Identity verification method and device based on palm vein image and electronic equipment

By monitoring environmental parameters to adjust the fill light intensity, collecting high-quality palm vein images and performing feature matching verification, the identification verification accuracy problem under the influence of environmental factors is solved, and the security of the automatic ticket sales and inspection system is improved.

CN119089420APending Publication Date: 2024-12-06BEIJING URBAN CONSTR INTELLIGENT CONTROL TECH CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411007524.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the acquisition of palm vein images through infrared cameras is susceptible to environmental factors, resulting in a decrease in image quality and thus reducing the accuracy of identity verification.

Method used

By monitoring the target environmental parameters, the target fill light intensity is determined based on the correspondence between environmental parameters and fill light intensity, the fill light is controlled for fill light, the palm vein images are collected, and the shape, texture and topological characteristics are extracted for matching verification.

Benefits of technology

It improves the quality of palm vein images and the accuracy of identity verification, enhances the security of the system, and effectively prevents fraud.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089420A_ABST
    Figure CN119089420A_ABST
Patent Text Reader

Abstract

The invention provides an identity verification method and device based on a palm vein image and electronic equipment, and relates to the technical field of verification, and the method comprises the steps: obtaining a target environment parameter under the condition of monitoring that a target palm exists in a scanning region; determining target light supplementing intensity corresponding to the target environment parameter based on a corresponding relation between the environment parameter and the light supplementing intensity; after a light supplementing lamp is controlled to carry out light supplementing based on the target light supplementing intensity, a palm vein image of the target palm is collected; and performing identity verification on a user corresponding to the target palm based on the palm vein image. According to the invention, the light supplementing intensity corresponding to the light supplementing lamp can be determined based on the target environment parameters collected in real time, so that the quality of the palm vein image is improved, and the accuracy of identity verification based on the palm vein image is further improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of authentication technology, and in particular to an identity authentication method, device and electronic equipment based on palm vein images. Background Art

[0002] In recent years, Palm Vein Recognition (PVR) technology, as a leader in the field of biometrics, has demonstrated significant advantages in security over traditional biometric authentication technologies (such as fingerprint and facial recognition).

[0003] In the related art, in security inspection or automatic ticket vending systems, the user's palm is directly captured by an infrared camera in a palm vein recognition module, and the captured palm vein image of the user's palm is matched with a preset palm vein image to achieve identity authentication based on the palm vein image.

[0004] However, in the above-mentioned related technologies, palm vein images are directly collected by infrared cameras, which makes the collected palm vein images easily affected by environmental factors, thereby reducing the quality of the palm vein images and further reducing the accuracy of identity authentication based on palm vein images. Summary of the invention

[0005] The present invention provides a palm vein image-based identity authentication method, device and electronic device, which are used to solve the defect of reducing the accuracy of palm vein image-based identity authentication in the prior art.

[0006] The present invention provides an identity authentication method based on palm vein images, comprising: When the target palm is detected in the scanning area, the target environment parameters are obtained; Determining a target fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; After controlling the fill light to perform fill light based on the target fill light intensity, collecting a palm vein image of the target palm; The identity of the user corresponding to the target palm is authenticated based on the palm vein image.

[0007] According to a palm vein image-based identity authentication method provided by the present invention, the method of determining the target fill light intensity corresponding to the target environmental parameter based on the corresponding relationship between the environmental parameter and the fill light intensity includes: Determining an initial fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; Acquire an initial image of the target palm, and determine a target skin color brightness of the target palm based on the initial image; Determining the fill light intensity corresponding to the target skin color brightness based on the corresponding relationship between skin color brightness and fill light intensity; The initial fill light intensity is adjusted based on the fill light intensity corresponding to the target skin color brightness to obtain the target fill light intensity.

[0008] According to a palm vein image-based identity authentication method provided by the present invention, the identity authentication of a user corresponding to the target palm based on the palm vein image includes: Extracting shape features, texture features and topological features of a palm vein network in the palm vein image; The shape feature, the texture feature and the topological structure feature are fused to obtain a fused palm vein feature; Matching the fused palm vein feature with each preset palm vein feature to obtain a matching result; If the matching result indicates that there is a preset palm vein feature that successfully matches the fused palm vein feature, determining that the identity authentication of the user is successful; If the matching result indicates that there is no preset palm vein feature that successfully matches the fused palm vein feature, it is determined that the identity authentication of the user has failed.

[0009] According to a palm vein image-based identity authentication method provided by the present invention, the step of extracting shape features, texture features and topological features of a palm vein network in the palm vein image includes: Preprocessing the palm vein image to obtain a target palm vein image; Binarizing the target palm vein image to obtain a binary image, wherein the binary image includes a palm vein area; Detecting the edge of each palm vein in the palm vein area to obtain the edge of each palm vein; Extracting the center line of the corresponding palm vein based on the edge of each palm vein, and constructing the palm vein network based on the center line of each palm vein; The shape features of the palm vein network, the texture features of the palm vein network and the topological structure features of the palm vein network are extracted based on the palm vein network.

