Authentication methods and authentication systems

Abstract

This application discloses an identity verification method and system, belonging to the field of identity verification technology. The method includes: if the palm to be identified is detected to be within a preset recognition range, sending a first supplementary light command to a first supplementary light component and a second supplementary light component; sending a first image acquisition command to a first image acquisition device and a second image acquisition device; receiving a palm shape image and a palm print image sent by the first image acquisition device, and a palm vein image sent by the second image acquisition device; acquiring palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, palm print image, and palm vein image, respectively; acquiring fusion features corresponding to the palm to be identified based on the palm shape features, palm print features, and palm vein features, and acquiring the identity recognition result corresponding to the palm to be identified based on the fusion features.

Description

Technical Field

[0001] This application belongs to the field of authentication technology, and in particular relates to an authentication method and authentication system. Background Technology

[0002] With the deepening development of social informatization and digitalization, palm recognition technology, as an emerging biometric identification method, has gradually attracted people's attention. It typically involves acquiring images of the user's palm using a data acquisition device, and then verifying the user's identity based on the palm image.

[0003] However, since the identity verification process requires high-quality palm images, a complex optical path system and a large imaging distance are needed to obtain high-quality images, resulting in large size and high cost of palm image acquisition equipment. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes an authentication method and authentication system to solve the problems of large size and high cost of authentication systems.

[0005] In a first aspect, this application provides an authentication method applied to an authentication system, the authentication system including a main controller, a first image acquisition unit, and a second image acquisition unit; the first image acquisition unit includes a first image acquisition device and a first supplementary lighting component; the second image acquisition unit includes a second image acquisition device and a second supplementary lighting component, the method comprising: If the palm to be identified is detected to be within the preset recognition range, a first supplementary light command is sent to the first supplementary light component and the second supplementary light component; the first supplementary light command is used to instruct the first supplementary light component and the second supplementary light component to provide supplementary light to the palm to be identified; Send a first image acquisition command to a first image acquisition device and a second image acquisition device; the first image acquisition command is used to instruct the first image acquisition device to acquire the palm shape image and palm print image of the palm to be identified, and to instruct the second image acquisition device to acquire the palm vein image of the palm to be identified. Receive palm shape image and palm print image sent by the first image acquisition device, and palm vein image sent by the second image acquisition device; Based on palm shape image, palm print image and palm vein image, obtain the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be identified, respectively; Based on palm shape features, palm print features, and palm vein features, the fusion features corresponding to the palm to be identified are obtained, and based on the fusion features, the identity recognition result corresponding to the palm to be identified is obtained.

[0006] According to the authentication method of this application, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, a palm print image and a palm shape image are acquired by a first image acquisition device, and the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. Based on the palm shape image, palm print image and palm vein image, the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be identified are acquired respectively. Based on the palm shape feature, palm print feature and palm vein feature, the fusion feature corresponding to the palm to be identified is acquired, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is acquired. By illuminating the palm to be identified by the first supplementary lighting component and the second supplementary lighting component respectively, the quality of the acquired palm print image, palm shape image and palm vein image is improved, so that high-quality feature images can be acquired without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the authentication system.

[0007] According to one embodiment of this application, based on a palm shape image, a palm print image, and a palm vein image, the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified are obtained, respectively, including: The palm shape image, palm print image, and palm vein image are respectively input into the corresponding palm recognition model; the palm recognition model includes a region image extraction module and a feature extraction module. The local images corresponding to the palm shape image, palm print image, and palm vein image are obtained respectively through the region image extraction module; The feature extraction module obtains the palm shape features, palm print features, and palm vein features of the hand to be identified based on the corresponding local image.

[0008] According to one embodiment of this application, a region image extraction module is used to obtain local images corresponding to a palm shape image, a palm print image, and a palm vein image, respectively, including: For palm-shaped images, palm print images, or palm vein images, local images corresponding to the palm-shaped images, palm print images, or palm vein images are extracted based on predefined reference points in the region image extraction module.

[0009] According to one embodiment of this application, based on palm shape features, palm print features, and palm vein features, a fusion feature corresponding to the palm to be identified is obtained, and based on the fusion feature, an identity recognition result corresponding to the palm to be identified is obtained, including: Obtain palm shape fusion weights, palm print fusion weights, and vein fusion weights; Based on palmprint fusion weight, palm shape fusion weight, and vein fusion weight, palmprint features, palm shape features, and vein features are fused to obtain the fused features corresponding to the palm to be identified.

[0010] According to one embodiment of this application, before sending a first supplementary light command to the first supplementary light component and the second supplementary light component if the palm to be identified is detected to be within a preset identification range, the method further includes: The real-time distance of the target object is obtained, and the position detection result of the target object is obtained based on the real-time distance; the real-time distance is the distance between the target object and the first image acquisition device. If the location detection result indicates that the target object is within the preset recognition range, a second image acquisition command is sent to the second image acquisition device; the second image acquisition command is used to instruct the second image acquisition device to acquire the first target object image of the target object. The system receives a first target object image sent by a second image acquisition device and obtains a determination and recognition result for the target object based on the first target object image.

[0011] According to one embodiment of this application, receiving a first target object image sent by a second image acquisition device, and obtaining a determination and recognition result for the target object based on the first target object image, includes: Using a palm recognition model, the target confidence level of the target object is obtained based on the first target object image; If the target confidence level is greater than the confidence level threshold, the recognition result for the target object is determined to be the hand to be recognized.

[0012] According to one embodiment of this application, the authentication system further includes a buzzer and an indicator light; after obtaining the real-time distance of the target object and obtaining the position detection result of the target object based on the real-time distance, the method includes: If the position detection result indicates that the target object is not within the preset recognition range, a state switching command is sent to the buzzer and the indicator light. The state switching command is used to instruct the buzzer to sound and to instruct the indicator light to switch to the first state in order to guide the target object to change its posture.

[0013] According to one embodiment of this application, after receiving a first target object image sent by a second image acquisition device and determining a recognition result based on the first target object image, the method includes: If the target object is not the hand to be identified, perform a decoding operation on the first target object image; In the event of a decoding failure, a second supplementary lighting command is sent to the first supplementary lighting component, and a third image acquisition command is sent to the first image acquisition device. The second supplementary lighting command is used to instruct the first supplementary lighting component to provide supplementary lighting to the target object, and the third image acquisition command is used to instruct the first image acquisition device to acquire an image of the second target object.

