feature library based on the acquired feature differences, and perform feature matching based on the updated palm feature library the next time it acquires a palm image to be recognized.

[0151] See Figure 10 This is an exemplary information interaction flowchart of the anomaly identification handling method provided in the embodiments of this application, used to represent the information interaction between the object to be identified, the swiping device, and the server. The flowchart may include the following steps 1001-1013.

[0152] Step 1001: Power on the palm-swiping device and start the millimeter-wave radar module.

[0153] Step 1002: The object to be identified swipes its palm within the specified range of the palm-swiping device.

[0154] Step 1003: In the target recognition session, if the hand features to be identified fail to match multiple times, cache the abnormal hand image each time a match fails.

[0155] This process can be found in [reference]. Figure 9 Steps 903-907 shown will not be repeated here.

[0156] Furthermore, during step 1003, a second similarity can be calculated between the palm features to be identified and the palm features to be identified in other abnormal palm images. This allows for determination of whether a second similarity below a threshold exists, thus confirming whether the session termination condition has been met. This process can participate in… Figure 2 The relevant descriptions in the method embodiments shown will not be repeated here.

[0157] Step 1004: The millimeter-wave radar module checks whether the session termination condition has been met.

[0158] The millimeter-wave radar module determines whether the session termination condition has been met by detecting whether the object to be identified has left the designated range, or whether a new object to be identified has entered the designated range and started scanning.

[0159] It should be noted that this step can be performed in real time during the execution of step 1003.

[0160] Step 1005: Match successful.

[0161] Upon successful matching, the system can request the identity information and payment information of the object to be identified from the server.

[0162] Step 1006: Return the result.

[0163] The server can return identity information and payment result information to the swipe device.

[0164] Step 1007: Display the image of the abnormal palm.

[0165] Displaying abnormal hand images allows the target person to select the target hand image and confirm the upload.

[0166] Step 1008: Select the target hand image and confirm the upload.

[0167] Step 1009: Upload the target feature information corresponding to the target hand image.

[0168] The palm-scanning device can extract features from a target palm image, obtain target feature information, and then upload the target feature information to the server.

[0169] Step 1010: Return the result.

[0170] The palm-swiping device can return payment result information and upload result information to the object to be identified, such as displaying the relevant information on the screen.

[0171] Step 1011: Train the ability to recognize palm prints.

[0172] The server can train the palm recognition capability based on the target feature information.

[0173] Step 1012: Send feature differences.

[0174] The server can send feature differences to the swipe device.

[0175] Step 1013: Update the palm feature database.

[0176] The palm-scanning device can update the palm feature database based on feature differences.

[0177] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0178] Based on the same inventive concept as the above-described method embodiments, this application also provides an anomaly identification and handling device. For example... Figure 11 The anomaly detection and handling device 1100 shown may include:

[0179] Detection unit 1101 is used to detect the object to be identified;

[0180] The session management unit 1102 is used to create a target identification session when an object to be identified is detected;

[0181] The identification unit 1103 is used to repeatedly perform the following operations based on the target identification session until the session ends: based on the current shooting parameters of the palm-scanning device, acquire the palm image of the object to be identified, and extract features from the palm image to obtain the palm features to be identified; match the palm features to be identified with each reference palm feature recorded in the palm feature library; when it is determined that there is no successfully matched reference palm feature, adjust the current shooting parameters, and use the adjusted shooting parameters for the next shooting.

[0182] In one possible implementation, when the recognition unit 1103 determines that there is no successfully matched reference palm feature, after adjusting the current shooting parameters, it is further configured to: associate and save the palm image to be recognized as an abnormal palm image with the target recognition session.

[0183] When the session termination condition is met, the identification unit 1103 is further configured to: if it is determined that at least one abnormal palm image is associated with and saved in the target identification session, then filter the at least one abnormal palm image according to the matching degree; extract features from the filtered target palm images to obtain target feature information; upload the obtained target feature information to the server so that the server associates the target feature information with the object to be identified, and sends the feature difference between the target feature information and the reference palm features associated with the object to be identified to the palm-scanning device; and update the palm feature database based on the received feature difference.