[0010] According to a palm vein image-based identity authentication method provided by the present invention, the identity authentication of a user corresponding to the target palm based on the palm vein image includes: Acquire video information of the target palm; Sending an analysis request including the video information to a cloud device, wherein the analysis request is used to instruct the cloud device to determine a blood flow detection result in the target palm based on the video information; receiving the blood flow detection result sent by the cloud device; When the blood flow detection result indicates that the blood in the target palm is in a flowing state, identity authentication of a user corresponding to the target palm is performed based on the palm vein image.

[0011] According to a palm vein image-based identity authentication method provided by the present invention, matching the fused palm vein feature with each preset palm vein feature to obtain a matching result includes: Performing dimension reduction on the fused palm vein feature to obtain a dimension reduced palm vein feature; Inputting the dimension-reduced palm vein feature into a feature enhancement model to obtain an enhanced palm vein feature output by the feature enhancement model, wherein the feature enhancement model is trained based on sample palm vein features; The enhanced palm vein feature is matched with each of the preset palm vein features to obtain the matching result.

[0012] The present invention also provides an identity verification device based on a palm vein image, comprising: An acquisition unit, used for acquiring target environment parameters when detecting the presence of a target palm in the scanning area; A determination unit, configured to determine a target fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; A collection unit, configured to collect a palm vein image of the target palm after controlling the fill light to perform fill light based on the target fill light intensity; A verification unit is used to authenticate the identity of a user corresponding to the target palm based on the palm vein image.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the identity authentication method based on palm vein images as described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the identity verification method based on palm vein images as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned identity authentication methods based on palm vein images.

[0016] The palm vein image-based identity authentication method, device, and electronic device provided by the present invention acquire target environment parameters when the target palm is detected in the scanning area, determine the target fill light intensity corresponding to the target environment parameters based on the corresponding relationship between the environment parameters and the fill light intensity, and after controlling the fill light to perform fill light based on the target fill light intensity, collect the palm vein image of the target palm, and perform identity authentication on the user corresponding to the target palm based on the palm vein image. It can be seen that the present invention can determine the fill light intensity corresponding to the fill light based on the target environment parameters collected in real time, so as to improve the quality of the palm vein image, and further improve the accuracy of identity authentication based on the palm vein image. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is one of the flow charts of the identity authentication method based on palm vein images provided in an embodiment of the present invention.

[0019] Figure 2 This is the second flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention.

[0020] Figure 3 This is the third flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention.

[0021] Figure 4 This is the fourth flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention.

[0022] Figure 5 It is a schematic diagram of the structure of an identity verification device based on palm vein images provided in an embodiment of the present invention.

[0023] Figure 6 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In the Automatic Fare Collection (AFC) system, the implementation of palm vein recognition technology has greatly simplified the passenger's passage process. Passengers can complete identity verification and ticket deduction without contact by simply waving their palms. This not only shortens the gate time and improves the efficiency of passage during peak hours, but also effectively avoids congestion caused by queuing for ticket purchase and ticket verification, making public transportation smoother and more convenient. In addition, palm vein recognition technology can reduce the dependence on physical tickets and reduce the cost of ticket production, issuance, recycling and processing. At the same time, the increase in automation also reduces the need for manual intervention and reduces operating and maintenance costs. In addition, given the difficult-to-copy nature of palm veins, this technology significantly enhances the security of the automatic ticket collection system, effectively curbs theft and fraud, and ensures the safety of passengers' funds. More importantly, the application of palm vein recognition technology in the AFC system uses a contactless verification method to minimize the risk of contact transmission on the surface of public objects, providing passengers with a healthier and safer travel environment. At the same time, the integration of this technology also contributes to the construction of smart cities, promotes the development of urban transportation in a smarter and greener direction, and demonstrates the infinite possibilities of future travel modes.

[0026] In the related art, palm vein images are directly collected by infrared cameras, which makes the collected palm vein images easily affected by environmental factors, thereby reducing the quality of the palm vein images and further reducing the accuracy of identity authentication based on palm vein images.

[0027] Based on this, the present invention proposes an identity authentication method based on palm vein images, which can determine the fill light intensity corresponding to the fill light based on the target environment parameters collected in real time, so as to improve the quality of the palm vein images and further improve the accuracy of identity authentication based on palm vein images.

[0028] Combine the following Figure 1-Figure 4 The palm vein image-based identity authentication method of the present invention is described. The execution subject of the palm vein image-based identity authentication method can be an electronic device such as a security inspection terminal or a server, or it can be an identity authentication device based on a palm vein image set in the electronic device. The identity authentication device based on a palm vein image can be implemented by software, hardware, or a combination of the two.

[0029] Figure 1 FIG. 1 is one of the flow charts of the identity authentication method based on palm vein image provided by an embodiment of the present invention, such as Figure 1 As shown, the palm vein image-based identity authentication method includes the following steps: Step 101: When a target palm is detected in a scanning area, target environment parameters are obtained.