[0014] Secondly, this application provides an identity verification system, which includes: a main controller, a first image acquisition unit and a second image acquisition unit, wherein the first image acquisition unit includes a first image acquisition device and a first supplementary lighting component, and the second image acquisition unit includes a second image acquisition device and a second supplementary lighting component; The main controller is used to send a first supplementary light command to the first supplementary light component and the second supplementary light component if it detects that the palm to be identified is within the preset recognition range; The first supplementary lighting component is used to execute the first supplementary lighting instruction upon receiving the first supplementary lighting instruction, and to provide supplementary lighting to the palm to be identified; The second supplementary lighting component is used to execute the first supplementary lighting instruction upon receiving the first supplementary lighting instruction, and to provide supplementary lighting to the palm to be identified; The main controller is also used to send a first image acquisition command to the first image acquisition device and the second image acquisition device; The first image acquisition device is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm shape image and palm print image of the hand to be identified, and send the palm shape image and palm print image to the main controller. The second image acquisition device is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm vein image of the palm to be identified, and send the palm vein image to the main controller. The main controller is also used to obtain the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, palm print image, and palm vein image, respectively; to obtain the fusion features corresponding to the palm to be identified based on the palm shape features, palm print features, and palm vein features; and to obtain the identity recognition result corresponding to the palm to be identified based on the fusion features.

[0015] According to one embodiment of this application, the main controller is further configured to: The palm shape image, palm print image, and palm vein image are respectively input into the corresponding palm recognition model; the palm recognition model includes a region image extraction module and a feature extraction module. The local images corresponding to the palm shape image, palm print image, and palm vein image are obtained respectively through the region image extraction module; The feature extraction module obtains the palm shape features, palm print features, and palm vein features of the hand to be identified based on the corresponding local image.

[0016] According to one embodiment of this application, the main controller is further configured to: For palm-shaped images, palm print images, or palm vein images, local images corresponding to the palm-shaped images, palm print images, or palm vein images are extracted based on predefined reference points in the region image extraction module.

[0017] According to one embodiment of this application, the main controller is further configured to: Obtain palm shape fusion weights, palm print fusion weights, and vein fusion weights; Based on palmprint fusion weight, palm shape fusion weight, and vein fusion weight, palmprint features, palm shape features, and vein features are fused to obtain the fused features corresponding to the palm to be identified.

[0018] According to one embodiment of this application, the first supplementary lighting component includes several light-emitting arrays, each light-emitting array including a red light-emitting diode, a yellow light-emitting diode, a blue light-emitting diode and at least one white light-emitting diode.

[0019] According to one embodiment of this application, the second supplementary lighting component includes an infrared light-emitting diode and at least one convex lens.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is one of the flowcharts illustrating the authentication method provided in the embodiments of this application; Figure 2 This is a second flowchart illustrating the authentication method provided in the embodiments of this application; Figure 3 This is one of the structural schematic diagrams of the identity verification system provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the first supplementary lighting component provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the first supplementary lighting component provided in the embodiments of this application; Figure 6 This is a second schematic diagram of the structure of the identity verification system provided in the embodiments of this application; Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0023] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0024] The authentication method and authentication system provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0025] The authentication method can be applied to the terminal, and can be executed by the hardware or software in the terminal.

[0026] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablets with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads).

[0027] The following embodiments describe a terminal including a display and a touch-sensitive surface. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0028] The authentication method provided in this application embodiment can be executed by an electronic device or a functional module or entity in an electronic device that can implement the authentication method. The electronic devices mentioned in this application embodiment include, but are not limited to, mobile phones, tablets, computers, cameras, and wearable devices. The authentication method provided in this application embodiment is described below using an electronic device as the execution subject.

[0029] like Figure 1 As shown, the authentication method includes steps 110, 120, 130, 140, and 150.

[0030] In some embodiments, the authentication method of this application can be applied to an authentication system, which includes a main controller, a first image acquisition unit and a second image acquisition unit. The first image acquisition unit includes a first image acquisition device and a first supplementary lighting component, and the second image acquisition unit includes a second image acquisition device and a second supplementary lighting component.

[0031] Step 110: If the palm to be identified is detected to be within the preset identification range, a first supplementary light command is sent to the first supplementary light component and the second supplementary light component; the first supplementary light command is used to instruct the first supplementary light component and the second supplementary light component to provide supplementary light to the palm to be identified.

[0032] In some embodiments, the main controller can determine whether the real-time distance between the target object and the target object meets the distance standard and whether the target object is the hand to be identified, upon detecting the target object.

[0033] In actual execution, the target object can be the palm to be identified, or it can be an object containing target information, such as QR code information, barcode information, or any theoretically feasible data information.

[0034] In some embodiments, when the palm to be identified is detected to be within a preset recognition range, the main controller sends a first acquisition command to the first image acquisition unit through a communication connection with the first image acquisition unit, and sends a first acquisition command to the second image acquisition unit through a communication connection with the second image acquisition unit.

[0035] In some embodiments, when the first image acquisition unit receives the first acquisition command, it sends a first supplementary lighting command to the first supplementary lighting component to provide supplementary lighting for the palm to be identified. When the second image acquisition unit receives the first acquisition command, it sends a second supplementary lighting command to the second supplementary lighting component to provide supplementary lighting for the palm to be identified.

[0036] In actual implementation, the first supplementary lighting component may include at least one light-emitting array, each light-emitting array including a red light-emitting diode, a yellow light-emitting diode, a blue light-emitting diode and at least one white light-emitting diode.

[0037] In some embodiments, after obtaining the first acquisition command, the first image acquisition unit can determine the number of light-emitting arrays to be activated based on the brightness requirements in the first acquisition command, and activate the light-emitting arrays based on the number of light-emitting arrays to be activated.

[0038] In actual implementation, the second supplementary lighting component may include an infrared light-emitting diode and at least one convex lens.

[0039] In some embodiments, after receiving the first acquisition command, the second image acquisition unit triggers the second supplementary lighting component to turn on, so as to provide supplementary lighting for the target object.

[0040] Step 120: Send a first image acquisition command to the first image acquisition device and the second image acquisition device; the first image acquisition command is used to instruct the first image acquisition device to acquire the palm shape image and palm print image of the hand to be identified, and to instruct the second image acquisition device to acquire the palm vein image of the hand to be identified.

[0041] In actual implementation, the first image acquisition device can be a camera or any theoretically feasible image acquisition device; this application does not impose any specific restrictions on it.

[0042] In some embodiments, the first image acquisition unit obtains a first acquisition instruction and sends the first image acquisition instruction to the first image acquisition device, instructing the first image acquisition device to acquire a palm print image and a palm shape image, and sends the palm print image and palm shape image to the main controller through a communication connection with the main controller.

[0043] In actual implementation, the second image acquisition device can be a camera or any theoretically feasible image acquisition device; this application does not impose any specific restrictions on it.

[0044] In some embodiments, the second image acquisition unit receives a first acquisition instruction and sends the first image acquisition instruction to the second image acquisition device to instruct the second image acquisition device to acquire a palm vein image, and sends the palm vein image to the main controller through a communication connection with the main controller.

[0045] Step 130: Receive the palm shape image and palm print image sent by the first image acquisition device, and the palm vein image sent by the second image acquisition device.

[0046] Step 140: Based on the palm shape image, palm print image, and palm vein image, obtain the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified.

[0047] In actual implementation, the main controller may include an artificial intelligence processing chip, which includes a neural network processing unit (NPU).