[0184] In one possible implementation, when the identification unit 1103 matches the palm feature to be identified with each reference palm feature recorded in the palm feature library, it is configured to: calculate the first similarity between the palm feature to be identified and each reference palm feature recorded in the palm feature library, and determine the reference palm feature whose first similarity is greater than or equal to the qualifying similarity threshold as a successfully matched reference palm feature; the step of filtering the at least one abnormal palm image according to the matching degree includes: taking the abnormal palm image among the at least one abnormal palm image whose first similarity is greater than or equal to the intermediate similarity threshold as the target palm image; the intermediate similarity threshold is less than the qualifying similarity threshold.

[0185] In one possible implementation, after the identification unit 1103 associates and saves the palm image to be identified as an abnormal palm image with the target identification session, it is further configured to: if there are other abnormal palm images associated and saved with the target identification session, calculate the second similarity between the palm features to be identified and the palm features to be identified in the other abnormal palm images respectively; when there is a second similarity less than the substandard similarity threshold, determine that the session termination condition has been met; the substandard similarity threshold is less than the intermediate similarity threshold.

[0186] In one possible implementation, when the recognition unit 1103 filters the at least one abnormal palm image according to the matching degree, it is used to: display the at least one abnormal palm image; and in response to the selection operation of the object to be identified on the at least one abnormal palm image, use the selected abnormal palm image as the target palm image.

[0187] In one possible implementation, the session termination condition further includes at least one of the following: determining that there is a successfully matched reference palm feature; detecting that the distance between the object to be identified and the palm-swiping device is greater than a preset distance threshold.

[0188] For ease of description, the above sections are divided into modules (or units) according to their functions and described separately. In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program with a predetermined function, which works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functions of that module or unit.

[0189] Having introduced the anomaly identification and processing method and apparatus according to exemplary embodiments of this application, we will now introduce a computer device according to another exemplary embodiment of this application.

[0190] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0191] Based on the same inventive concept as the above-described method embodiments, this application also provides a computer device. In one embodiment, the computer device may be a server. In this embodiment, the structure of the computer device is as follows: Figure 12 As shown, it may include at least a memory 1201, a communication module 1203, and at least one processor 1202.

[0192] The memory 1201 is used to store computer programs executed by the processor 1202. The memory 1201 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0193] Memory 1201 may be volatile memory, such as random-access memory (RAM); memory 1201 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 1201 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 1201 may be a combination of the above-described memories.

[0194] The processor 1202 may include one or more central processing units (CPUs) or digital processing units, etc. The processor 1202 is used to implement the above-described anomaly detection and handling method when it calls a computer program stored in the memory 1201.

[0195] The communication module 1203 is used to communicate with terminal devices and other servers.

[0196] This application embodiment does not limit the specific connection medium between the memory 1201, communication module 1203, and processor 1202. This application embodiment... Figure 12 The memory 1201 and the processor 1202 are connected via a bus 1204, and the bus 1204 is in Figure 12 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. The 1204 bus can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 12 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.

[0197] The memory 1201 stores a computer storage medium, which stores computer-executable instructions for implementing the anomaly handling method of this application embodiment. The processor 1202 is used to execute the above-described anomaly handling method, such as... Figure 2 As shown.

[0198] In another embodiment, the computer device can also be other computer devices, such as... Figure 1 The palm-swiping device 110 is shown. In this embodiment, the computer device can be structured as follows: Figure 13 As shown, it includes components such as: communication component 1310, memory 1320, display unit 1330, camera 1340, sensor 1350, audio circuit 1360, Bluetooth module 1370, processor 1380, etc.

[0199] The communication component 1310 is used to communicate with the server. In some embodiments, it may include a Wireless Fidelity (WiFi) module, which is a short-range wireless transmission technology, and the electronic device can send and receive information through the WiFi module.

[0200] The memory 1320 can be used to store software programs and data. The processor 1380 executes various functions of the swiping device 110 and performs data processing by running the software programs or data stored in the memory 1320. The memory 1320 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 1320 stores an operating system that enables the swiping device 110 to run. In this application, the memory 1320 may store the operating system and various application programs, and may also store a computer program that executes the anomaly handling method of the embodiments of this application.