[0030] For example, a scanning area is provided on the palm vein recognition module, and a high-sensitivity infrared camera or infrared sensor is provided in the palm vein recognition module. The infrared sensor can effectively enhance the visibility of the palm vein structure in the image. In actual application, the user unfolds the target palm and covers it in the scanning area of ​​the palm vein recognition module, ensuring that the fingers are open so as to fully display the vein distribution. When the infrared camera or infrared sensor collects the palm vein image hidden under the skin of the target palm, it sends a message of monitoring the target palm to the processing module of the electronic device. When receiving the message, the processing module determines that the target palm exists in the scanning area. At this time, the target sensor is controlled to collect the target environmental parameters. Considering that the ambient temperature and ambient brightness will affect the instructions of the palm vein image, the target sensor can be a temperature sensor and / or a brightness sensor. The ambient temperature is collected by the temperature sensor, and the ambient brightness is collected by the brightness sensor.

[0031] It should be noted that the infrared camera may be a near-infrared camera, which is a light source type for palm vein imaging and can penetrate the surface of the skin without damaging the skin. The infrared sensor may be a charge-coupled device (CCD) for capturing palm vein images under near-infrared light.

[0032] Step 102: Determine a target fill light intensity corresponding to the target environment parameter based on the corresponding relationship between the environment parameter and the fill light intensity.

[0033] For example, taking the target environment parameter as the target environment brightness, the fill light intensity of the fill light is adjusted under different environment brightness, and the quality parameters of the corresponding reference palm vein image are recorded. The quality parameters may be brightness, contrast, signal-to-noise ratio, etc. These experimental data are statistically analyzed to find the corresponding relationship between the environment brightness and the fill light intensity. Using the same method, the corresponding relationship between the environment temperature and the fill light intensity, or the corresponding relationship between the environment brightness, the environment temperature and the fill light intensity can be obtained. The corresponding relationship between the environment parameters and the fill light intensity obtained in the experiment is stored. The corresponding relationship between the environment parameters and the fill light intensity includes the corresponding relationship between the environment brightness and the fill light intensity, the corresponding relationship between the environment temperature and the fill light intensity, or the corresponding relationship between the environment brightness, the environment temperature and the fill light intensity.

[0034] When the target environment parameters are obtained, taking the target environment parameters as the target environment brightness as an example, the target fill light intensity corresponding to the target environment brightness is searched in the corresponding relationship between the environment brightness and the fill light intensity. It should be noted here that when the target environment brightness is brighter, the corresponding target fill light intensity is a negative value, and when the target environment brightness is darker, the corresponding target fill light intensity is a positive value. The brightness of the target environment brightness can be determined based on the reference environment brightness, that is, when the target environment brightness is greater than the reference environment brightness, the target environment brightness is considered to be brighter, and when the target environment brightness is less than the reference environment brightness, the target environment brightness is considered to be darker.

[0035] Step 103: After controlling the fill light to perform fill light based on the target fill light intensity, a palm vein image of the target palm is collected.

[0036] For example, when the target fill light intensity corresponding to the target environment brightness is obtained, the fill light is controlled to output the target fill light intensity to achieve accurate fill light, and after the fill light is provided, the infrared camera or infrared sensor is controlled to collect the palm vein image of the target palm.

[0037] It should be noted that the fill light can be set on the light guide, and the light guide can be controlled to rotate to a certain position based on the ambient brightness, so that the lighting of the fill light is more uniform.

[0038] Step 104: Authentication of the user corresponding to the target palm is performed based on the palm vein image.

[0039] For example, when a palm vein image of the target palm is captured, the palm vein image can be matched with each preset palm vein image. When it is determined that there is a preset palm vein image that matches the palm vein image, it is determined that the user's identity authentication is successful. When it is determined that there is no preset palm vein image that matches the palm vein image, it is determined that the user's identity authentication has failed.

[0040] It should be noted that in order to improve the accuracy and robustness of identity authentication, a multimodal fusion method can also be used, that is, when it is determined that there is a preset palm vein image that matches the palm vein image, it is also necessary to obtain other biometric features of the user (such as fingerprint features and / or facial recognition features, etc.), and match the other biometric features with the preset biometric features. Only when there are preset biometric features that match other biometric features, and the preset biometric features that match other biometric features and the preset palm vein image that matches the palm vein image are for the same user, is it determined that the user's identity authentication is successful, thereby further improving the accuracy of identity authentication.

[0041] It should be noted that when the current processing power of the electronic device is low, the palm vein image can also be encrypted and sent to the cloud device, and the decrypted palm vein image is matched with each preset palm vein image through the cloud device, and the matching result is returned to the electronic device. The use of encryption technology can protect the security of the user's palm vein image and ensure the confidentiality and integrity of the user's palm vein image during transmission and storage. Cloud devices have huge computing resources and can process massive amounts of data. They are suitable for complex calculations such as big data analysis and machine learning, and are suitable for processing cross-regional and cross-system data integration and analysis tasks. Cloud data can be accessed anytime and anywhere, facilitating collaboration and data sharing between multiple locations and multiple users, which is conducive to decision support and remote monitoring. Cloud devices usually provide high-level data encryption, backup and recovery services to ensure data security and business continuity.

[0042] It should be noted that the electronic device also has an error handling mechanism, which locks the account or starts a higher-level identity authentication process after multiple authentication failures for the same user, and records the log information of each identity authentication, including time, user information, verification results, etc., for auditing and troubleshooting, but the present invention is not limited to this.