[0048] In some embodiments, after acquiring palm print images, palm shape images, and palm vein images, the main controller can use an artificial intelligence processing chip to perform a lightweight recognition algorithm on the palm print images, palm shape images, and palm vein images to obtain the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified.

[0049] Step 150: Based on palm shape features, palm print features, and palm vein features, obtain the fusion features corresponding to the palm to be identified, and based on the fusion features, obtain the identity recognition result corresponding to the palm to be identified.

[0050] In some embodiments, the main controller can identify palm print images, palm shape images, and palm vein images through at least one neural network model for authentication.

[0051] In some embodiments, palm print features, palm shape features, and vein features are fused, and the fused features are input into a classifier for authentication.

[0052] In some embodiments, after authentication, the main controller instructs a buzzer to sound and an indicator light to switch to a third state (e.g., green) to alert the target object to move away.

[0053] According to the identity verification method of this application embodiment, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, a palm print image and a palm shape image are acquired by a first image acquisition device, and the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. Based on the palm shape image, palm print image and palm vein image, the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be identified are acquired respectively. Based on the palm shape feature, palm print feature and palm vein feature, the fusion feature corresponding to the palm to be identified is acquired, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is acquired. By illuminating the target object by the first supplementary lighting component and the second supplementary lighting component respectively, the quality of the acquired palm print image, palm shape image and palm vein image is improved, so that high-quality feature images can be acquired without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device.

[0054] In some embodiments, the palm shape image, palm print image, and palm vein image are respectively input into the corresponding palm recognition model; the palm recognition model includes a region image extraction module and a feature extraction module; the region image extraction module obtains the local images corresponding to the palm shape image, palm print image, and palm vein image respectively; the feature extraction module obtains the palm shape features, palm print features, and palm vein features corresponding to the palm to be recognized based on the corresponding local images.

[0055] In some embodiments, after receiving the palm shape image and palm print image sent by the first image acquisition device, and the palm vein image sent by the second image acquisition device, the palm shape image, palm print image and palm vein image can be input into the corresponding palm recognition model to obtain the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be recognized.

[0056] In actual implementation, the palm recognition model includes a first palm recognition model corresponding to palm print images, a second palm recognition model corresponding to palm vein images, and a third palm recognition model corresponding to palm shape images.

[0057] In some embodiments, a palm print image is input to a first palm recognition model to determine and output the palm print features of the palm to be recognized; a palm vein image is input to a second palm recognition model to determine and output the palm vein features of the palm to be recognized; and a palm shape image is input to a third palm recognition model to determine and output the palm shape features of the palm to be recognized.

[0058] In some embodiments, a palmprint image is input into a first palm recognition model, a region image extraction module of the first palm recognition model obtains a local image of the palmprint image, and a feature extraction module of the first palm recognition model obtains palmprint features based on the local image of the palmprint image.

[0059] In some embodiments, a palm vein image is input into a second palm recognition model, the region image extraction module of the second palm recognition model obtains a local image of the palm vein image, and the feature extraction module of the second palm recognition model obtains palm vein features based on the local image of the palm vein image.

[0060] In some embodiments, a palm-shaped image is input into a third palm recognition model, the region image extraction module of the third palm recognition model obtains a local image of the palm-shaped image, and the feature extraction module of the third palm recognition model obtains palm-shaped features based on the local image of the palm-shaped image.

[0061] In some embodiments, for each local image, palm shape features, palm print features, or palm vein features are extracted from the local image based on the feature extraction neural network in the feature extraction module.

[0062] In some embodiments, the first decoder in the third palm recognition model includes a first branch for outputting the coordinates of the key points via heatmap regression or coordinate regression. The key points include the center point of the palm root, the root points of each finger, and the fingertip points. The first decoder in the third palm recognition model also includes a second branch for palm region detection. This second branch generates parameters for a bounding box or rotated rectangle through regression calculation. These parameters include the center point coordinates, width, height, and rotation angle to accommodate any orientation of the palm in the image. In some embodiments, the main controller can use the third palm recognition model to recognize palm images and obtain palm shape features such as the palm aspect ratio, palm area, the projected length from the root to the fingertip of each finger (thumb to little finger), and their relative proportions. The palm contour can be input into a very shallow CNN (containing only 2-3 convolutional layers) in the third palm recognition model, or principal component analysis (PCA) can be used to extract the shape context features of the contour.

[0063] In some embodiments, a first palm recognition model (e.g., an independently trained SqueezeNet) can be used to extract feature vectors of main lines, wrinkles, and minutiae. The first palm recognition model may include shallow convolutional layers and deep convolutional layers; the shallow convolutional layers are used to capture fine-grained edges and textures, while the deep convolutional layers are used to understand the macroscopic structure of the texture. The main controller can use the first palm recognition model to recognize grayscale and contrast-enhanced palmprint images, obtaining palmprint features such as the distribution of main lines, wrinkles, and minutiae.

[0064] In some embodiments, the second palm recognition model uses depthwise separable convolutions, significantly reducing parameters and computational cost while maintaining performance. This model focuses on the unique texture patterns formed by vascular networks under near-infrared light, including vein bifurcation points, intersections, and orientations. In some embodiments, the second palm recognition model (e.g., MobileNetV2) includes a global average pooling layer and a fully connected layer. The main controller can use the second palm recognition model to identify palm vein images and obtain vein features such as vein texture, vein bifurcation points, and vein intersections.

[0065] According to the identity verification method of this application embodiment, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, a palm print image and a palm shape image are acquired by a first image acquisition device, and the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. The palm print image is input into a first palm recognition model to determine and output the palm print features of the palm to be identified; the palm vein image is input into a second palm recognition model to determine and output the palm vein features of the palm to be identified; the palm shape image is input into a third palm recognition model to determine and output the palm shape features of the palm to be identified; based on the palm shape features, palm print features, and palm vein features, the fusion features corresponding to the palm to be identified are obtained, and based on the fusion features, the identity recognition result corresponding to the palm to be identified is obtained. By illuminating the target object with the first supplementary lighting component and the second supplementary lighting component respectively, the quality of the acquired palm print image, palm shape image, and palm vein image is improved, so that high-quality feature images can be obtained without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device. Furthermore, a lightweight recognition algorithm is implemented to obtain palm print features, palm shape features, and vein features, saving computing power.

[0066] In some embodiments, for palm-shaped images, palm print images, or palm vein images, local images corresponding to the palm-shaped images, palm print images, or palm vein images are extracted based on reference points predefined in the region image extraction module.

[0067] In some embodiments, for palmprint images, the region image extraction module in the first palm recognition model can extract local images of the palmprint image based on predefined reference points.

[0068] In some embodiments, for palm-shaped images, the region image extraction module in the third palm recognition model can extract local images of the palm-shaped image based on predefined reference points.

[0069] In some embodiments, palm shape fusion weight, palm print fusion weight, and vein fusion weight are obtained; based on the palm print fusion weight, palm shape fusion weight, and vein fusion weight, the palm print features, palm shape features, and vein features are fused to obtain the fusion features corresponding to the palm to be identified.