[0201] The display unit 1330 can also be used to display information input by the object or information provided to the object, as well as a graphical user interface (GUI) of various menus of the palm-swiping device 110. Specifically, the display unit 1330 may include a display screen 1332 disposed on the front of the palm-swiping device 110. The display screen 1332 may be configured as a liquid crystal display, a light-emitting diode, or the like. The display unit 1330 can be used to display reminder information, abnormal palm images that require selection by the object to be identified, etc., as described in the embodiments of this application.

[0202] The display unit 1330 can also be used to receive input digital or character information and generate signal inputs related to object settings and function control of the physical terminal device 210. Specifically, the display unit 1330 may include a touch screen 1331 disposed on the front of the palm-swiping device 110, which can collect touch operations on or near the object, such as clicking a button, dragging a scroll box, etc.

[0203] The touchscreen 1331 can be placed on top of the display screen 1332, or the touchscreen 1331 and the display screen 1332 can be integrated to realize the input and output functions of the physical terminal device 210. After integration, it can be referred to as a touch display screen. In this application, the display unit 1330 can display the application and the corresponding operation steps.

[0204] Camera 1340 can be used to capture still images, and objects can publish images captured by camera 1340 through an application. There can be one or multiple cameras 1340. An object generates an optical image through a lens, which is projected onto a photosensitive element. The photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to processor 1380 to be converted into a digital image signal.

[0205] The physical terminal device may also include at least one sensor 1350, such as an accelerometer 1351, a proximity sensor 1352, a fingerprint sensor 1353, and a temperature sensor 1354. The terminal device may also be equipped with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, and motion sensor.

[0206] Audio circuitry 1360, speaker 1361, and microphone 1362 provide an audio interface between the object and the swiping device 110. Audio circuitry 1360 converts received audio data into electrical signals, which are then transmitted to speaker 1361, where they are converted into sound signals for output. Physical terminal device 210 may also be equipped with volume buttons for adjusting the volume of the sound signal. On the other hand, microphone 1362 converts collected sound signals into electrical signals, which are received by audio circuitry 1360, converted into audio data, and then output to communication component 1310 for transmission to, for example, another physical terminal device 210, or to memory 1320 for further processing.

[0207] Bluetooth module 1370 is used to interact with other Bluetooth devices that also have Bluetooth modules via the Bluetooth protocol. For example, a physical terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smartwatch) that also has a Bluetooth module through Bluetooth module 1370, thereby exchanging data.

[0208] The processor 1380 is the control center of the physical terminal device, connecting various parts of the terminal through various interfaces and lines. It executes various functions and processes data by running or executing software programs stored in the memory 1320 and calling data stored in the memory 1320. In some embodiments, the processor 1380 may include one or more processing units; the processor 1380 may also integrate an application processor and a baseband processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the baseband processor mainly handles wireless communication. It is understood that the baseband processor may not be integrated into the processor 1380. In this application, the processor 1380 can run the operating system, applications, user interface display and touch response, as well as the anomaly handling method of this embodiment. Furthermore, the processor 1380 is coupled to the display unit 1330.

[0209] Furthermore, it should be noted that in the specific embodiments of this application, object data related to anomaly identification and handling is involved. When the above embodiments of this application are applied to specific products or technologies, permission or consent from the object is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0210] In some possible implementations, various aspects of the anomaly identification and handling method provided in this application can also be implemented as a program product, comprising a computer program. When the program product is run on a computer device, the computer program causes the computer device to perform the steps of the anomaly identification and handling method according to the various exemplary embodiments of this application described above. For example, the computer device can perform actions such as... Figure 2 The steps are shown in the figure.

[0211] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0212] The program product of the embodiments of this application may employ a portable compact disc read-only memory (CD-ROM) and include a computer program, and may run on an electronic device. However, the program product of this application is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with a command execution system, apparatus, or device.

[0213] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a readable computer program. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with a command execution system, apparatus, or device.