[0043] It should be noted that the palm vein images of the target palms of each user and the collection time collected can also be stored correspondingly, so that public transportation operators can better analyze passenger behavior based on the palm vein images of the target palms of each user collected and the collection time, so as to optimize route planning and operation time, etc., and formulate personalized services to improve the overall service quality.

[0044] The palm vein image identity authentication method, device and electronic device provided by the present invention acquire target environment parameters when the target palm is detected in the scanning area, determine the target fill light intensity corresponding to the target environment parameters based on the corresponding relationship between the environment parameters and the fill light intensity, and after controlling the fill light to perform fill light based on the target fill light intensity, collect the palm vein image of the target palm, and perform identity authentication on the user corresponding to the target palm based on the palm vein image. It can be seen that the present invention can determine the fill light intensity corresponding to the fill light based on the target environment parameters collected in real time to improve the quality of the palm vein image, further improve the accuracy of identity authentication based on the palm vein image, and the identity authentication method can be applied to the automatic ticket vending and checking system to improve the security of the automatic ticket vending and checking system, effectively prevent fraud, and protect the property safety of passengers.

[0045] In one embodiment, Figure 2 FIG. 2 is a flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention. Figure 2As shown, the above step 102 determines the target fill light intensity corresponding to the target environmental parameter based on the corresponding relationship between the environmental parameter and the fill light intensity, which can be specifically achieved by the following steps: Step 1021: Determine an initial fill light intensity corresponding to the target environment parameter based on the corresponding relationship between the environment parameter and the fill light intensity.

[0046] For example, based on the correspondence between the environmental parameters and the fill-light intensity, the fill-light intensity corresponding to the target environmental parameters is determined, and the fill-light intensity corresponding to the target environmental parameters is used as the initial fill-light intensity.

[0047] Step 1022: Acquire an initial image of the target palm, and determine the target skin color brightness of the target palm based on the initial image.

[0048] For example, an initial image of the target palm is captured by a camera, and the initial image is converted from an RGB (red, green, and blue) color space to a color space that is more suitable for skin color analysis, such as a hue saturation value (HSV) color space. In the HSV color space, the V component represents brightness. A representative brightness value can be obtained by calculating the average or median brightness values ​​of all pixels in the skin color area in the initial image of the HSV color space, and the brightness value is determined as the target skin color brightness of the target palm.

[0049] Step 1023: Determine the fill light intensity corresponding to the target skin color brightness based on the correspondence between the skin color brightness and the fill light intensity.

[0050] For example, the fill light intensity of the fill light is adjusted in advance under different skin colors, and the quality parameters of the corresponding reference palm vein image are recorded. The quality parameters may be brightness, contrast, signal-to-noise ratio, etc. These experimental data are statistically analyzed to find the corresponding relationship between skin color brightness and fill light intensity, and the determined corresponding relationship between skin color brightness and fill light intensity is stored. When the target skin color brightness of the target palm is obtained, the fill light intensity corresponding to the target skin color brightness is found in the corresponding relationship between skin color brightness and fill light intensity.

[0051] Step 1024: Adjust the initial fill light intensity based on the fill light intensity corresponding to the target skin color brightness to obtain the target fill light intensity.

[0052] For example, when the fill light intensity and the initial fill light intensity corresponding to the target skin color brightness are obtained, the fill light intensity and the initial fill light intensity corresponding to the target skin color brightness are superimposed to obtain the target fill light intensity. It should be noted here that when the target skin color brightness is brighter, the corresponding fill light intensity is a negative value, and when the target skin color brightness is darker, the corresponding fill light intensity is a positive value. The brightness of the target skin color brightness can be determined based on the reference skin color brightness, that is, when the target skin color brightness is greater than the reference skin color brightness, the target skin color brightness is considered to be brighter, and when the target skin color brightness is less than the reference skin color brightness, the target skin color brightness is considered to be darker.

[0053] In one embodiment, based on the correspondence between skin color brightness and fill light intensity, the fill light intensity corresponding to the target skin color brightness of the target palm can be determined, and the initial fill light intensity corresponding to the target environmental parameters can be corrected, so that the final target fill light brightness is more in line with the user, the quality of the palm vein image is improved, and the accuracy of identity authentication based on the palm vein image is further improved.

[0054] In one embodiment, Figure 3 FIG. 3 is a flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention. Figure 3 As shown, the above step 104 performs identity authentication on the user corresponding to the target palm based on the palm vein image, which can be specifically implemented by the following steps: Step 1041: extracting shape features, texture features, and topological features of the palm vein network in the palm vein image.

[0055] For example, the palm vein network is a unique network structure formed by the veins inside the human palm. These veins grow randomly according to physiological needs during the embryonic period, and become longer or thicker as the human body develops after birth, but the distribution and shape of the network are basically stable after adulthood and no longer change significantly. The shape characteristics of the palm vein network mainly include geometric characteristics such as the direction, length, curvature, branches and intersections of the veins. The shape characteristics of each person's palm vein network are unique, providing a basis for personal identification. The texture characteristics of the palm vein network refer to the unique texture patterns formed by the palm vein network on the palm surface. These texture patterns are determined by factors such as the thickness, density and distribution of the veins. The texture characteristics of the palm vein network have high complexity and uniqueness, making the texture characteristics of each person's palm vein network unique. Texture features can be extracted based on local binary patterns (LBP) or Gabor filtering to reflect the microstructure of palm veins.