[0070] In some embodiments, after obtaining palmprint features, palm shape features, and vein features, palm shape fusion weight, palmprint fusion weight, and vein fusion weight can be obtained; based on the palmprint fusion weight, palm shape fusion weight, and vein fusion weight, the palmprint features, palm shape features, and vein features are fused to obtain the fusion features corresponding to the palm to be identified, so as to obtain the identity recognition result corresponding to the palm to be identified.

[0071] In some embodiments, a palmprint image is input into a first palm recognition model, and the palmprint features of the palm to be recognized are output while the palmprint confidence of the palmprint image is obtained, and the palmprint fusion weight is obtained based on the palmprint confidence.

[0072] In some embodiments, a palm vein image is input into a second palm recognition model, and while outputting the palm vein features of the palm to be recognized, the palm vein confidence score of the palm vein image is obtained, and the vein fusion weight is obtained based on the palm vein confidence score.

[0073] In some embodiments, a palm shape image is input into a third palm recognition model, and the palm shape features of the palm to be recognized are output while the palm shape confidence of the palm shape image is obtained. The palm shape fusion weight is obtained based on the palm shape confidence.

[0074] In some embodiments, after acquiring palmprint features, palm shape features, and vein features, these features can be normalized. Then, based on the palmprint fusion weights, palm shape fusion weights, and vein fusion weights, the normalized palmprint features, palm shape features, and vein features are concatenated to generate a multimodal feature vector. A fully connected layer is introduced to perform a nonlinear transformation on the multimodal feature vector to learn the interaction relationships between different modalities, outputting a compact and more discriminative fused feature.

[0075] According to the authentication method of this application embodiment, the main controller dynamically adjusts the weights of different features based on image quality and the confidence level of each feature to improve the accuracy of the fusion result. It can maintain high recognition accuracy and stability when facing various complex hand conditions and environmental changes.

[0076] In some embodiments, before sending a first supplementary light command to the first and second supplementary light components if the palm to be identified is detected to be within a preset recognition range, the real-time distance of the target object is obtained, and the position detection result of the target object is obtained based on the real-time distance of the target object; the real-time distance of the target object is the distance between the target object and the first image acquisition device; if the position detection result indicates that the target object is within the preset recognition range, a second image acquisition command is sent to the second image acquisition device; the second image acquisition command is used to instruct the second image acquisition device to acquire a first target object image of the target object; the first target object image sent by the second image acquisition device is received, and a determination recognition result for the target object is obtained based on the first target object image.

[0077] In some embodiments, the authentication system may include a ranging sensor that detects the real-time distance between the first image acquisition device and the target object and sends the real-time distance to the main controller.

[0078] In actual execution, the position detection result of the target object indicates whether the target object is within the preset recognition range.

[0079] In some embodiments, the main controller can determine that a target object is within a preset recognition range if the real-time target distance is greater than or equal to a first distance threshold and less than a second distance threshold. The real-time target distance is the distance between the target object and the authentication system.

[0080] In actual execution, both the first and second distance thresholds can be preset values. For example, both the first and second distance thresholds can be set based on the imaging distance of the first or second image acquisition device. The first distance threshold is less than the second distance threshold. For example, if the first distance threshold is 4 cm and the second distance threshold is 30 cm, the main controller can determine that the target object is within the preset recognition range when the real-time target distance is 15 cm.

[0081] In some embodiments, when the target object is within a preset recognition range, the main controller sends a second acquisition command to the second image acquisition unit. After receiving the second acquisition command, the second image acquisition unit activates the second supplementary lighting component to supplement the target object and sends the second image acquisition command to the second image acquisition device. Based on the second image acquisition device, the first target object image is acquired and sent to the main controller.

[0082] In some embodiments, the main controller can analyze the first target object image to determine whether the first target object image includes a hand to be identified, so as to determine whether the target object is a hand to be identified.

[0083] In some embodiments, when the target object is a hand to be identified, the main controller can determine whether the target object meets the feature acquisition criteria based on the first target object image.

[0084] In practice, the feature acquisition standard refers to the standard by which a target object can be completely acquired by the identity verification system. Because users cannot perceive the acquisition range of the identity verification system, the hand to be identified may not be completely within the system's acquisition range. Consequently, the hand image acquired by the system may not fully include the user's hand biometric features, affecting the accuracy of identity recognition.

[0085] According to the identity verification method of this application embodiment, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, a palm print image and a palm shape image are acquired by a first image acquisition device, and the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. Based on the palm shape image, palm print image and palm vein image, the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be identified are acquired respectively. Based on the palm shape feature, palm print feature and palm vein feature, the fusion feature corresponding to the palm to be identified is acquired, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is acquired. By illuminating the target object by the first supplementary lighting component and the second supplementary lighting component respectively, the quality of the acquired palm print image, palm shape image and palm vein image is improved, so that high-quality feature images can be acquired without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device.

[0086] In some embodiments, a palm recognition model is used to obtain the target confidence level corresponding to the target object based on the first target object image; if the target confidence level is greater than the confidence level threshold, the recognition result for the target object is determined to be the palm to be recognized.

[0087] In actual execution, after acquiring the image of the first target object, the second palm recognition model can be used to perform palm vein feature recognition on the image of the first target object to obtain the target confidence level corresponding to the target object.

[0088] In some embodiments, the main controller can determine that the target object is the hand to be identified if the target confidence level is greater than or equal to the confidence level threshold; conversely, the main controller can determine that the target object is not the hand to be identified if the target confidence level is less than the confidence level threshold.

[0089] According to the identity verification method of this application embodiment, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, a palm print image and a palm shape image are acquired by a first image acquisition device, and the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. Based on the palm shape image, palm print image and palm vein image, the palm shape feature, palm print feature and palm vein feature corresponding to the palm to be identified are acquired respectively. Based on the palm shape feature, palm print feature and palm vein feature, the fusion feature corresponding to the palm to be identified is acquired, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is acquired. By illuminating the target object by the first supplementary lighting component and the second supplementary lighting component respectively, the quality of the acquired palm print image, palm shape image and palm vein image is improved, so that high-quality feature images can be acquired without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device.

[0090] In some embodiments, the authentication system further includes a buzzer and an indicator light; after determining the real-time distance of the target object and obtaining the position detection result of the target object based on the real-time distance, if the position detection result indicates that the target object is not within the preset recognition range, a state switching instruction is sent to the buzzer and the indicator light; the state switching instruction is used to instruct the buzzer to sound and to instruct the indicator light to switch to the first state, so as to guide the target object to change its posture.