[0214] Computer programs contained on readable media may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0215] Computer programs for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The computer program can execute entirely on the user's computer device, partially on the user's computer device, as a standalone software package, partially on the user's computer device and partially on a remote computer device, or entirely on a remote computer device. In cases involving remote computer devices, the remote computer device can be connected to the user's computer device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer device (e.g., via the Internet using an Internet service provider).

[0216] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0217] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0218] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing a computer-usable computer program.

[0219] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0220] These computer program commands may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the commands stored in the computer-readable storage medium produce an article of manufacture including command means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0221] These computer program commands can also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing the commands executed on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0222] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0223] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for identifying and handling anomalies, characterized in that, Applications in palm-swiping devices include: Upon detecting an object to be identified, a target identification session is created, and based on the target identification session, the following operations are repeated until the session termination condition is met: Based on the current shooting parameters of the palm-scanning device, an image of the palm of the object to be identified is obtained, and feature extraction is performed on the image of the palm to be identified to obtain the palm features to be identified. The palm features to be identified are matched with each reference palm feature recorded in the palm feature database. If it is determined that there is no matching reference hand feature, the current shooting parameters are adjusted, and the adjusted shooting parameters are used for the next shooting.

2. The method according to claim 1, characterized in that, When it is determined that no matching reference palm feature exists, after adjusting the current shooting parameters, the method further includes: The image of the hand to be identified is associated with and saved as an abnormal hand image in the target recognition session; When the session termination condition is met, the method further includes: If it is determined that at least one abnormal palm image is associated with and saved in the target recognition session, then the at least one abnormal palm image is filtered according to the degree of matching. Feature extraction is performed on the selected target hand images to obtain target feature information; The obtained target feature information is uploaded to the server so that the server associates the target feature information with the object to be identified and sends the feature difference between the target feature information and the reference palm feature associated with the object to be identified to the palm-swiping device. The palm feature database is updated based on the received feature differences.

3. The method according to claim 2, characterized in that, The step of matching the palm feature to be identified with each reference palm feature recorded in the palm feature database includes: Calculate the first similarity between the palm feature to be identified and each reference palm feature recorded in the palm feature database, and determine the reference palm features whose first similarity is greater than or equal to the qualified similarity threshold as successfully matched reference palm features. The step of filtering the at least one abnormal palm image based on the degree of matching includes: The abnormal hand image with a first similarity greater than or equal to the intermediate similarity threshold among the at least one abnormal hand image is taken as the target hand image; the intermediate similarity threshold is less than the qualified similarity threshold.

4. The method according to claim 3, characterized in that, After associating and saving the palm image to be identified as an abnormal palm image with the target recognition session, the method further includes: If there are other abnormal palm images associated with the target recognition session, then calculate the second similarity between the palm features to be recognized and the palm features to be recognized in the other abnormal palm images respectively. When a second similarity value below the substandard similarity threshold exists, the session termination condition is determined to be met; the substandard similarity threshold is less than the intermediate similarity threshold.

5. The method according to claim 2, characterized in that, The step of filtering the at least one abnormal palm image based on the degree of matching includes: Display the image of the at least one abnormal palm; In response to the selection operation of the at least one abnormal palm image by the object to be identified, the selected abnormal palm image is used as the target palm image.

6. The method according to any one of claims 2-5, characterized in that, The session termination condition also includes at least one of the following: Identify a matching reference hand feature; The distance between the object to be identified and the palm-swiping device is detected to be greater than a preset distance threshold.

7. An anomaly identification and processing device, characterized in that, include: The detection unit is used to detect the object to be identified. The session management unit is used to create a target identification session when an object to be identified is detected. The identification unit is used to repeatedly perform the following operations based on the target identification session until the session ends: based on the current shooting parameters of the palm-scanning device, acquire the palm image of the object to be identified, and extract features from the palm image to obtain the palm features to be identified; The hand features to be identified are matched against each of the reference hand features recorded in the hand feature database. If no matching reference hand features are found, the current shooting parameters are adjusted and the adjusted shooting parameters are used for the next shooting.

8. A computer device, characterized in that, It includes a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It includes program code that, when run on a computer device, causes the computer device to perform the steps of the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images