[0056] The topological structural characteristics of the palmar venous network refer to the connection relationship, branching order and overall layout between venous vessels. This topological structural feature not only includes the number and distribution of venous vessels, but also the connectivity and hierarchical relationship between blood vessels, and has high stability.

[0057] Step 1042: Fuse the shape feature, the texture feature, and the topological structure feature to obtain a fused palm vein feature.

[0058] For example, when the shape features, texture features and topological structure features of the palm vein network in the palm vein image are extracted, the shape features, texture features and topological structure features are combined or spliced ​​to obtain a fused palm vein feature.

[0059] Step 1043: Match the fused palm vein feature with each preset palm vein feature to obtain a matching result.

[0060] For example, when the fused palm vein feature of the target palm is obtained, the fused palm vein feature is matched with each preset palm vein feature to obtain a matching result between each preset palm vein feature and the fused palm vein feature. Matching algorithms include but are not limited to Euclidean distance, cosine similarity or Hamming distance. These matching algorithms can measure the similarity between the fused palm vein feature and the preset palm vein feature to determine whether they match. If the calculated distance or similarity score is less than or equal to a threshold, the match is considered to have failed. If the calculated distance or similarity score is greater than the threshold, the match is considered to have succeeded.

[0061] Step 1044: When the matching result indicates that there is a preset palm vein feature that successfully matches the fused palm vein feature, determine that the identity authentication of the user is successful.

[0062] For example, when the matching result indicates that there is a preset palm vein feature that successfully matches the fused palm vein feature, it means that the user corresponding to the target palm is legitimate, and the user's identity authentication is determined to be successful. A message of successful identity authentication can be fed back to the user through an indicator light, screen display, or voice.

[0063] Step 1045: If the matching result indicates that there is no preset palm vein feature that successfully matches the fused palm vein feature, determine that the user's identity authentication fails.

[0064] For example, when the matching result indicates that there is no preset palm vein feature that successfully matches the fused palm vein feature, it means that the user corresponding to the target palm is illegal, and the user's identity authentication fails. The user can be informed of the identity authentication failure through indicator lights, screen displays or voice, and the user can be reminded to provide other identity proof information or collect a new palm vein image for re-verification.

[0065] In this embodiment, the shape features, texture features and topological structure features of the palm vein network are fused to obtain a fused palm vein feature, and the fused palm vein feature is matched with each preset palm vein feature to make the matching result more accurate.

[0066] In one embodiment, Figure 4 FIG. 4 is a flow chart of the identity authentication method based on palm vein images provided in an embodiment of the present invention. Figure 4 As shown, the above step 1041 extracts the shape features, texture features and topological features of the palm vein network in the palm vein image, which can be specifically achieved by the following steps: Step 401: pre-process the palm vein image to obtain a target palm vein image.

[0067] For example, the palm vein image is preprocessed. First, the preprocessing includes denoising, smoothing and edge detection operations to reduce noise and highlight the boundaries of blood vessels. Second, the preprocessing also includes converting the palm vein image after denoising, smoothing and edge detection operations into a grayscale image to reduce processing complexity, and then using denoising techniques such as high-pass filtering or band-stop filtering to remove random noise in the grayscale image. The vein structure in the filtered grayscale image is then separated by a background subtraction algorithm. The background subtraction algorithm can be a difference method or a segmentation based on a skin color model. The contrast of the image corresponding to the vein structure is then enhanced to make the vein structure more prominent, and finally the target palm vein image is obtained.

[0068] Step 402: binarize the target palm vein image to obtain a binarized image, wherein the binarized image includes a palm vein area.

[0069] For example, first, at least one threshold value is determined, and the threshold value is used to divide the grayscale range of image pixels to determine which pixels are classified as foreground (usually objects of interest) and which pixels are classified as background; then, the grayscale value of each pixel in the target palm vein image is compared with the threshold value. If the grayscale value of the pixel is less than the threshold value, the pixel is classified as background; if the grayscale value of the pixel is greater than or equal to the threshold value, the pixel is classified as foreground; according to the classification result of each pixel, the foreground type pixel is set to a first specific value (for example, 255, indicating white), and the background type pixel is set to a second specific value (for example, 0, indicating black), and a binary image is obtained, that is, an image containing only black and white colors is obtained, and the white part is the palm vein area, and the palm vein area is also the region of interest (ROI). Among them, the threshold value is adjusted as the content or external conditions of the target palm vein image change. For example, the threshold value can be dynamically adjusted based on the image histogram. Threshold segmentation is widely used in image analysis, image segmentation, object recognition, text recognition, medical image processing and other fields, especially in image processing tasks with obvious grayscale differences between the target and the background.

[0070] Step 403: Detect the edge of each palm vein in the palm vein area to obtain the edge of each palm vein.

[0071] For example, an edge detection algorithm may be used to detect the edge of each palm vein in the palm vein region to obtain the edge of each palm vein. The edge detection algorithm may be, for example, Canny edge detection.