[0091] In some embodiments, after obtaining the real-time distance of the target object and obtaining the position detection result of the target object based on the real-time distance, In some embodiments, when the target object is not within a preset recognition range, the main controller instructs a buzzer to sound and an indicator light to switch to a second state to prompt the target object to adjust its real-time distance. For example, if the first distance threshold is 4 cm, and the target real-time distance is 2 cm, the main controller instructs a buzzer to sound and an indicator light to switch to the first state, prompting an increase in the target real-time distance; if the second distance threshold is 30 cm, and the target real-time distance is 45 cm, the main controller instructs a buzzer to sound and an indicator light to switch to the second state, prompting a decrease in the target real-time distance.

[0092] In actual implementation, the indicator light can be a light-emitting diode (LED).

[0093] In some embodiments, the main controller can instruct the buzzer to sound (e.g., emit a continuous "beep" sound) when the target object is not within the preset recognition range, and at the same time instruct the indicator light to switch to the first state, such as instructing the indicator light to switch to red or yellow, so as to guide the target object to change its posture until the target object meets the feature acquisition standard.

[0094] According to the authentication method of this application, when the palm to be identified is detected to be within a preset recognition range, the palm to be identified is illuminated by a first supplementary lighting component, and a palm print image and a palm shape image are acquired by a first image acquisition device. Then, the palm to be identified is illuminated by a second supplementary lighting component, and a palm vein image is acquired by a second image acquisition device. Based on the palm shape image, palm print image, and palm vein image, the palm shape feature, palm print feature, and palm vein feature corresponding to the palm to be identified are acquired respectively. Based on the palm shape feature, palm print feature, and palm vein feature, the corresponding fusion feature of the palm to be identified is acquired, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is obtained. By illuminating the target object with the first and second supplementary lighting components respectively, the quality of the acquired palm print image, palm shape image, and palm vein image is improved. This allows for the acquisition of high-quality feature images without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device. With precise guidance from a ranging sensor and a signal light, the user does not need physical contact, making the experience of placing the palm natural, intuitive, and quick.

[0095] In some embodiments, after receiving a first target object image sent by a second image acquisition device and determining the recognition result based on the first target object image, if the target object is not the hand to be recognized, a decoding operation is performed on the first target object image; if the decoding operation fails, a second supplementary lighting command is sent to a first supplementary lighting component, and a third image acquisition command is sent to a first image acquisition device; the second supplementary lighting command is used to instruct the first supplementary lighting component to provide supplementary lighting to the target object, and the third image acquisition command is used to instruct the first image acquisition device to acquire a second target object image.

[0096] In some embodiments, if the target object is not the hand to be identified, the first supplementary light component in the first image acquisition unit is not turned on to avoid overexposure and reflection of the target object by the supplementary light, which would affect the image quality and make it difficult to perform decoding operations on the image of the first target object.

[0097] In some embodiments, the target object itself has low brightness (e.g., low brightness of an electronic device display screen, or paper documents lacking their own light source), resulting in low image quality of the first target object and causing decoding operation failure. In the event of decoding operation failure, the main controller sends a third acquisition command to the first image acquisition unit; based on the third acquisition command, the first image acquisition unit sends a second supplementary lighting command to the first supplementary lighting component to activate the first supplementary lighting component to provide supplementary lighting for the target object, and sends a third image acquisition command to the first image acquisition device to instruct the first image acquisition device to acquire the image of the second target object, and then sends the image of the second target object to the main controller.

[0098] To better understand the authentication method provided in the embodiments of this application, further explanation is provided below. It should be understood that the following discussion is merely exemplary.

[0099] In some embodiments, the authentication method of this application can be applied to an authentication system, which includes a main controller, a first image acquisition unit, a second image acquisition unit, a buzzer, a ranging sensor, and an indicator light. The first image acquisition unit includes a first image acquisition device and a first supplementary lighting component, and the second image acquisition unit includes a second image acquisition device and a second supplementary lighting component.

[0100] This application provides an authentication method, the specific steps of which are as follows: Figure 2 As shown: Step 210: Determine whether the target object is within the preset recognition range.

[0101] In some embodiments, the authentication system may include a ranging sensor that detects the real-time distance between the authentication system and the target object and sends the real-time distance to the main controller.

[0102] In some embodiments, the main controller can determine that a target object is within a preset recognition range if the real-time target distance is greater than or equal to a first distance threshold and less than a second distance threshold. The real-time target distance is the distance between the target object and the authentication system.

[0103] In actual execution, both the first and second distance thresholds can be preset values. For example, both the first and second distance thresholds can be set based on the imaging distance of the first or second image acquisition device. The first distance threshold is less than the second distance threshold. For example, if the first distance threshold is 4 cm and the second distance threshold is 30 cm, the main controller can determine that the target object is within the preset recognition range when the real-time target distance is 15 cm.

[0104] Step 215: If the target object is not within the preset recognition range, send a state switching command to the buzzer and the indicator light; the state switching command is used to instruct the buzzer to sound and to instruct the indicator light to switch to the first state in order to guide the target object to change its posture.

[0105] In some embodiments, when the target object is not within a preset recognition range, the main controller instructs a buzzer to sound and an indicator light to switch to a second state to prompt the target object to adjust its real-time distance. For example, if the first distance threshold is 4 cm, and the target real-time distance is 2 cm, the main controller instructs a buzzer to sound and an indicator light to switch to the first state, prompting an increase in the target real-time distance; if the second distance threshold is 30 cm, and the target real-time distance is 45 cm, the main controller instructs a buzzer to sound and an indicator light to switch to the second state, prompting a decrease in the target real-time distance.

[0106] In actual implementation, the indicator light can be a light-emitting diode (LED).

[0107] In some embodiments, the main controller can instruct the buzzer to sound (e.g., emit a continuous "beep" sound) when the target object is not within the preset recognition range, and at the same time instruct the indicator light to switch to the first state, such as instructing the indicator light to switch to red or yellow, so as to guide the target object to change its posture until the target object meets the feature acquisition standard.

[0108] Step 220: When the target object is within the preset recognition range, send a second image acquisition command to the second image acquisition device; the second image acquisition command is used to instruct the second image acquisition device to acquire the image of the first target object; receive the image of the first target object sent by the second image acquisition device.

[0109] In some embodiments, when the target object is within a preset recognition range, the main controller sends a second acquisition command to the second image acquisition unit. After receiving the second acquisition command, the second image acquisition unit activates the second supplementary lighting component to supplement the target object and sends the second image acquisition command to the second image acquisition device. Based on the second image acquisition device, the first target object image is acquired and sent to the main controller.

[0110] Step 225: Determine whether the target object is the hand to be identified based on the first target object image.

[0111] In some embodiments, the image of the first target object is analyzed based on the second palm recognition model to obtain the target confidence score; based on the target confidence score, it is determined whether the target object is the palm to be recognized.

[0112] In some embodiments, the main controller may determine that the target object is the hand to be identified if the target confidence level is greater than or equal to the first confidence level threshold; conversely, the main controller may determine that the target object is not the hand to be identified if the target confidence level is less than the first confidence level threshold.

[0113] Step 230: If the target object is not the hand to be identified, perform a decoding operation on the first target object image; if the decoding operation fails, send a second supplementary light command to the first supplementary light component and send a third image acquisition command to the first image acquisition device; the second supplementary light command is used to instruct the first supplementary light component to provide supplementary light to the target object, and the third image acquisition command is used to instruct the first image acquisition device to acquire the second target object image.

[0114] In some embodiments, if the target object is not the hand to be identified, the first supplementary light component in the first image acquisition unit is not turned on to avoid overexposure and reflection of the target object by the supplementary light, which would affect the image quality and make it difficult to perform decoding operations on the image of the first target object.

[0115] In some embodiments, the target object itself has low brightness (e.g., low brightness of an electronic device display screen, or paper documents lacking their own light source), resulting in low image quality of the first target object and causing decoding operation failure. In the event of decoding operation failure, the main controller sends a third acquisition command to the first image acquisition unit; based on the third acquisition command, the first image acquisition unit sends a second supplementary lighting command to the first supplementary lighting component to activate the first supplementary lighting component to provide supplementary lighting for the target object, and sends a third image acquisition command to the first image acquisition device to instruct the first image acquisition device to acquire the image of the second target object, and then sends the image of the second target object to the main controller.

[0116] Step 235: When the target object is the palm to be identified, send a first supplementary light command to the first supplementary light component and the second supplementary light component; the first supplementary light command is used to instruct the first supplementary light component and the second supplementary light component to provide supplementary light to the palm to be identified.

[0117] In some embodiments, the main controller can determine whether the real-time distance between the target object and the target object meets the distance standard and whether the target object is the hand to be identified, upon detecting the target object.

[0118] In actual execution, the target object can be the palm to be identified, or it can be an object containing target information, which can be QR code information, barcode information, or any theoretically feasible data information.

[0119] In some embodiments, when the palm to be identified is detected to be within a preset recognition range, the main controller sends a first acquisition command to the first image acquisition unit through a communication connection with the first image acquisition unit, and sends a first acquisition command to the second image acquisition unit through a communication connection with the second image acquisition unit.

[0120] In some embodiments, when the first image acquisition unit receives the first acquisition command, it sends a first supplementary lighting command to the first supplementary lighting component to provide supplementary lighting for the palm to be identified. When the second image acquisition unit receives the first acquisition command, it sends a second supplementary lighting command to the second supplementary lighting component to provide supplementary lighting for the palm to be identified.

[0121] In actual implementation, the first supplementary lighting component may include at least one light-emitting array, each light-emitting array including a red light-emitting diode, a yellow light-emitting diode, a blue light-emitting diode and at least one white light-emitting diode.

[0122] In some embodiments, after obtaining the first acquisition command, the first image acquisition unit can determine the number of light-emitting arrays to be activated based on the brightness requirements in the first acquisition command, and activate the light-emitting arrays based on the number of light-emitting arrays to be activated.

[0123] In actual implementation, the second supplementary lighting component may include an infrared light-emitting diode and at least one convex lens.

[0124] In some embodiments, after receiving the first acquisition command, the second image acquisition unit triggers the second supplementary lighting component to turn on, so as to provide supplementary lighting for the target object.

[0125] Step 240: Send a first image acquisition command to the first image acquisition device and the second image acquisition device; the first image acquisition command is used to instruct the first image acquisition device to acquire the palm shape image and palm print image of the hand to be identified, and to instruct the second image acquisition device to acquire the palm vein image of the hand to be identified; receive the palm shape image and palm print image sent by the first image acquisition device, and the palm vein image sent by the second image acquisition device.

[0126] In actual implementation, the first image acquisition device can be a camera or any theoretically feasible image acquisition device; this application does not impose any specific restrictions on it.

[0127] In some embodiments, the first image acquisition unit obtains a first acquisition instruction and sends the first image acquisition instruction to the first image acquisition device, instructing the first image acquisition device to acquire a palm print image and a palm shape image, and sends the palm print image and palm shape image to the main controller through a communication connection with the main controller.

[0128] In actual implementation, the second image acquisition device can be a camera or any theoretically feasible image acquisition device; this application does not impose any specific restrictions on it.

[0129] In some embodiments, the second image acquisition unit receives a first acquisition instruction and sends the first image acquisition instruction to the second image acquisition device to instruct the second image acquisition device to acquire a palm vein image, and sends the palm vein image to the main controller through a communication connection with the main controller.

[0130] Step 245: Input the palm print image into the first palm recognition model, determine and output the palm print features of the palm to be recognized; input the palm vein image into the second palm recognition model, determine and output the palm vein features of the palm to be recognized; input the palm shape image into the third palm recognition model, determine and output the palm shape features of the palm to be recognized.

[0131] In some embodiments, the first decoder in the third palm recognition model further includes a first branch, which is used to output the coordinates of the key points through heatmap regression or coordinate regression. The key points include the center point of the palm root, the root points of each finger, and the fingertip points. In some embodiments, the main controller can use the third palm recognition model to recognize the palm shape image and obtain palm shape features such as the palm aspect ratio, palm area, the projected length from the root to the fingertip of each finger (thumb to little finger), and their relative proportions.

[0132] In some embodiments, a first palm recognition model (e.g., SqueezeNet) can be used to extract feature vectors of main lines, wrinkles, and minutiae. The first palm recognition model may include shallow convolutional layers and deep convolutional layers; the shallow convolutional layers are used to capture fine-grained edges and textures, while the deep convolutional layers are used to understand the macroscopic structure of the texture. The main controller can use the first palm recognition model to recognize palmprint images and obtain palmprint features such as the distribution of main lines, wrinkles, and minutiae.

[0133] In some embodiments, the second palm recognition model (e.g., MobileNetV2) includes a global average pooling layer and a fully connected layer. The main controller can use the second palm recognition model to recognize palm vein images and obtain vein features such as vein texture, vein bifurcation points, and vein intersection points.

[0134] Step 250: Obtain palm shape fusion weight based on palm shape features, obtain palm print fusion weight based on palm vein features, and obtain vein fusion weight based on palm vein features; based on palm print fusion weight, palm shape fusion weight, and vein fusion weight, fuse palm print features, palm shape features, and vein features to obtain the fusion features corresponding to the palm to be identified.

[0135] In some embodiments, a palmprint image is input into a first palm recognition model, and the palmprint features of the palm to be recognized are output while the palmprint confidence of the palmprint image is obtained, and the palmprint fusion weight is obtained based on the palmprint confidence.

[0136] In some embodiments, a palm vein image is input into a second palm recognition model, and while outputting the palm vein features of the palm to be recognized, the palm vein confidence score of the palm vein image is obtained, and the vein fusion weight is obtained based on the palm vein confidence score.

[0137] In some embodiments, a palm shape image is input into a third palm recognition model, and the palm shape features of the palm to be recognized are output while the palm shape confidence of the palm shape image is obtained. The palm shape fusion weight is obtained based on the palm shape confidence.

[0138] Step 255: Based on the fusion features, obtain the identity recognition result corresponding to the palm to be identified.