[0072] Step 404: extract the center line of the corresponding palm vein based on the edge of each palm vein, and construct the palm vein network based on the center line of each palm vein.

[0073] For example, through the thinning algorithm, the center line of the corresponding palm vein is extracted based on the edge of each palm vein to form the skeleton of the venous network. The thinning algorithm is a technology used in image processing, especially in the processing of binary images (i.e. black and white images), the purpose is to thin the lines, edges, etc. in the binary image into a line of pixel width. This process is also called skeletonization or medial axis transformation of the image. The main goal of the thinning algorithm is to reduce the width of the lines in the image while maintaining its connectivity and topological structure, and finally obtain a palm vein network constructed based on the center line of each palm vein.

[0074] Step 405: extracting shape features of the palm vein network, texture features of the palm vein network, and topological features of the palm vein network based on the palm vein network.

[0075] For example, when the palm vein network is obtained, image analysis is performed on the palm vein network to extract shape features of the palm vein network, texture features of the palm vein network, and topological features of the palm vein network.

[0076] In one embodiment, a palm vein image is preprocessed to obtain a target palm vein image, the target palm vein image is binarized to obtain a binary image, the edges of each palm vein in a palm vein area of ​​the binary image are detected to obtain the edges of each palm vein, the center line of the corresponding palm vein is extracted based on the edge of each palm vein, and a palm vein network is constructed based on the center line of each palm vein, and finally, shape features of the palm vein network, texture features of the palm vein network, and topological structure features of the palm vein network are extracted based on the palm vein network, so that the extracted features are more accurate.

[0077] In one embodiment, the above step 104 performs identity authentication on the user corresponding to the target palm based on the palm vein image, which can be specifically implemented in the following manner: Acquire video information for the target palm; send an analysis request including the video information to a cloud device, wherein the analysis request is used to instruct the cloud device to determine a blood flow detection result in the target palm based on the video information; receive the blood flow detection result sent by the cloud device; and authenticate the user corresponding to the target palm based on the palm vein image when the blood flow detection result indicates that the blood in the target palm is in a flowing state.

[0078] For example, video information of the target palm is captured by a near-infrared camera, and the video information of the target palm is carried in an analysis request and sent to a cloud device. When the cloud device receives the analysis request sent by the electronic device, it parses the analysis request to obtain the video information of the target palm, and sends the video information of the target palm to the near-infrared imaging device. When the near-infrared imaging device receives the video information of the target palm, it performs near-infrared image processing on each frame of the video information of the target palm, analyzes the near-infrared light intensity and pattern changes of the palm area in each frame, determines the blood flow detection result based on the near-infrared light intensity and pattern changes of the palm area in each frame, and sends the blood flow detection result to the electronic device through the cloud device. When the electronic device determines that the blood flow detection result indicates that the blood in the target palm is in a flowing state, it indicates that the target palm is a legitimate palm and liveness detection is achieved. At this time, the identity of the user corresponding to the target palm is authenticated based on the palm vein image to avoid forgery attacks caused by counterfeit palms.

[0079] In one embodiment, before the identity of the user corresponding to the target palm is authenticated based on the palm vein image, liveness detection is first performed based on the video information of the target palm to ensure that the palm vein image involved in the identity authentication comes from the real user, avoid forgery attacks caused by counterfeit palms, and further improve the accuracy of identity authentication.

[0080] In one embodiment, the above step 1043 matches the fused palm vein feature with each preset palm vein feature to obtain a matching result, which can be specifically achieved by the following method: The fused palm vein feature is dimensionally reduced to obtain a reduced-dimensional palm vein feature; the reduced-dimensional palm vein feature is input into a feature enhancement model to obtain an enhanced palm vein feature output by the feature enhancement model, wherein the feature enhancement model is trained based on sample palm vein features; the enhanced palm vein feature is matched with each of the preset palm vein features to obtain the matching result.

[0081] For example, when the fused palm vein feature is obtained, the fused palm vein feature is reduced in dimension by using a dimensionality reduction technique to obtain a reduced-dimensional palm vein feature. The dimensionality reduction technique may be principal component analysis (PCA) or linear discriminant analysis (LDA) or t-distributed stochastic neighbor embedding (t-SNE) and other techniques to reduce the feature dimension while retaining as much information as possible. The reduced-dimensional palm vein feature is then input into a pre-trained feature enhancement model to obtain an enhanced palm vein feature output by the feature enhancement model, so that the enhanced palm vein feature includes a more complex palm vein feature. The enhanced palm vein feature is matched with each preset palm vein feature. When it is determined that there is a preset palm vein feature that matches the enhanced palm vein feature, it is determined that the user's identity authentication is successful. When it is determined that there is no preset palm vein feature that matches the enhanced palm vein feature, it is determined that the user's identity authentication fails.

[0082] It should be noted that the specific training method of the feature enhancement model is: obtain multiple sample images including palm veins, input the multiple sample images into the initial feature enhancement model, obtain the predicted enhanced palm vein features output by the initial feature enhancement model, generate a predicted image based on the predicted enhanced palm vein features, construct a loss function based on the predicted image and the corresponding sample image, adjust the model parameters of the initial feature enhancement model based on the loss function, and finally obtain the feature enhancement model.