[0139] This application also provides an identity verification system.

[0140] like Figure 3 As shown, the identity verification system 300 includes: a main controller 310, a first image acquisition unit 320, and a second image acquisition unit 330; the first image acquisition unit 320 includes a first image acquisition device 321 and a first supplementary lighting component 322; the second image acquisition unit 330 includes a second image acquisition device 331 and a second supplementary lighting component 332. The main controller 310 is used to send a first supplementary light command to the first supplementary light component 322 and the second supplementary light component 332 if the palm to be identified is detected to be within a preset recognition range; The first supplementary lighting component 322 is used to execute the first supplementary lighting instruction upon receiving the first supplementary lighting instruction, and to provide supplementary lighting to the palm to be identified; The second supplementary lighting component 332 is used to execute the first supplementary lighting instruction upon receiving the first supplementary lighting instruction, and to provide supplementary lighting to the palm to be identified. The main controller 310 is also used to send a first image acquisition command to the first image acquisition device 321 and the second image acquisition device 331; The first image acquisition device 321 is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm shape image and palm print image of the hand to be identified, and send the palm shape image and palm print image to the main controller 310. The second image acquisition device 331 is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm vein image of the palm to be identified, and send the palm vein image to the main controller 310. The main controller 310 is also used to acquire palm shape features, palm print features and palm vein features corresponding to the palm to be identified based on palm shape image, palm print image and palm vein image respectively; acquire fusion features corresponding to the palm to be identified based on palm shape features, palm print features and palm vein features; and acquire identity recognition results corresponding to the palm to be identified based on fusion features.

[0141] According to the identity verification system of this application embodiment, when the palm to be identified is detected to be within a preset recognition range, the system provides supplementary lighting to the palm to be identified based on a first supplementary lighting component, acquires palm print images and palm shape images based on a first image acquisition device, provides supplementary lighting to the palm to be identified based on a second supplementary lighting component, acquires palm vein images based on a second image acquisition device, acquires palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, palm print features, and palm vein images, acquires fusion features corresponding to the palm to be identified based on the palm shape features, palm print features, and palm vein features, and acquires identity recognition results corresponding to the palm to be identified based on the fusion features. By providing supplementary lighting to the target object through the first supplementary lighting component and the second supplementary lighting component, the acquired palm print images, palm shape images, and palm vein images are of higher quality. This allows the identity recognition device to acquire high-quality feature images without a complex optical path system and a large imaging distance, thereby reducing the size and cost of the identity recognition device.

[0142] In some embodiments, the main controller is configured to: input palm shape image, palm print image and palm vein image into the corresponding palm recognition model respectively; the palm recognition model includes a region image extraction module and a feature extraction module; obtain local images corresponding to the palm shape image, palm print image and palm vein image respectively through the region image extraction module; and obtain palm shape features, palm print features and palm vein features corresponding to the palm to be recognized based on the local images through the feature extraction module.

[0143] In some embodiments, the main controller is also configured to extract local images corresponding to palm images, palm print images, or palm vein images based on reference points predefined in the region image extraction module.

[0144] In some embodiments, the main controller is used to extract palm shape features, palm print features, or palm vein features from each local image based on the feature extraction neural network in the feature extraction module.

[0145] In some embodiments, the main controller is used for palm shape fusion weight, palm print fusion weight, and vein fusion weight; based on the palm print fusion weight, palm shape fusion weight, and vein fusion weight, the palm print features, palm shape features, and vein features are fused to obtain the fused features corresponding to the palm to be identified.

[0146] In some embodiments, before sending a first supplementary lighting command to the first supplementary lighting component and the second supplementary lighting component if the palm to be identified is detected to be within a preset recognition range, the main controller is further configured to: The real-time distance of the target object is obtained, and the position detection result of the target object is obtained based on the real-time distance; the real-time distance is the distance between the target object and the first image acquisition device. If the location detection result indicates that the target object is within the preset recognition range, a second image acquisition command is sent to the second image acquisition device. The second image acquisition device is used to acquire an image of the first target object upon receiving a second image acquisition command, and to send the image of the first target object to the main controller; The main controller is also used to determine the recognition result based on the image of the first target object.

[0147] In some embodiments, the main controller is further configured to: Using a palm recognition model, the target confidence level of the target object is obtained based on the image of the first target object; If the target confidence level is greater than the confidence level threshold, the recognition result for the target object is determined to be the hand to be recognized.

[0148] In some embodiments, the authentication system further includes a buzzer and indicator lights; the main controller is also used for: If the target object is not within the preset recognition range when the real-time distance indicates that the target is not within the target recognition range, a state switching command is sent to the buzzer and indicator light. The buzzer is used to sound when a state switching command is received; The indicator light is used to switch to the first state upon receiving a state switching command, in order to guide the target object to change its posture.

[0149] In some embodiments, the main controller is also configured to perform a decoding operation on the first target object image when the target object is not the hand to be identified; In the event of decoding failure, a second supplementary lighting command is sent to the first supplementary lighting component, and a third image acquisition command is sent to the first image acquisition device. The first supplementary lighting component is used to provide supplementary lighting to the target object upon receiving a second supplementary lighting instruction. The first image acquisition device is used to acquire an image of the second target object upon receiving a third image acquisition command.

[0150] In some embodiments, the first supplementary lighting component includes several light-emitting arrays, each light-emitting array including a red light-emitting diode, a yellow light-emitting diode, a blue light-emitting diode and at least one white light-emitting diode.

[0151] In some embodiments, such as Figure 4 shown, the first supplementary light component 400 may include a light homogenizing ring 410 and a plurality of light emitting arrays 42i (0 < i ≤ N, where N represents the total number of light emitting arrays), and each light emitting array 42i is mounted on the light homogenizing ring 410.

[0152] In some embodiments, in each light emitting array, red light emitting diodes, yellow light emitting diodes, blue light emitting diodes, and a plurality of white light emitting diodes may be arranged in sequence. For example, in each light emitting array, the light emitting diodes may be arranged in the order of white, red, yellow, blue, and white.

[0153] In some embodiments, the second supplementary light component includes an infrared light emitting diode and at least one convex lens.

[0154] In some embodiments, such as Figure 5 shown, the second supplementary light component 500 includes a base 510, an infrared light emitting diode 520, and two convex lenses 53h (0 < h ≤ 2). The infrared light emitting diode 520 is above the base 510, and the two convex lenses 53h are both above the infrared light emitting diode 520.

[0155] In some embodiments, such as Figure 6 shown, the authentication system 600 includes: a main controller 610, a first image acquisition unit 615, a second image acquisition unit 620, a lens 625, a bottom cover heat sink 630, a housing main body 635, a light homogenizing ring 640, a dust-proof rubber pad 645, a distance measurement sensor 650, and an outer cover glass 655.

[0156] The authentication system in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the scope of the system.