[0083] It should be noted that the initial feature enhancement model can be constructed based on deep learning technologies such as convolutional neural network (CNN) or recurrent neural network (RNN), and the present invention is not limited to this.

[0084] In this embodiment, the fused palm vein features are dimensionally reduced, and the dimensionally reduced palm vein features are input into the feature enhancement model to obtain enhanced palm vein features output by the feature enhancement model. The enhanced palm vein features are matched with each preset palm vein feature to obtain a matching result, thereby further improving the matching accuracy.

[0085] The following is a description of the identity authentication device based on a palm vein image provided by the present invention. The identity authentication device based on a palm vein image described below and the identity authentication method based on a palm vein image described above can be referred to in correspondence with each other.

[0086] Figure 5 is a schematic diagram of the structure of an identity verification device based on palm vein images provided by an embodiment of the present invention, such as Figure 5 As shown, the palm vein image-based identity authentication device 500 includes an acquisition unit 501, a determination unit 502, a collection unit 503 and a verification unit 504; wherein: An acquisition unit 501 is used to acquire target environment parameters when a target palm is detected in the scanning area; A determination unit 502, configured to determine a target fill light intensity corresponding to the target environment parameter based on a correspondence between the environment parameter and the fill light intensity; The acquisition unit 503 is used to acquire the palm vein image of the target palm after controlling the fill light to perform fill light based on the target fill light intensity; The verification unit 504 is configured to verify the identity of the user corresponding to the target palm based on the palm vein image.

[0087] The palm vein image-based identity authentication device provided by the present invention acquires target environment parameters when detecting the presence of a target palm in a scanning area, determines the target fill light intensity corresponding to the target environment parameters based on the corresponding relationship between the environment parameters and the fill light intensity, and after controlling the fill light to perform fill light based on the target fill light intensity, acquires the palm vein image of the target palm, and performs identity authentication on the user corresponding to the target palm based on the palm vein image. It can be seen that the present invention can determine the fill light intensity corresponding to the fill light based on the target environment parameters acquired in real time, so as to improve the quality of the palm vein image, and further improve the accuracy of identity authentication based on the palm vein image.

[0088] Based on any of the foregoing embodiments, the determining unit 502 is specifically configured to: Determining an initial fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; Acquire an initial image of the target palm, and determine a target skin color brightness of the target palm based on the initial image; Determining the fill light intensity corresponding to the target skin color brightness based on the corresponding relationship between skin color brightness and fill light intensity; The initial fill light intensity is adjusted based on the fill light intensity corresponding to the target skin color brightness to obtain the target fill light intensity.

[0089] Based on any of the above embodiments, the verification unit 504 is specifically used for: Extracting shape features, texture features and topological features of a palm vein network in the palm vein image; Fusing the shape feature, the texture feature and the topological structure feature to obtain a fused palm vein feature; Matching the fused palm vein feature with each preset palm vein feature to obtain a matching result; If the matching result indicates that there is a preset palm vein feature that successfully matches the fused palm vein feature, determining that the identity authentication of the user is successful; If the matching result indicates that there is no preset palm vein feature that successfully matches the fused palm vein feature, it is determined that the identity authentication of the user has failed.

[0090] Based on any of the above embodiments, the verification unit 504 is further specifically configured to: Preprocessing the palm vein image to obtain a target palm vein image; Binarizing the target palm vein image to obtain a binary image, wherein the binary image includes a palm vein area; Detecting the edge of each palm vein in the palm vein area to obtain the edge of each palm vein; Extracting the center line of the corresponding palm vein based on the edge of each palm vein, and constructing the palm vein network based on the center line of each palm vein; The shape features of the palm vein network, the texture features of the palm vein network and the topological structure features of the palm vein network are extracted based on the palm vein network.

[0091] Based on any of the above embodiments, the verification unit 504 is further specifically configured to: Acquire video information of the target palm; Sending an analysis request including the video information to a cloud device, wherein the analysis request is used to instruct the cloud device to determine a blood flow detection result in the target palm based on the video information; receiving the blood flow detection result sent by the cloud device; When the blood flow detection result indicates that the blood in the target palm is in a flowing state, identity authentication of a user corresponding to the target palm is performed based on the palm vein image.

[0092] Based on any of the above embodiments, the verification unit 504 is further specifically configured to: Performing dimension reduction on the fused palm vein feature to obtain a dimension reduced palm vein feature; Inputting the dimension-reduced palm vein feature into a feature enhancement model to obtain an enhanced palm vein feature output by the feature enhancement model, wherein the feature enhancement model is trained based on sample palm vein features; The enhanced palm vein feature is matched with each of the preset palm vein features to obtain the matching result.

[0093] Figure 6 is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the identity authentication method based on the palm vein image, the method comprising: obtaining the target environment parameter when the target palm is detected in the scanning area; determining the target fill light intensity corresponding to the target environment parameter based on the corresponding relationship between the environment parameter and the fill light intensity; after controlling the fill light to perform fill light based on the target fill light intensity, collecting the palm vein image of the target palm; and authenticating the user corresponding to the target palm based on the palm vein image.

[0094] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0095] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the palm vein image-based identity authentication method provided by the above-mentioned methods, and the method includes: when a target palm is detected in the scanning area, obtaining target environmental parameters; based on the correspondence between environmental parameters and fill light intensity, determining the target fill light intensity corresponding to the target environmental parameters; after controlling the fill light to perform fill light based on the target fill light intensity, collecting the palm vein image of the target palm; and authenticating the user corresponding to the target palm based on the palm vein image.

[0096] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the palm vein image-based identity authentication method provided by the above-mentioned methods, the method comprising: acquiring target environmental parameters when a target palm is detected in a scanning area; determining a target fill light intensity corresponding to the target environmental parameters based on a correspondence between environmental parameters and fill light intensity; after controlling the fill light to perform fill light based on the target fill light intensity, acquiring a palm vein image of the target palm; and authenticating the user corresponding to the target palm based on the palm vein image.

[0097] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0098] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An identity authentication method based on palm vein image, characterized in that: include: When the target palm is detected in the scanning area, the target environment parameters are obtained; Determining a target fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; After controlling the fill light to perform fill light based on the target fill light intensity, collecting a palm vein image of the target palm; The identity of the user corresponding to the target palm is authenticated based on the palm vein image.

2. The identity authentication method based on palm vein image according to claim 1, characterized in that: The determining, based on the correspondence between the environmental parameter and the fill light intensity, the target fill light intensity corresponding to the target environmental parameter includes: Determining an initial fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; Acquire an initial image of the target palm, and determine a target skin color brightness of the target palm based on the initial image; Determining the fill light intensity corresponding to the target skin color brightness based on the corresponding relationship between skin color brightness and fill light intensity; The initial fill light intensity is adjusted based on the fill light intensity corresponding to the target skin color brightness to obtain the target fill light intensity.

3. The identity authentication method based on palm vein image according to claim 1, characterized in that: The identity verification of the user corresponding to the target palm based on the palm vein image includes: Extracting shape features, texture features and topological features of a palm vein network in the palm vein image; Fusing the shape feature, the texture feature and the topological structure feature to obtain a fused palm vein feature; Matching the fused palm vein feature with each preset palm vein feature to obtain a matching result; If the matching result indicates that there is a preset palm vein feature that successfully matches the fused palm vein feature, determining that the identity authentication of the user is successful; If the matching result indicates that there is no preset palm vein feature that successfully matches the fused palm vein feature, it is determined that the identity authentication of the user has failed.

4. The identity authentication method based on palm vein image according to claim 3, characterized in that: The step of extracting the shape features, texture features and topological features of the palm vein network in the palm vein image includes: Preprocessing the palm vein image to obtain a target palm vein image; Binarizing the target palm vein image to obtain a binary image, wherein the binary image includes a palm vein area; Detecting the edge of each palm vein in the palm vein area to obtain the edge of each palm vein; Extracting the center line of the corresponding palm vein based on the edge of each palm vein, and constructing the palm vein network based on the center line of each palm vein; The shape features of the palm vein network, the texture features of the palm vein network and the topological structure features of the palm vein network are extracted based on the palm vein network.

5. The identity authentication method based on palm vein image according to any one of claims 1 to 4, characterized in that: The identity verification of the user corresponding to the target palm based on the palm vein image includes: Acquire video information of the target palm; Sending an analysis request including the video information to a cloud device, wherein the analysis request is used to instruct the cloud device to determine a blood flow detection result in the target palm based on the video information; receiving the blood flow detection result sent by the cloud device; When the blood flow detection result indicates that the blood in the target palm is in a flowing state, identity authentication of a user corresponding to the target palm is performed based on the palm vein image.

6. The identity authentication method based on palm vein image according to claim 3, characterized in that: The step of matching the fused palm vein feature with each preset palm vein feature to obtain a matching result includes: Performing dimension reduction on the fused palm vein feature to obtain a dimension reduced palm vein feature; Inputting the dimension-reduced palm vein feature into a feature enhancement model to obtain an enhanced palm vein feature output by the feature enhancement model, wherein the feature enhancement model is trained based on sample palm vein features; The enhanced palm vein feature is matched with each of the preset palm vein features to obtain the matching result.

7. An identity verification device based on palm vein images, characterized in that: include: An acquisition unit, used for acquiring target environment parameters when detecting the presence of a target palm in the scanning area; A determination unit, configured to determine a target fill light intensity corresponding to the target environmental parameter based on a correspondence between the environmental parameter and the fill light intensity; A collection unit, configured to collect a palm vein image of the target palm after controlling the fill light to perform fill light based on the target fill light intensity; A verification unit is used to authenticate the identity of a user corresponding to the target palm based on the palm vein image.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the identity authentication method based on palm vein image as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the palm vein image-based identity authentication method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the palm vein image-based identity authentication method according to any one of claims 1 to 6 is implemented.

Citation Information

Cited By

  • Method and system for testing static electricity of human body based on identity recognition of palm vein

    CN120514372A

  • Palm vein rapid identification method and device based on multistage feature index

    CN121214507A

  • A palm vein fast recognition method and device based on multi-level feature index

    CN121214507B

  • High-security scene-oriented non-inductive identity verification and closed-loop management method and system

    CN121545194A