[0157] The authentication system in this application embodiment can be a device with an operating system. This operating system can be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0158] The authentication system provided in this application embodiment can achieve... Figures 1 to 2 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0159] In some embodiments, such as Figure 7 As shown, this application embodiment also provides an electronic device 700, including a processor 701, a memory 702, and a computer program stored on the memory 702 and executable on the processor 701. When the program is executed by the processor 701, it implements the various processes of the above-described authentication method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0160] It should be noted that the computer equipment in this application embodiment includes the mobile electronic equipment and non-mobile electronic equipment described above.

[0161] This application also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described authentication method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0162] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0163] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described authentication method.

[0164] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0165] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described authentication method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0166] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0167] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0168] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0169] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0170] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0171] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. An authentication method, characterized in that, The system is applied to an authentication system, which includes a main controller, a first image acquisition unit, and a second image acquisition unit; the first image acquisition unit includes a first image acquisition device and a first supplementary lighting component. The second image acquisition unit includes a second image acquisition device and a second supplementary lighting component, and the method includes: If the palm to be identified is detected to be within a preset recognition range, a first supplementary light command is sent to the first supplementary light component and the second supplementary light component; the first supplementary light command is used to instruct the first supplementary light component and the second supplementary light component to provide supplementary light to the palm to be identified; Send a first image acquisition command to the first image acquisition device and the second image acquisition device; the first image acquisition command is used to instruct the first image acquisition device to acquire the palm shape image and palm print image of the palm to be identified, and to instruct the second image acquisition device to acquire the palm vein image of the palm to be identified; Receive the palm shape image and palm print image sent by the first image acquisition device, and the palm vein image sent by the second image acquisition device; Based on the palm shape image, the palm print image, and the palm vein image, the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified are obtained respectively; Based on the palm shape feature, the palm print feature, and the palm vein feature, the fusion feature corresponding to the palm to be identified is obtained, and based on the fusion feature, the identity recognition result corresponding to the palm to be identified is obtained.

2. The authentication method according to claim 1, characterized in that, The step of obtaining the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, the palm print image, and the palm vein image, respectively, includes: The palm shape image, the palm print image, and the palm vein image are respectively input into the corresponding palm recognition model; the palm recognition model includes a region image extraction module and a feature extraction module; The region image extraction module obtains local images corresponding to the palm shape image, the palm print image, and the palm vein image, respectively. The feature extraction module obtains the palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the corresponding local image.

3. The authentication method according to claim 2, characterized in that, The step of obtaining local images corresponding to the palm shape image, the palm print image, and the palm vein image through the region image extraction module includes: For the palm shape image, the palm print image, or the palm vein image, based on the reference points predefined in the region image extraction module, extract the corresponding local image of the palm shape image, the palm print image, or the palm vein image.

4. The authentication method according to claim 1, characterized in that, The process of obtaining the fused features corresponding to the palm to be identified based on the palm shape features, palm print features, and palm vein features, and obtaining the identity recognition result corresponding to the palm to be identified based on the fused features, includes: Obtain palm shape fusion weights, palm print fusion weights, and vein fusion weights; Based on the palmprint fusion weight, the palm shape fusion weight, and the vein fusion weight, the palmprint features, the palm shape features, and the vein features are fused to obtain the fused features corresponding to the palm to be identified.

5. The authentication method according to claim 1, characterized in that, Before sending the first supplementary light command to the first supplementary light component and the second supplementary light component if the palm to be identified is detected to be within the preset identification range, the method further includes: The real-time distance of the target object is obtained, and the position detection result of the target object is obtained based on the real-time distance; the real-time distance is the distance between the target object and the first image acquisition device. If the location detection result indicates that the target object is within the preset recognition range, a second image acquisition command is sent to the second image acquisition device; the second image acquisition command is used to instruct the second image acquisition device to acquire a first target object image of the target object. The system receives the first target object image sent by the second image acquisition device and obtains the recognition result for the target object based on the first target object image.

6. The authentication method according to claim 5, characterized in that, The step of receiving the first target object image sent by the second image acquisition device and obtaining the recognition result for the target object based on the first target object image includes: Using a palm recognition model, the target confidence level corresponding to the target object is obtained based on the first target object image; If the target confidence level is greater than the confidence level threshold, the recognition result for the target object is determined to be the hand to be recognized.

7. The authentication method according to claim 5, characterized in that, The authentication system further includes a buzzer and an indicator light; after obtaining the real-time distance of the target object and obtaining the position detection result of the target object based on the real-time distance, the method further includes: If the location detection result indicates that the target object is not within the preset recognition range, a state switching command is sent to the buzzer and the indicator light; the state switching command is used to instruct the buzzer to sound and to instruct the indicator light to switch to the first state, so as to guide the target object to change its posture.

8. The authentication method according to claim 5, characterized in that, After receiving the first target object image sent by the second image acquisition device and determining the recognition result based on the first target object image, the method further includes: If the target object is not the hand to be identified, a decoding operation is performed on the image of the first target object; In the event of a decoding failure, a second supplementary lighting command is sent to the first supplementary lighting component, and a third image acquisition command is sent to the first image acquisition device; the second supplementary lighting command is used to instruct the first supplementary lighting component to provide supplementary lighting to the target object, and the third image acquisition command is used to instruct the first image acquisition device to acquire an image of the second target object.

9. An identity verification system, characterized in that, The system includes: a main controller, a first image acquisition unit and a second image acquisition unit, wherein the first image acquisition unit includes a first image acquisition device and a first supplementary lighting component, and the second image acquisition unit includes a second image acquisition device and a second supplementary lighting component; The main controller is used to send a first supplementary light command to the first supplementary light component and the second supplementary light component if it detects that the palm to be identified is within a preset recognition range; The first supplementary lighting component is used to execute the first supplementary lighting command upon receiving the first supplementary lighting command, and to provide supplementary lighting to the palm to be identified; The second supplementary lighting component is used to execute the first supplementary lighting command upon receiving the first supplementary lighting command, and to provide supplementary lighting to the palm to be identified; The main controller is also used to send a first image acquisition command to the first image acquisition device and the second image acquisition device; The first image acquisition device is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm shape image and palm print image of the hand to be identified, and send the palm shape image and the palm print image to the main controller; The second image acquisition device is used to execute the first image acquisition instruction upon receiving the first image acquisition instruction, acquire the palm vein image of the palm to be identified, and send the palm vein image to the main controller; The main controller is further configured to acquire palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, the palm print image, and the palm vein image, respectively; acquire fusion features corresponding to the palm to be identified based on the palm shape features, the palm print features, and the palm vein features; and acquire the identity recognition result corresponding to the palm to be identified based on the fusion features.

10. The identity verification system according to claim 9, characterized in that, The first supplementary lighting component includes several light-emitting arrays, each of which includes a red light-emitting diode, a yellow light-emitting diode, a blue light-emitting diode, and at least one white light-emitting diode.

11. The identity verification system according to claim 9, characterized in that, The second supplementary lighting component includes an infrared light-emitting diode and at least one convex lens.

Images